CN113804100B - Method, device, device and storage medium for determining spatial coordinates of a target object - Google Patents

Abstract

Embodiments of the present disclosure provide a method, device, device and storage medium for determining spatial coordinates of a target object, and relate to the field of spatial surveying and mapping. The method includes acquiring an image recording a target object and a reference object in a spatial region. The method also includes acquiring map data of the map, the map data including the spatial coordinates of the reference object. The method also includes determining a mapping relationship between the image and the map according to the pixel coordinates of the reference object in the image and the spatial coordinates of the reference object. The method further includes determining the spatial coordinates of the target object based on the pixel coordinates and the mapping relationship of the target object in the image. In this way, the spatial coordinates of the target object can be determined efficiently and accurately without using professional surveying and mapping equipment, thereby greatly reducing costs.

Description

Method, device, device and storage medium for determining spatial coordinates of a target object

technical field

Embodiments of the present disclosure relate to the field of spatial surveying and mapping, and more specifically, to a method, device, device, and storage medium for determining spatial coordinates of a target object.

Background technique

In the field of smart transportation, for example, in order to facilitate fine-grained management of transportation facilities, it is necessary to determine the spatial coordinates of objects such as transportation facilities. In addition, in the process of constructing high-precision maps, it is also necessary to know the spatial coordinates of objects in the geographical environment.

Currently, techniques such as lidar measurements or oblique photography are relied upon to determine the spatial coordinates of objects. LiDAR measurement refers to the technique of reconstructing the spatial position and three-dimensional shape of objects through LiDAR. Oblique photography technology uses multiple sensors on the same drone to collect images of the subject from one vertical angle and four oblique angles at the same time, and reconstruct the spatial position and three-dimensional shape of the object. Although these two technologies can be used to obtain spatial coordinates with centimeter-level accuracy, there are problems such as high equipment and labor costs and limited use. After local changes in the space environment (for example: adding new equipment, Lane line update in the road, etc.), neither of these two technologies can conveniently and quickly obtain the spatial coordinates of the objects in the changed spatial region.

Contents of the invention

Example embodiments of the present disclosure provide a scheme for determining spatial coordinates of a target object.

In a first aspect of the present disclosure, a method of determining spatial coordinates of a target object is provided. The method includes acquiring an image recording a target object and a reference object in a spatial region. The method also includes acquiring map data of the map, the map data including the spatial coordinates of the reference object. The method also includes determining a mapping relationship between the image and the map according to the pixel coordinates of the reference object in the image and the spatial coordinates of the reference object. The method also includes determining the spatial coordinates of the target object based on the pixel coordinates and the mapping relationship of the target object in the image. Such a solution can efficiently and accurately determine the spatial coordinates of the target object without using professional surveying and mapping equipment, thereby greatly reducing costs.

In some embodiments, the method further includes updating the spatial coordinates of the target object to the map data. In this way, the map data can be updated quickly. Through the above method, in the case of entity update in a local space area, there is no need to use map data acquisition equipment to re-collect map data in the space area, saving manpower, material resources and Time costs.

In some embodiments, the target object includes entities newly added in the spatial region after map data collection is performed on the spatial region; the reference object includes entities existing in the spatial region before map data collection is performed on the spatial region. In this way, rapid response to environmental changes can be achieved.

In some embodiments, the entities existing in the spatial region before map data collection is performed on the spatial region may define a first plane, and the newly added entity may be located on the first plane.

In some embodiments, newly added entities in the space region may include newly installed equipment, such as electric police cameras, traffic radar, and the like. In such an embodiment, the entities present in the spatial region before the map data collection is performed on the spatial region may include devices installed with the device, such as electric police poles, street light poles, billboards, traffic light poles, and the like.

In some embodiments, the newly added entities in the spatial area may include newly planned lane lines. In such an embodiment, the entities existing in the spatial region before map data collection is performed on the spatial region may include existing lane lines and the like.

In some embodiments, the target object includes a first part of a building in the spatial region, and the reference object includes a second part of the building; the first part is collected by a data collection device that collects map data, and the second part is not collected by the data collection device arrive. In this way, the spatial coordinates of high-rise parts of high-rise buildings can be determined more conveniently and quickly.

In some embodiments, determining the mapping relationship between the image and the map includes: according to the pixel coordinates of the plurality of first control points on the reference object and the spatial coordinates of the plurality of corresponding points in the map of the plurality of first control points, Determine the mapping relationship between the image and the map. According to the pixel coordinates of multiple first control points and the spatial coordinates of multiple corresponding points, the mapping relationship can be quickly determined.

In some embodiments, the plurality of first control points includes at least four first control points, and the at least four first control points are located on the first plane and are not collinear. The mapping relationship between the image and the map can be obtained more accurately through at least four first control points.

In some embodiments, determining the mapping relationship between the image and the map includes: determining the first statistical result, the second statistical result and the third statistical result of the spatial coordinates of the plurality of corresponding points on the three dimensions of the spatial coordinate system; And if it is determined that both the first statistical result and the second statistical result are greater than the third statistical result, then based on the pixel coordinates of a plurality of first control points and the spatial coordinates of a plurality of corresponding points, the correlation between the first statistical result and the second The coordinates in the dimension corresