CN114943809A - Map model generation method and device and storage medium - Google Patents

Abstract

The present application provides a method, device and storage medium for generating a map model, which relate to the field of communications and are used to improve the accuracy of a map model (eg, a three-dimensional model). The method includes: acquiring a plurality of first images and a plurality of first positions, the plurality of first images include a first object to be rescued and a scene object, the first position is a position where the first images are collected, the plurality of first positions and the plurality of first positions are corresponding to the first image. A first map model is generated according to the plurality of first images and the plurality of first locations, the first map model is used to reflect the disaster scene, and the first map model includes scene objects. Acquire location information of the first object to be rescued. The first map model is processed according to the position information of the first object to be rescued to generate a second map model, where the second map model includes the position information of the first object to be rescued, the first object to be rescued and the scene object.

Description

A method, device and storage medium for generating a map model

technical field

The present application relates to the field of communications, and in particular, to a method, device and storage medium for generating a map model.

Background technique

In recent years, with the development of drone technology, drones can be used in a variety of scenarios. For example, after disasters such as earthquakes, floods, and mudslides occur, rescuers can learn about the scene through videos collected by drones.

At present, when the drone is at the disaster site, it needs to collect video first, and then transmit the collected video back to the terminal. After that, rescuers can learn about the situation at the disaster site and make rescue plans based on the video content played on the terminal. However, in the above technical solution, the drone only collects the video of the disaster scene, and the amount of information collected is small, which seriously affects the judgment of the rescuers on the disaster scene, and at the same time delays the rescue time.

SUMMARY OF THE INVENTION

The present application provides a method, device and storage medium for generating a map model, which are used to improve the accuracy of a map model (eg, a three-dimensional model).

To achieve the above object, the application adopts the following technical solutions:

According to a first aspect of the present application, a method for generating a map model is provided. The method includes:

The map model generating device (may be referred to as a "generating device") acquires multiple first images and multiple first positions, the multiple first images include the first object to be rescued and the scene object, and the first position is to collect the first image The positions of the plurality of first positions correspond to the plurality of first images. The generating device generates a first map model according to a plurality of first images and a plurality of first positions, the first map model is used to reflect the disaster scene, and the first map model includes scene objects. The generating device obtains the position information of the first object to be rescued. The generating device processes the first map model according to the position information of the first object to be rescued to generate a second map model, where the second map model includes the position information of the first object to be rescued, the first object to be rescued and the scene object.

Optionally, the method for generating a map model further includes: the generating device acquires a plurality of second images, and the plurality of second images are all collected images. The generating device obtains a plurality of first images, including: the generating device determines a plurality of first images from the plurality of second images according to the first position and the plurality of first positions corresponding to the target image, and the target image is any second image , the distances between the first positions corresponding to the multiple first images and the first positions corresponding to the target image are smaller than the preset distance threshold.

Optionally, the method for generating a map model further includes: the generating device generates a plurality of second positions according to a plurality of first positions and a plurality of first images, and the reprojection error of the first images collected at the second positions is smaller than the first position. The reprojection error of the first image collected at the position, and the plurality of second positions correspond to the plurality of first images. The generating means generates a first map model according to the plurality of second positions and the plurality of first images.

Optionally, the method for generating the map model further includes: the generating device processes multiple second positions and multiple first images through a target preset algorithm to determine a dense point cloud, and the target preset algorithm is used to determine a plurality of first images. A set of coordinates corresponding to pixels of an image, and a dense point cloud is determined by sets of coordinates corresponding to pixels of a plurality of first images. The generating device processes the dense point cloud to generate a triangulation model. The generating device performs rendering processing on the triangulation model by using the plurality of first images to generate a first map model.

Optionally, the plurality of first images include a second object to be rescued, and the second object to be rescued includes the first object to be rescued. The method for generating a map model further includes: the generating device performs deduplication processing on the second object to be rescued to obtain the first object to be rescued. The generating device determines the position information of the first object to be rescued according to a plurality of first positions and a plurality of target position relationships, where the target position relationship is a relationship between the first position and the position of the first object to be rescued.

According to a second aspect of the present application, there is provided an apparatus for generating a map model, the apparatus including an acquisition module and a processing module.

The acquisition module is configured to acquire a plurality of first images and a plurality of first positions, the plurality of first images include a first object to be rescued and a scene object, the first position is the position where the first image is collected, and the plurality of first positions are the same as the first position. A plurality of first images correspond. The processing module is configured to generate a first map model according to a plurality of first images and a plurality of first positions, the first map model is used to reflect the disaster scene, and the first map model includes scene objects. The acquiring module is further configured to acquire the location information of the first object to be rescued. The processing module is specifically configured to process the first map model according to the position information of the first object to be rescued to generate a second map model, where the second map model includes the position information of the first object to be rescued, the first object to be rescued and the scene object.

Optionally, the acquiring module is further configured to acquire multiple second images, where the multiple second images are all acquired images. The processing module is further configured to determine a plurality of first images from a plurality of second images according to a first position and a plurality of first positions corresponding to the target image, the target image is any second image, and the plurality of first images correspond to The distance between the first position of the target image and the first position corresponding to the target image is less than the preset distance threshold.

Optionally, the processing module is further configured to generate a plurality of second positions according to a plurality of first positions and a plurality of first images, and the reprojection error of the first image collected at the second position is smaller than that of the first image collected at the first position. The reprojection error of the image, the plurality of second positions correspond to the plurality of first images. The processing module is further configured to generate a first map model according to the plurality of second positions and the plurality of first images.

Optionally, the processing module is further configured to process multiple second positions and multiple first images through a target preset algorithm to determine a dense point cloud, and the target preset algorithm is used to determine the pixel points of the multiple first images. The corresponding coordinate set, the dense point cloud is determined by the coordinate set corresponding to the pixel points of the multiple first images. The processing module is also used to process the dense point cloud to generate a triangulation model. The processing module is further configured to perform rendering processing on the triangulation model by using the plurality of first images to generate a first map model.

Optionally, the plurality of first images include a second object to be rescued, and the second object to be rescued includes the first object to be rescued. The processing module is further configured to perform deduplication processing on the second object to be rescued to obtain the first object to be rescued. The processing module is further configured to determine the position information of the first object to be rescued according to a plurality of first positions and a plurality of target position relationships, where the target position relationship is the relationship between the first position and the position of the first object to be rescued.

According to a third aspect of the present application, there is provided an apparatus for generating a map model, the apparatus comprising: a processor and a memory. The processor and the memory are coupled. The memory is used to store one or more programs, the one or more programs include computer-executable instructions, and when the generating apparatus for the map model runs, the processor executes the computer-executable instructions stored in the memory to implement the first aspect and The method for generating a map model described in any possible implementation manner of the first aspect.

According to a fourth aspect of the present application, a computer-readable storage medium is provided, where instructions are stored in the computer-readable storage medium, and when the instructions are executed on a computer, the computer is made to execute any one of the first aspect and the first aspect. The generation method of the map model described in the possible implementations.

According to a fifth aspect of the present application, there is provided a computer program product, comprising a computer program, which, when the computer program is executed by a processor, enables a computer to implement the first aspect and any possible implementation manner of the first aspect Describes the generation method of the map model.

In the above solution, the technical problems and technical effects that can be solved by the generating device, computer equipment, computer storage medium or computer program product of the map model can be referred to the technical problems and technical effects solved in the first aspect above, and will not be repeated here. Repeat.

The technical solution provided by the present application brings at least the following beneficial effects: the generating device can acquire a plurality of first images and a plurality of first positions, the plurality of first images include a first object to be rescued and a scene object, and the first position is the collection of the first position. The position of an image, the plurality of first positions correspond to the plurality of first images. Afterwards, the generating device may generate a first map model according to the plurality of first images and the plurality of first positions, where the first map model is used to reflect the disaster scene, and the first map model includes scene objects. In addition, the generating device can obtain the position information of the first object to be rescued, and process the first map model according to the position information of the first object to be rescued to generate a second map model, where the second map model includes the first object to be rescued The position information of the object, the first object to be rescued and the scene object. That is, the generating device may mark the position information of the first object to be rescued and objects in the disaster scene (eg, the first object to be rescued and the scene objects) on the second map model. In this way, the amount of information in the map model can be increased, and then it can provide a valuable reference for rescuers to reasonably allocate rescue forces, determine key areas for disaster relief, select safe rescue routes, and select locations for post-disaster reconstruction. In addition, compared with the video of the disaster scene, in the technical solution of the present application, the amount of data of the second map model is smaller. In this way, the amount of data transmitted by the generating device can be reduced, and the time for the generating device to transmit information to the terminal can be saved, thereby speeding up the rescue progress and improving the rescue efficiency.

Description of drawings

FIG. 1 is a schematic diagram of a communication system according to an exemplary embodiment;

2 is a flowchart of a method for generating a map model according to an exemplary embodiment;

FIG. 3 is a flowchart of another method for generating a map model according to an exemplary embodiment;

4 is a schematic diagram of an example of determining location information according to an exemplary embodiment;

FIG. 5 is a schematic diagram of an example of marking position information according to an exemplary embodiment;

FIG. 6 is a flowchart of another method for generating a map model according to an exemplary embodiment;

FIG. 7 is a flowchart of another method for generating a map model according to an exemplary embodiment;

FIG. 8 is a schematic diagram of an example of generating a map model according to an exemplary embodiment;

FIG. 9 is a flowchart of another method for generating a map model according to an exemplary embodiment;

FIG. 10 is a flowchart of another method for generating a map model according to an exemplary embodiment;

Fig. 11 is a flowchart of another method for generating a map model according to an exemplary embodiment;

FIG. 12 is a structural block diagram of an apparatus for generating a map model according to an exemplary embodiment;

FIG. 13 is a schematic structural diagram of an apparatus for generating a map model according to an exemplary embodiment;

Figure 14 is a conceptual partial view of a computer program product, shown according to an exemplary embodiment.

Detailed ways

In order to make those skilled in the art better understand the technical solutions of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings.

It should be noted that the terms "first", "second", etc. in the description and claims of the present application and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific sequence or sequence. It is to be understood that data so used may be interchanged under appropriate circumstances so that the embodiments of the application described herein can be practiced in sequences other than those illustrated or described herein. The implementations described in the illustrative examples below are not intended to represent all implementations consistent with this application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application as recited in the appended claims.

Furthermore, references to the terms "comprising" and "having" in the description of this application, and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or modules is not limited to the listed steps or modules, but may optionally also include other unlisted steps or modules, or optionally also Other steps or modules inherent to these processes, methods, products or devices are included.

In addition, in the embodiments of the present application, words such as "exemplary" or "for example" are used to represent examples, illustrations or illustrations. Any embodiment or design described in this application as "exemplary" or "such as" should not be construed as preferred or advantageous over other embodiments or designs. Rather, use of words such as "exemplary" or "such as" is intended to present concepts in a specific manner.

First, the application scenarios of the embodiments of the present application are introduced.

The method for generating a map model according to the embodiment of the present application is applied to a scenario in which a terminal (such as a drone) collects disaster-affected scenario information. In the related art, when the drone collects the information of the disaster-affected scene, it needs to collect the disaster-affected scene first, and transmit the video obtained through the collection back to the terminal. After that, rescuers can understand the situation of the disaster scene and make rescue plans based on the video content played by the terminal. However, in the current technical solution, the UAV only collects images of the disaster scene. In this way, without locating the objects of the disaster-affected scene, the judgment of the rescuer on the disaster-affected scene is seriously affected, and the rescue time is also delayed.

Exemplarily, when the drone detects that it has entered the disaster-stricken village, it can collect the disaster-stricken village and transmit the collected video of the disaster-affected village back to the terminal. After that, rescuers can learn about the situation of the disaster-stricken villages and make rescue plans based on the video content played by the terminal. If there are personnel A to be rescued and scene object B in the video played by the terminal, the rescue personnel cannot determine the specific positions of personnel A to be rescued and scene object B according to the video content played by the terminal.

To sum up, in the current technical solution, the drone only collects images of the disaster scene, and the amount of information collected is small, which seriously affects the judgment of the rescuers on the disaster scene, and at the same time delays the rescue time.

In order to solve the above problem, an embodiment of the present application provides a method for generating a map model, and the drone can obtain the image of the disaster scene and the collection position (ie, the position where the drone collects the image). After that, the drone can generate a map model of the disaster scene based on the image and collection location of the disaster scene. Moreover, the drone can determine the location information of the object to be rescued in the image of the disaster scene. In the case of generating a map model of the disaster scene and determining the position information of the object to be rescued in the image of the disaster scene, the drone can mark the position information of the object to be rescued on the map model of the disaster scene. In this way, rescuers can judge the disaster-affected scene according to the marked map model returned by the drone to the terminal, and make a rescue plan, which improves the accuracy of the rescuer's judgment on the disaster-affected scene. Moreover, compared with video transmission, the amount of data of the marked map model returned by the drone to the terminal is less, and the transmission speed is faster, which can speed up the rescue progress.

The implementation environment of the embodiments of the present application will be introduced below.

FIG. 1 is a schematic diagram of a communication system provided by an embodiment of the present application. As shown in FIG. 1 , the communication system may include: a terminal 01 and a terminal 02 . Wherein, the terminal 01 can acquire acquisition information (such as an image and an acquisition location (ie, the location where the terminal 01 acquires an image)), and the terminal 01 and the terminal 02 can perform wireless communication.

For example, terminal 01 may communicate with terminal 02 through satellite communication. For another example, the terminal 01 may communicate with the terminal 02 through spread spectrum microwave communication. For another example, the terminal 01 may communicate with the terminal 02 through digital radio communication. For another example, the terminal 01 may communicate with the terminal 02 through Bluetooth.

Wherein, the terminal 01 can process the collected information, such as generating a map model through the image and the collection location. The terminal 01 may send the collection information to the terminal 02 . The terminal 02 can display the collected information.

In some embodiments, data may be stored and processed in the terminal 01 .

In other embodiments, the terminal 01 may be connected to the server. The terminal 01 can send the collected information to the server, and the server can store the collected information and process the collected information. Afterwards, the server may send the processed collection information to the terminal 01 .

The terminal (such as terminal 01 or terminal 02) may be a mobile phone, tablet computer, desktop type, laptop type, handheld computer, notebook computer, Ultra-mobile Personal Computer (UMPC), netbook, and netbook with transceiving function. A device that can collect images and locate such as a drone, and the specific form of the terminal is not particularly limited in this application. It can interact with the user in one or more ways, such as a keyboard, a touchpad, a touchscreen, a remote control, a voice interaction or a handwriting device.

After the application scenarios and implementation environments of the embodiments of the present application are introduced, the method for generating a map model provided by the embodiments of the present application will be described in detail below in combination with the above-mentioned implementation environments.

Hereinafter, the technical solutions provided by the embodiments of the present application are described in detail by taking the terminal 01 as an unmanned aerial vehicle as an example.

Fig. 2 is a flow chart of a method for generating a map model according to an exemplary embodiment. As shown in FIG. 2, the method may include S201-S205.

S201, the drone acquires a plurality of first images.

Wherein, the plurality of first images include the object to be rescued and the scene object.

It should be noted that, the embodiment of the present application does not limit the first rescue object. For example, the first rescue object may be a person with red hair and squatting on the ground. For another example, the first rescue object may be a person with white hair and standing against a wall. For another example, the first rescue object may be an animal (eg, cat, dog, pig, etc.). For another example, the first rescue object may be an airplane, a ship, a car, or the like. The embodiment of the present application does not limit the scene object. For example, a scene object can be a gray and broken bridge. As another example, the scene object may be a white and complete dome. As another example, the scene object may be a green and broken tree.

In a possible implementation manner, the UAV can collect the target video, and the target video is the video of the disaster scene. After that, the drone can acquire every frame of the target video. The multiple first images may be all or part of the image frames in the target video.

Exemplarily, the drone obtains a video A by collecting, and the video A includes an image frame A, an image frame B, and an image frame C. The drone can take image frame A, image frame B, and image frame C as the first image.

In another possible implementation manner, the drone may collect images through a camera to obtain the first image.

Exemplarily, the drone obtains the image A through acquisition, and uses the image A as the first image B.

Understandably, the drone can acquire the first image in different ways. In this way, the ways for the UAV to obtain the first image can be increased, and the operability and flexibility are improved.

In some embodiments, before the drone acquires the first image, the drone may acquire a plurality of second images, and the plurality of second images are all acquired images. After that, the drone determines a plurality of first images from the plurality of second images according to the first position and the plurality of first positions corresponding to the target image. The distances between the first positions corresponding to the plurality of first images and the first positions corresponding to the target image are smaller than the preset distance threshold. Wherein, the target image is any second image.

It should be noted that, for the introduction of the multiple first positions, reference may be made to the descriptions in the following embodiments, which are not repeated here. Moreover, the embodiment of the present application does not limit the preset distance threshold. For example, the preset distance threshold may be a height difference of 1 meter and a horizontal distance of 2 meters. For another example, the preset distance threshold may be a height difference of 0.5 meters and a horizontal distance of 1.5 meters. For another example, the preset distance threshold may be a height difference of 2 meters and a horizontal distance of 3 meters.

Exemplarily, suppose that the drone determines the target image A, and sets the preset distance threshold to a height difference of 0.5 meters and a horizontal distance of 1.2 meters. If the height difference between image A and target image A is 0.7 meters, and the horizontal distance is 1.3 meters, the position of image A and the position of target image A are greater than the preset distance threshold, and it is determined that image A is not the first image. If the height difference between image B and target image A is 0.5 m, and the horizontal distance is 1.2 m, the position of image B and the position of target image A are equal to the preset distance threshold, and it is determined that image B is not the first image. If the height difference between image C and target image A is 0.4 m, and the horizontal distance is 1.1 m, then the position of image C and the position of target image A are less than the preset distance threshold, and image C is determined to be the first image.

S202, the drone acquires multiple first positions.

In the embodiment of the present application, the first position is the position where the drone collects the first image, and the plurality of first positions correspond to the plurality of first images.

Exemplarily, the plurality of first images include: image A, image B, and image C, and the plurality of first positions include: position A, position B, and position C. Wherein, the position A is the position where the drone collects the image A, the position B is the position where the drone collects the image B, and the position C is the position where the drone collects the image C.

In a possible implementation manner, the drone may acquire the first position by locating the position where the first image is collected.

It should be noted that the embodiment of the present application does not limit the positioning method. For example, the drone may determine the first position corresponding to the first image through a Global Positioning System (Global Positioning System, GPS). For another example, the UAV may determine the first position corresponding to the first image through the BeiDou Navigation Satellite System (BeiDou Navigation Satellite System, BDS). For another example, the UAV may determine the first position corresponding to the first image through a Global Navigation Satellite System (Global Navigation Satellite System, GLONASS).

In a possible design, the first position may include at least one of the following: longitude and latitude information of the drone, altitude information of the drone, and heading angle of the drone.

Exemplarily, in the case of acquiring image A and image B, according to the BDS, the drone determines that the location to acquire image A is 36° north latitude, 110° east longitude, 900 meters high, and 72° heading angle, and the location to acquire image B is 47° north latitude, 99° east longitude, 850 meters high. That is, the first position corresponding to image A is 36° north latitude, 110° east longitude, 900 meters high, and 72° heading angle, and the first position corresponding to image B is 47° north latitude, 99° east longitude, and 850 meters high.

It should be noted that, the embodiment of the present application does not limit the minimum unit of the first position. For example, the latitude and longitude of the first location can be accurate to degrees, for example, the first location is 35° north latitude, 130° east longitude, and 720 meters high. For another example, the latitude and longitude of the first position may be accurate to the minute, for example, the first position is 31°22' north latitude, 121°43' east longitude, and a height of 900 meters. For another example, the height of the first position may be accurate to millimeters, for example, the first position is 36° north latitude, 110° east longitude, and has a height of 900.005 meters.

S203. The drone generates a first map model according to the plurality of first images and the plurality of first positions.

Wherein, the first map model is used to reflect the disaster scene.

In one possible design, the first map model includes scene objects.

Exemplarily, the first map model includes scene object A and scene object B. Among them, scene object A is a black and broken bridge, and scene object B is a red and complete spire building.

In some embodiments, as shown in FIG. 3 , in the method for generating a map model, S203 may include S301-S302.

S301. The drone generates a plurality of second positions according to the plurality of first positions and the plurality of first images.

In the embodiment of the present application, the reprojection error of the first image collected by the drone at the second position is smaller than the reprojection error of the first image collected at the first position. The plurality of second locations correspond to the plurality of first images.

It should be noted that the reprojection error refers to the difference between the projection of the real three-dimensional space point on the image plane (that is, the pixel point on the image) and the reprojection (the obtained virtual pixel point). That is to say, the degree of difference between the map model generated by the image collected at the second position and the actual scene is smaller than the degree of difference between the map model generated by the image collected at the first position and the actual scene. That is, the accuracy of the map model generated by the images collected at the second location is high.

Exemplarily, the plurality of first images include: image A, image B, and image C, the plurality of first positions include: first position A, first position B, and first position C, and the plurality of second positions include: first position Two position A, second position B and second position C. Wherein, the second position A corresponds to the image A, the second position B corresponds to the image B, and the second position C corresponds to the image C. Moreover, the reprojection error of the image A collected by the drone at the second position A is less than the reprojection error of the image A collected at the first position A, and the reprojection error of the image B collected by the drone at the second position B is less than The reprojection error of the image B collected at the first position B, the reprojection error of the image C collected by the drone at the second position C is smaller than the reprojection error of the image C collected at the first position C.

In a possible implementation manner, the UAV may process multiple first positions and multiple first images through an aerial triangulation optimization algorithm to generate multiple second positions. Wherein, the space triangulation optimization algorithm is used to determine the second position corresponding to the first image.

It should be noted that the first position corresponding to the first image and the corresponding second position may be the same position or two different positions.

Exemplarily, if the first position corresponding to the first image A is 27.2° north latitude, 113.43° east longitude, and 740 meters high, and the first position corresponding to the first image B is 31° north latitude, 105° east longitude, and 330 meters high, then Through the aerial three optimization algorithm, the drone determines that the second position corresponding to the first image A is 27°2' north latitude, 113°43' east longitude, and the height is 740 meters, and the second position corresponding to the first image B is determined to be 31° north latitude. , 105° east longitude, 330 meters high.

S302. The drone generates a first map model according to the plurality of second positions and the plurality of first images.

In a possible implementation manner, the UAV may generate a dense point cloud according to multiple first positions and multiple first images. For the introduction of the dense point cloud, reference may be made to the descriptions in the following embodiments, which will not be repeated here. After that, the drone can process the dense point cloud through multiple second positions to generate the first map model.

In another possible implementation manner, the UAV may generate a triangulation network model according to the plurality of second positions and the plurality of first images, and construct the first map model by using the triangulation network model.

It can be understood that the drone can generate multiple second positions according to multiple first positions and multiple first images, and the reprojection error of the first image collected at the second position is smaller than that of the first image collected at the first position. The reprojection error of the plurality of second positions corresponds to the plurality of first images. That is, compared with the dense point cloud generated according to the first position and the first image corresponding to the first position, the dense point cloud generated by the second position and the first image corresponding to the second position is more accurate. Afterwards, the drone generates a first map model according to the plurality of generated second positions and the plurality of first images. Because the reprojection error of the first image collected by the drone at the second position is smaller than the reprojection error of the first image collected at the first position. In this way, the accuracy of the first map model can be improved.

S204, the drone obtains the location information of the first object to be rescued.

In a possible implementation manner, the UAV may determine the position information of the first object to be rescued according to a plurality of first positions and a plurality of target position relationships, and the target position relationship is the relationship between the first position and the first object to be rescued. relationship between locations.

In a possible design, the target position relationship may include at least one of the following: a directional position between the first position and the position of the first object to be rescued, a horizontal distance between the first position and the position of the first object to be rescued , the height difference between the first position and the position of the first object to be rescued.

Exemplarily, the drone may determine that the first object to be rescued A is located at a position 30° east-southeast of the first position A and a horizontal distance of 50 meters. Alternatively, the UAV can determine that the first object A to be rescued is located at a position 45° west-southwest of the first position A, with a horizontal distance of 40 meters and a height of 15 meters. Alternatively, the UAV may determine that the first object A to be rescued is located at a position 60° east-north of the first position A, with a horizontal distance of 60 meters and a lower position of 10 meters.

Optionally, the UAV may determine the target position relationship in a preset manner. For example, the UAV can determine through the ultrasonic sensor that the first position A is located at 30° east-southeast of the first object A to be rescued and a horizontal distance of 50 meters. For another example, the unmanned aerial vehicle may determine through the photoelectric sensor that the first position A is located at 45° southwest of the first object A to be rescued and a horizontal distance of 40 meters. For another example, the UAV can use a laser range finder to determine that the first position A is located at a position 60° east-north of the first object A to be rescued and a horizontal distance of 60 meters.

The following describes how the drone determines the position information of the first object to be rescued according to the relationship between multiple first positions and multiple target positions.

Exemplarily, as shown in Figure ₄ , the figure mainly has three coordinate systems, namely, the image coordinate system with O1 as the origin, the camera coordinate system with _O2 as the origin, and the world coordinate system with _O3 as the origin. . Among them, the image coordinate system is parallel to the camera coordinate system, and O ₁ O ₂ is perpendicular to the camera coordinate system, the origin of the world coordinate system is the projection point of the camera on the horizontal plane, and the Y axis points to the front of the camera. The height H is used to indicate the height of the camera (that is, the height of the drone), the angle α is used to indicate the pitch angle of the camera, the measurement point Q is used to indicate the first object to be rescued, and the projection point P is used to indicate that the measurement point Q is in the world coordinate system Y The projection position on the axis, the pixel point coordinate point Q ₁ (u, v) is used to represent the position of the measurement point Q in the image coordinate system, and the pixel point coordinate point P ₁ (u ₀ , v) is used to represent the projection point P in the image. The position of the coordinate system, the coordinate point O ₃ is used to represent the projection position of the UAV in the world coordinate system, and the coordinate point O ₁ (u ₀ , v ₀ ) is used to represent the position of the lens center point in the image coordinate system, and the coordinate point M It is used to indicate the position of the center of the image coordinate system (ie the origin O ₁ ) on the Y-axis of the world coordinate system. Among them, dx on the image coordinate system represents the actual length of the unit pixel of the u-axis, dy represents the actual length of the unit pixel of the v-axis, and the units of the actual lengths dx and dy represented by the unit pixel are millimeters per pixel (mm/ pix), the focal length f represents the distance between the origin O ₁ and the origin O ₂ , and the unit of the focal length f is millimeters (mm). In the figure, the relationship between O ₃ M and the pitch angle α can be expressed as H=O ₃ M·tanα. Then the distance O ₃ P in the Y-axis direction from the measuring point Q to the coordinate point O ₃ can be calculated. The derivation process can refer to formula 1, formula 2 and formula 3.

β=α-γ Formula two.

)，则可以计算出测量点Q到坐标点O₃的X轴方向的距离PQ。推导过程可以参考公式四、公式五和公式六。O ₃ P and ΔPO ₂ Q～ΔP ₁ O ₂ Q ₁ obtained by the above formula (ie

), then the distance PQ in the X-axis direction from the measurement point Q to the coordinate point O ₃ can be calculated. For the derivation process, please refer to Equation 4, Equation 5 and Equation 6.

即第一待救援对象和无人机所处位置在实际地面的距离。之后，无人机可以将第一图像的第一位置的经纬度信息转换为投影坐标，根据已知的无人机在第一图像的第一位置的航向角和无人机与第一图像中第一待救援对象之间的距离，计算出该第一待救援对象在投影坐标系上的坐标，再将该第一待救援对象的坐标转化为经纬度坐标，得到第一待救援对象的位置信息。推导过程可以参考公式七、公式八、公式九、公式十和公式十一。Then the distance from Q to the origin of the world coordinate system is:

That is, the distance between the first object to be rescued and the position of the drone on the actual ground. After that, the UAV can convert the latitude and longitude information of the first position of the first image into projection coordinates, according to the known heading angle of the UAV at the first position of the first image and the first position of the UAV and the first image in the first image. Once the distance between the objects to be rescued is calculated, the coordinates of the first object to be rescued on the projected coordinate system are calculated, and then the coordinates of the first object to be rescued are converted into latitude and longitude coordinates to obtain the location information of the first object to be rescued. For the derivation process, please refer to Formula 7, Formula 8, Formula 9, Formula 10 and Formula 11.

L=I+L ₀ Formula eleven.

S205: The drone generates a second map model by processing the position information of the first object to be rescued on the first map model.

The second map model includes location information of the first object to be rescued, the first object to be rescued, and a scene object.

In a possible implementation manner, the drone may mark the first object to be rescued on the first map model according to the position information of the first object to be rescued to generate the second map model.

Exemplarily, as shown in FIG. 5 , if the location information A of the first object A to be rescued corresponds to the location A of the first map model, the location A of the first map model is marked. If the location information B of the first object to be rescued B corresponds to the location B of the first map model, the location B of the first map model is marked. If the location information C of the first object C to be rescued corresponds to the location C of the first map model, the location C of the first map model is marked.

The technical solutions provided by the above embodiments bring at least the following beneficial effects: the generating device can acquire multiple first images and multiple first positions, the multiple first images include the first object to be rescued and the scene object, and the first position is collected The positions of the first images, the plurality of first positions correspond to the plurality of first images. Afterwards, the generating device may generate a first map model according to the plurality of first images and the plurality of first positions, where the first map model is used to reflect the disaster scene, and the first map model includes scene objects. In addition, the generating device can obtain the position information of the first object to be rescued, and process the first map model according to the position information of the first object to be rescued to generate a second map model, where the second map model includes the first object to be rescued The position information of the object, the first object to be rescued and the scene object. That is, the generating device may mark the position information of the first object to be rescued and objects in the disaster scene (eg, the first object to be rescued and the scene objects) on the second map model. In this way, the amount of information in the map model can be increased, and then it can provide a valuable reference for rescuers to reasonably allocate rescue forces, determine key areas for disaster relief, select safe rescue routes, and select locations for post-disaster reconstruction. In addition, compared with the video of the disaster scene, in the technical solution of the present application, the amount of data of the second map model is smaller. In this way, the amount of data transmitted by the generating device can be reduced, and the time for the generating device to transmit information to the terminal can be saved, thereby speeding up the rescue progress and improving the rescue efficiency.

In some embodiments, as shown in FIG. 6 , in the method for generating a map model, S302 may include S601-S603.

S601. The drone processes multiple second positions and multiple first images through a target preset algorithm to determine a dense point cloud.

In a possible implementation manner, a target preset algorithm is stored in the UAV, and the target preset algorithm is used to determine a set of coordinates corresponding to the pixels of the plurality of first images. The UAV may determine a set of coordinates corresponding to the pixels of the multiple first images according to the target preset algorithm. After that, the UAV uses the plurality of second positions as reference points, and determines the dense point cloud according to the set of coordinates corresponding to the pixels of the plurality of first images. The dense point cloud is determined by a set of coordinates corresponding to the pixel points of the plurality of first images.

It should be noted that, the embodiment of the present application does not limit the target preset algorithm.

Exemplarily, the target presetting algorithm includes a stereo pair matching algorithm and a forward intersection algorithm. If the first image A corresponds to the first position A, the first image B corresponds to the first position B, and the first image A is adjacent to the first image B, the stereo matching algorithm is used to determine the first image A and the first image A set of pixels with the same name corresponding to B. After that, through the forward intersection algorithm, the three-dimensional coordinates of the pixel points in the pixel point set A with the same name are determined, and the three-dimensional coordinate set B is obtained. By marking the three-dimensional coordinate set B in the three-dimensional coordinate system, the dense point cloud A is determined.

In some embodiments, the dense point cloud is obtained by down-sampling each image through a preset image down-sampling coefficient and specifying multiple point cloud sampling density levels. Among them, the point cloud sampling density level includes high density level, medium density level and low density level. Except for the high-density level, the full-pixel depth map is generated for the image, and other pixels are used for depth map generation, that is, at the medium density level, the depth map is generated for every other pixel in the horizontal and vertical directions of the image; At low density levels, the depth map is generated every two pixels in the horizontal and vertical directions of the image.

Exemplarily, in the case of determining a dense point cloud for the first image A, if the preset image downsampling coefficient is 3, and the specified point cloud sampling density level is high density level, medium density level and low density level, then in In the first image A, one pixel point is taken every 3 pixels in each row and each column to form the first image B. If the point cloud sampling density level of the first image B is a high density level, a full-pixel depth map is generated for the first image B. If the point cloud sampling density level of the first image B is a medium density level, the depth map is generated for every other pixel in the horizontal direction and the vertical direction of the first image B. If the point cloud sampling density level of the first image B is a low density level, the depth map is generated for every two pixels in the horizontal direction and the vertical direction of the first image B.

It can be understood that by specifying the downsampling coefficient and the point cloud sampling density, the number of three-dimensional coordinates for determining pixel points can be reduced. This reduces the time to determine dense point clouds.

S602, the drone processes the dense point cloud to generate a triangulation network model.

It should be noted that the process of generating a triangulation network model by processing a dense point cloud by a UAV can refer to the method of generating a triangulation network model through a dense point cloud in the conventional technology, which will not be repeated here.

Exemplarily, the UAV can process the dense point cloud through the Delaunay tetrahedron algorithm, generate the Delaunay tetrahedron space division, and construct the global optimization graph, and the nodes of the global optimization graph are divided by the space. The tetrahedron in is constructed, and the edges of the global optimization graph are the triangular faces of the adjacent tetrahedron. Then, the UAV can determine the triangular faces in the Delaunay tetrahedron where the line connecting each point to the camera it sees intersects, accumulate the weight value 1 to the corresponding edge in the global optimization graph, and obtain the global optimization of visible line constraints picture. Finally, the UAV can segment the global optimization graph through the minimum cut maximum flow algorithm, determine the internal and external relationship between each tetrahedron and the model surface, and extract the shared triangular faces of adjacent tetrahedra located inside and outside the surface to form the final Triangulation model.

S603 , the drone performs rendering processing on the triangulation model by using a plurality of first images to generate a first map model.

Exemplarily, the drone may select the closest visible camera to the triangulation of each triangulation model as its associated camera. Then, the UAV divides the spatially connected triangular faces of the same associated camera into the same group, and obtains the image blocks collected on the associated camera. Finally, the UAV combines all the image blocks into a texture map according to the packing algorithm, realizes the texture mapping of the triangulation model, and obtains the first map model.

It can be understood that the UAV can process multiple second positions and multiple first images through the target preset algorithm to determine the dense point cloud, and the target preset algorithm is used to determine the corresponding pixel points of the multiple first images. The set of coordinates of the dense point cloud is determined by the set of coordinates corresponding to the pixels of the multiple first images. And compared with the dense point cloud generated according to the first position and the first image corresponding to the first position, the dense point cloud generated by the second position and the first image corresponding to the second position is more accurate. After that, the drone processes the dense point cloud to generate a triangulation model, and renders the triangulation model through a plurality of first images to generate a first map model. In this way, the accuracy of the first map model can be improved.

In some embodiments, the drone may determine a characteristic object for each of the plurality of first images. After that, the drone can model the characteristic object based on the first image with the same characteristic object

As shown in FIG. 7, after performing S201, the method for generating a map model may further include S701-S702.

S701. The drone extracts M characteristic objects corresponding to a plurality of first images through a first preset algorithm.

Wherein, the characteristic objects include a first object to be rescued and a scene object, a plurality of first images correspond to M characteristic objects, and M is a positive integer.

Exemplarily, the 3 (that is, M is 3) feature objects include: feature object A, feature object B, and feature object C, where feature object A can be the first object to be rescued A (such as a person), and feature object B can be a scene. Object A (such as a river), and feature object C can be scene object B (such as a house).

It should be noted that the number of the multiple first images may be the same as or different from M, which is not limited in this embodiment of the present application. Generally, the number of the plurality of first images is greater than M. That is, the feature objects of different first images may be the same.

Exemplarily, the plurality of first images include: image A, image B, image C, and image D, image A includes feature object A, image B includes feature object B, and image C and image D include the same feature object C.

Optionally, a first image may include multiple feature objects. For example, the first image A includes: the first object A to be rescued and the scene object A.

In this embodiment of the present application, the first preset algorithm is used to extract characteristic objects in a plurality of first images.

It should be noted that, the embodiment of the present application does not limit the first preset algorithm. For example, the first preset algorithm may be a Scale Invariant Feature Transform (SIFT) algorithm. For another example, the first preset algorithm may be a Speeded Up Robust Features (SURF) algorithm. For another example, the first preset algorithm may be an Oriented Fast and Rotated Brief (ORB) algorithm.

It should be noted that, the embodiment of the present application does not limit the feature object. For example, the feature object can be a color feature. For another example, the feature object may be a texture feature. For another example, the feature object may be a shape feature.

S702 , the drone processes the multiple first images according to the M characteristic objects to obtain M image sets.

Among them, M image sets correspond to M feature objects. An image set includes at least one first image, and the characteristic objects corresponding to the first images in an image set are the same.

In a possible implementation manner, the drone may perform matching on multiple first images according to the characteristic objects of the first images, to obtain an image set with the same characteristic objects.

Optionally, the drone can set a preset pixel size range. If the pixel size of the feature object is within the preset pixel size range, multiple first images having the same feature object are matched. If the pixel size of the feature object is not within the preset pixel size range, the matching of multiple first images having the same feature object is canceled.

Exemplarily, the drone sets a preset pixel size range of (2000, 4000). If the pixel size of the feature object A is 3000, multiple first images with the same feature object A are matched. If the pixel size of the feature object B is 5000, the matching of multiple first images having the same feature object B is cancelled.

In some embodiments, after the drone matches multiple first images with the same feature object, the drone may model the M feature objects from the M image sets.

It can be understood that, the drone matches the plurality of first images according to the characteristic objects extracted from the plurality of first images, and can determine the plurality of first images with the same characteristic objects. In this way, the same feature objects in the multiple first images can be modeled by using multiple first images with the same feature objects. In this way, the feature object can be modeled more accurately. Moreover, by setting a preset pixel size range, the feature objects of the first image can be screened. In this way, the matching time for multiple first images having the same feature object can be greatly reduced.

The method for generating the map model provided by the present application will be introduced below with reference to specific examples. As shown in FIG. 8 , taking building a map model of feature object A as an example, the image set corresponding to feature object A is image set A (that is, the feature objects of the first image in image set A are all feature object A). The UAV can process the second position corresponding to each first image in the image set A and the image set A through the target preset algorithm, and obtain the dense point cloud of the feature object A as shown in (a) in Figure 8. A. By processing the dense point cloud A, the drone can generate the triangulation model A of the feature object A shown in (b) in Figure 8. The UAV renders the triangulation model A through the image set A, and can generate the map model A of the feature object A shown in (c) in FIG. 8 .

In some embodiments, as shown in FIG. 9, before S204, the method for generating the map model may further include S901-S902.

S901, the drone obtains the second object to be rescued.

In the embodiment of the present application, the plurality of first images include the second object to be rescued, and the second object to be rescued includes the first object to be rescued.

Exemplarily, the first image A includes a second object A to be rescued and a second object B to be rescued. The second object to be rescued A includes the first object to be rescued A, the first object to be rescued B and the first object to be rescued C, and the second object to be rescued B includes the first object to be rescued D and the first object to be rescued E .

In a possible design, the UAV stores a target detection algorithm, and the target detection algorithm is used to identify target objects (ie, the second object to be rescued and the scene object) in the plurality of first images, and detect the target objects in the plurality of first images. Feature extraction is performed on the target object in the image. The UAV performs feature extraction on target objects in multiple first images through a target detection algorithm, and configures a unique identity document (ID) for the target objects with features.

It should be noted that, the embodiment of the present application does not limit the target detection algorithm. For example, an R-CNN (Region-CNN, region segmentation technology) algorithm based on a region proposal (eg, R-CNN, Fast R-CNN, Faster R-CNN, etc.). Another example is a one-stage (one stage/step) algorithm (such as Yolo, SSD, etc.).

Exemplarily, if the first image A includes people and buildings, the multi-target tracking algorithm is used to identify the object to be rescued in the first image A and extract features such as hair color and posture, and then use the multi-target tracking algorithm to identify the object to be rescued in the first image A Scene objects are identified and features such as color and shape of scene objects are extracted. After that, the person with yellow hair and squatting on the ground in the first image A is assigned the ID as the object to be rescued A, the person with white hair and standing against the wall in the first image A is assigned the ID as the object to be rescued B, and the first image A is assigned the ID as the object to be rescued. The configuration ID of the white and complete dome building in the image A is the scene object A, and the configuration ID of the red and broken bridge in the first image A is the scene object B.

It can be understood that, by identifying the target objects in the multiple first images, rescuers can formulate a rescue plan based on the rescue needs of the second object to be rescued in the disaster scene and the damage of the scene objects. In this way, while speeding up the rescue progress, it also ensures the safety of the rescuers.

In a possible implementation manner, the drone may process multiple first images collected in real time.

Exemplarily, the drone collects the first image A at time A, and processes the first image A. Alternatively, the drone collects the first image B and the first image C at time B, and processes the first image B and the first image C. Alternatively, the drone collects the first image D, the first image E, and the first image F at time C, and processes the first image D, the first image E, and the first image F.

In another possible implementation manner, the drone may process the multiple first images of the disaster scene after the acquisition of the multiple first images is completed.

Exemplarily, the drone collects the first image A, the first image B, and the first image C when the collection of the disaster-affected scene is completed. After that, the drone processes the first image A, the first image B and the first image C.

It will be appreciated that the drone can process the first image in different ways. In this way, the processing method of the UAV for the first image can be increased, and the operability and flexibility are improved.

S902, the drone obtains the first object to be rescued by deduplicating the second object to be rescued.

In a possible implementation manner, the drone can perform deduplication processing on the duplicate objects in the second object to be rescued to obtain the first object to be rescued.

Exemplarily, the drone first determines multiple motion state definitions of the second object A to be rescued through the Kalman filter algorithm, and the multiple motion state definitions vary with the movement of the second object A to be rescued, and the second object A to be rescued changes. The position and velocity of the previous frame of object A will be used to predict the position and velocity of the current frame, and the two observed normally distributed states are linearly weighted to obtain the predicted state of the current frame. Then, the similarity between the two frames before and after the second object A to be rescued is calculated by the Hungarian algorithm, and the similarity matrix of the two frames before and after the second object A to be rescued is obtained. IOU) to obtain the corresponding similarity matrix, and by comparing the similarity matrix of the two frames before and after, the problem of the actual matching target of the two frames before and after is solved.

As shown in FIG. 10 , if the second object to be rescued with the configured ID includes the second object to be rescued A and the second object to be rescued B, the predicted second object to be rescued includes the predicted second object to be rescued A and the predicted second object to be rescued Rescue object B. The second object to be rescued A corresponds to the predicted second object to be rescued A, and the second object to be rescued B corresponds to the predicted second object to be rescued B. The position and speed of the second object A to be rescued are matched with the predicted position and speed of the second object A to be rescued through the IOU comparison calculation. If the position and speed of the second object to be rescued A match the predicted position and speed of the second object to be rescued A successfully, update the position and speed of the second object to be rescued A (that is, to predict the second object A to be rescued) The position and speed of , are used to predict the position and speed of the second object to be rescued in the next frame), and enter the IOU comparison calculation. If the position and speed of the second object to be rescued A and the predicted position and speed of the second object to be rescued A fail to match, then the predicted position and speed of the second object to be rescued B and the predicted position and speed of the second object to be rescued A are compared. Speed matching is performed. If the position and speed of the predicted second object to be rescued B and the predicted position and speed of the second object to be rescued A fail to match, configure a new ID for the predicted second object to be rescued A as the second to be rescued Object C, and predicts the position and speed of the next frame of the second object C to be rescued, and enters the IOU comparison calculation. If the second object to be rescued A fails to match the predicted second object to be rescued A, and the predicted position and speed of the second object to be rescued B match the predicted position and speed of the second object to be rescued A successfully, delete the second object to be rescued. Rescue object A. In this way, the first object to be rescued is finally obtained.

It can be understood that the drone configures an ID for the target object in the first image and performs de-duplication processing. In this way, the target objects that need to be located can be reduced, and the rescue progress can be accelerated.

The following describes the method for generating a map model provided by the present application with reference to specific examples. As shown in FIG. 11 , the generating system for the map model includes a UAV camera and an image analysis module. Wherein, the drone camera can collect the original image (ie, the first image and the first position). The image analysis module can detect and classify the targets in the collected original images (ie, the first object to be rescued and the scene object), perform de-duplication processing on the classified targets, and locate the de-duplicated targets. After that, the image analysis module displays the deduplicated and located target on the map model (ie, the first map model).

The solutions provided by the embodiments of the present application have been introduced above mainly from the perspective of computer equipment. It can be understood that, in order to realize the above-mentioned functions, the computer device includes corresponding hardware structures and/or software modules for executing each function. Those skilled in the art should easily realize that the method for generating map models of each example described in conjunction with the embodiments disclosed in this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is performed by hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each particular application, but such implementations should not be considered beyond the scope of this application.

The embodiments of the present application also provide a map model generating apparatus. The device for generating the map model may be a computer device, or a CPU in the above-mentioned computer device, or a processing module in the above-mentioned computer device for determining the generation of a map model, or a map model in the above-mentioned computer device. generated client.

In this embodiment of the present application, the generation of the map model may be divided into functional modules or functional units according to the foregoing method examples. For example, each functional module or functional unit may be divided corresponding to each function, or two or more functions may be integrated in in a processing module. The above-mentioned integrated modules can be implemented in the form of hardware, and can also be implemented in the form of software function modules or functional units. Wherein, the division of modules or units in the embodiments of the present application is schematic, and is only a logical function division, and there may be other division manners in actual implementation.

As shown in FIG. 12 , it is a structural block diagram of an apparatus for generating a map model provided by an embodiment of the present application. The map model generating apparatus is used to execute the map model generating method shown in FIG. 2 . The map model generating apparatus 1200 includes an acquisition module 1201 and a processing module 1202 .

The acquisition module 1201 is used to acquire multiple first images and multiple first positions, the multiple first images include the first object to be rescued and the scene object, the first position is the position where the first image is collected, and the multiple first positions corresponding to the plurality of first images. The processing module 1202 is configured to generate a first map model according to a plurality of first images and a plurality of first positions, the first map model is used to reflect the disaster scene, and the first map model includes scene objects. The obtaining module 1201 is further configured to obtain the position information of the first object to be rescued. The processing module 1202 is specifically configured to process the first map model through the position information of the first object to be rescued to generate a second map model, where the second map model includes the position information of the first object to be rescued, the first object to be rescued and the scene object.

Optionally, the acquiring module 1201 is further configured to acquire multiple second images, where the multiple second images are all acquired images. The processing module 1202 is further configured to determine a plurality of first images from a plurality of second images according to a first position and a plurality of first positions corresponding to the target image, the target image is any second image, and the plurality of first images The distance between the corresponding first position and the first position corresponding to the target image is smaller than the preset distance threshold.

Optionally, the processing module 1202 is further configured to generate a plurality of second positions according to a plurality of first positions and a plurality of first images, and the reprojection error of the first image collected at the second position is smaller than that of the first image collected at the first position. The reprojection error of an image, the plurality of second positions correspond to the plurality of first images. The processing module 1202 is further configured to generate a first map model according to the plurality of second positions and the plurality of first images.

Optionally, the processing module 1202 is further configured to process multiple second positions and multiple first images through a target preset algorithm to determine a dense point cloud, and the target preset algorithm is used to determine the pixels of multiple first images. The coordinate set corresponding to the point, and the dense point cloud is determined by the coordinate set corresponding to the pixel points of the multiple first images. The processing module 1202 is further configured to process the dense point cloud to generate a triangulation model. The processing module 1202 is further configured to perform rendering processing on the triangulation model by using the plurality of first images to generate a first map model.

Optionally, the plurality of first images include a second object to be rescued, and the second object to be rescued includes the first object to be rescued. The processing module 1202 is further configured to perform deduplication processing on the second object to be rescued to obtain the first object to be rescued. The processing module 1202 is further configured to determine the position information of the first object to be rescued according to a plurality of first positions and a plurality of target position relationships, where the target position relationship is the relationship between the first position and the position of the first object to be rescued.

FIG. 13 shows yet another possible structure of the map model generating apparatus involved in the above embodiment. The apparatus for generating the map model includes: a processor 1301 and a communication interface 1302 . The processor 1301 is used to control and manage the actions of the device, for example, to perform each step in the method flow shown in the above method embodiments, and/or to perform other processes of the technology described herein. The communication interface 1302 is used to support the communication between the generating apparatus of the map model and other network entities. The map model generating apparatus may further include a memory 1303 and a bus 1304, and the memory 1303 is used to store program codes and data of the apparatus.

The above-mentioned processor 1301 may implement or execute various exemplary logical blocks, units and circuits described in conjunction with the disclosure of the present invention. The processor may be a central processing unit, a general purpose processor, a digital signal processor, an application specific integrated circuit, a field programmable gate array or other programmable logic device, transistor logic device, hardware component, or any combination thereof. It may implement or execute the various exemplary logical blocks, units and circuits described in connection with this disclosure. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a digital signal processor (Digital Signal Processor, DSP) and a microprocessor, and the like.

The memory 1303 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as read-only memory, flash memory, hard disk or solid-state disk; the memory may also include the above-mentioned types of memory. combination.

The bus 1304 may be an Extended Industry Standard Architecture (EISA) bus or the like. The bus 1304 can be divided into an address bus, a data bus, a control bus, and the like. For ease of presentation, only one thick line is used in FIG. 13, but it does not mean that there is only one bus or one type of bus.

In actual implementation, the acquiring module 1201 may be implemented by the communication interface 1302 shown in FIG. 13 , and the processing module 1202 may be implemented by calling the program code in the memory 1303 by the processor 1301 shown in FIG. 13 . For the specific execution process, reference may be made to the description of the method for generating the map model shown in FIG. 2 , which will not be repeated here.

From the description of the above embodiments, those skilled in the art can clearly understand that for the convenience and brevity of the description, only the division of the above functional modules is used as an example for illustration. In practical applications, the above functions can be allocated as required. It is completed by different functional modules, that is, the internal structure of the device is divided into different functional modules, so as to complete all or part of the functions described above. For the specific working process of the system, apparatus and unit described above, reference may be made to the corresponding process in the foregoing method embodiments, and details are not described herein again.

Embodiments of the present application further provide a computer-readable storage medium, where instructions are stored in the computer-readable storage medium, and when the instructions are executed on a computer, the computer is made to execute the map model in the method flow shown in the above method embodiments generation method.

The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any combination of the above. More specific examples (non-exhaustive list) of computer readable storage media include: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read only memory (Read-Only Memory, ROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, EPROM), registers, hard disk, optical fiber, portable compact disk read-only memory (Compact Disc Read-Only Memory, CD-ROM) ), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing, or any other form of computer-readable storage medium known in the art. An exemplary storage medium is coupled to the processor, such that the processor can read information from, and write information to, the storage medium. Of course, the storage medium can also be an integral part of the processor. The processor and the storage medium may be located in an Application Specific Integrated Circuit (ASIC). In the embodiments of the present application, the computer-readable storage medium may be any tangible medium containing or storing a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device.

FIG. 14 schematically shows a conceptual partial view of a computer program product provided by an embodiment of the present application, where the computer program product includes a computer program for executing a computer process on a computing device.

In one embodiment, the computer program product is provided using the signal bearing medium 1400 . Signal bearing medium 1400 may include one or more program instructions that, when executed by one or more processors, may provide the functions, or portions thereof, described above with respect to FIG. 2 . Thus, for example, with reference to the embodiment shown in FIG. 2 , one or more of the features of S201 - S205 may be undertaken by one or more instructions associated with the signal bearing medium 1400 . In addition, the program instructions in Figure 14 also describe example instructions.

In some examples, the signal bearing medium 1400 may include a computer readable medium 1401 such as, but not limited to, a hard drive, a compact disc (CD), a digital video disc (DVD), a digital tape, a memory, a read only memory (read only memory) -only memory, ROM) or random access memory (random access memory, RAM), etc.

In some implementations, the signal bearing medium 1400 may include a computer recordable medium 1402 such as, but not limited to, memory, read/write (R/W) CDs, R/W DVDs, and the like.

In some embodiments, signal bearing medium 1400 may include communication medium 1403, such as, but not limited to, digital and/or analog communication media (eg, fiber optic cables, waveguides, wired communication links, wireless communication links, etc.).

Signal bearing medium 1400 may be conveyed by wireless form of communication medium 1403 . The one or more program instructions may be, for example, computer-executable instructions or logic-implemented instructions.

In some examples, a generating apparatus such as the map model described with respect to FIG. 12 may be configured to, in response to one or more program instructions via computer readable medium 1401 , computer recordable medium 1402 , and/or communication medium 1403 , Provides various operations, functions, or actions.

Since the device for generating map models, the computer-readable storage medium, and the computer program product in the embodiments of the present invention can be applied to the above methods, the technical effects that can be obtained may also refer to the above method embodiments, the embodiments of the present invention. It is not repeated here.

The above are only specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and any changes or substitutions within the technical scope disclosed in the present application should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims (13)

1. A method of generating a map model, the method comprising:

the method comprises the steps of obtaining a plurality of first images and a plurality of first positions, wherein the plurality of first images comprise a first object to be rescued and a scene object, the first positions are positions for collecting the first images, and the plurality of first positions correspond to the plurality of first images;

generating a first map model according to the plurality of first images and the plurality of first positions, wherein the first map model is used for reflecting a disaster-stricken scene and comprises the scene object;

acquiring position information of the first object to be rescued;

and processing the first map model through the position information of the first object to be rescued to generate a second map model, wherein the second map model comprises the position information of the first object to be rescued, the first object to be rescued and the scene object.

2. The method of claim 1, wherein prior to acquiring the plurality of first images, the method further comprises:

acquiring a plurality of second images, wherein the plurality of second images are all acquired images;

acquiring the plurality of first images, including:

determining a plurality of first images from a plurality of second images according to a first position corresponding to a target image and the plurality of first positions, wherein the target image is any one of the second images, and the distance between the first position corresponding to the plurality of first images and the first position corresponding to the target image is smaller than a preset distance threshold.

3. The method of claim 1 or 2, wherein generating a first map model from the plurality of first images and the plurality of first locations comprises:

generating a plurality of second positions according to the plurality of first positions and the plurality of first images, wherein the reprojection error of the first images acquired at the second positions is smaller than that of the first images acquired at the first positions, and the plurality of second positions correspond to the plurality of first images;

generating the first map model from the plurality of second locations and the plurality of first images.

4. The method of claim 3, wherein the first map model is generated based on the plurality of second locations and the plurality of first images, the method further comprising:

processing the second positions and the first images through a target preset algorithm to determine dense point clouds, wherein the target preset algorithm is used for determining coordinate sets corresponding to pixel points of the first images, and the dense point clouds are determined by the coordinate sets corresponding to the pixel points of the first images;

processing the dense point cloud to generate a triangulation network model;

rendering the triangulation network model through the plurality of first images to generate the first map model.

5. The method according to claim 4, characterized in that the plurality of first images comprise a second object to be rescued comprising the first object to be rescued;

before the obtaining of the position information of the first object to be rescued, the method further comprises:

carrying out duplicate removal processing on the second object to be rescued to obtain the first object to be rescued;

the obtaining of the position information of the first object to be rescued includes:

and determining the position information of the first object to be rescued according to the plurality of first positions and a plurality of target position relations, wherein the target position relations are relations between the first positions and the positions of the first object to be rescued.

6. An apparatus for generating a map model, the apparatus comprising:

the device comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring a plurality of first images and a plurality of first positions, the plurality of first images comprise a first object to be rescued and a scene object, the first positions are positions for acquiring the first images, and the plurality of first positions correspond to the plurality of first images;

a processing module, configured to generate a first map model according to the plurality of first images and the plurality of first positions, where the first map model is used to reflect a disaster-affected scene, and the first map model includes the scene object;

the acquisition module is further used for acquiring the position information of the first object to be rescued;

the processing module is specifically configured to process the first map model according to the position information of the first object to be rescued, and generate a second map model, where the second map model includes the position information of the first object to be rescued, and the scene object.

7. The apparatus of claim 6,

the acquisition module is further configured to acquire a plurality of second images, where the plurality of second images are all acquired images;

the processing module is further configured to determine the plurality of first images from the plurality of second images according to the first positions corresponding to the target images and the plurality of first positions, where the target image is any one of the plurality of second images, and a distance between the first positions corresponding to the plurality of first images and the first positions corresponding to the target images is smaller than a preset distance threshold.

8. The apparatus of claim 7,

the processing module is further configured to generate a plurality of second positions according to the plurality of first positions and the plurality of first images, a reprojection error of a first image acquired at a second position is smaller than a reprojection error of a first image acquired at a first position, and the plurality of second positions correspond to the plurality of first images;

the processing module is further configured to generate the first map model according to the plurality of second locations and the plurality of first images.

9. The apparatus of claim 8,

the processing module is further configured to process the plurality of second positions and the plurality of first images through a target preset algorithm to determine dense point clouds, wherein the target preset algorithm is used for determining a coordinate set corresponding to pixel points of the plurality of first images, and the dense point clouds are determined by the coordinate set corresponding to the pixel points of the plurality of first images;

the processing module is also used for processing the dense point cloud to generate a triangulation network model;

the processing module is further configured to render the triangulation network model through the plurality of first images, and generate the first map model.

10. The apparatus according to claim 9, wherein the plurality of first images include a second object to be rescued including the first object to be rescued;

the processing module is further used for performing duplicate removal processing on the second object to be rescued to obtain the first object to be rescued;

the processing module is further configured to determine the position information of the first object to be rescued according to the plurality of first positions and a plurality of target position relationships, where the target position relationship is a relationship between the first position and the position of the first object to be rescued.

11. An apparatus for generating a map model, comprising: a processor and a memory; the processor and the memory are coupled; the memory is used for storing one or more programs, and the one or more programs comprise computer-executable instructions which are stored by the memory and executed by the processor when the generating device of the map model runs so as to cause the generating device of the map model to execute the generating method of the map model according to any one of claims 1-5.

12. A computer-readable storage medium having instructions stored therein, wherein when the instructions are executed by a computer, the computer performs the map model generation method according to any one of claims 1 to 5.

13. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, carries out the method of generating a map model according to any one of claims 1-5.

Images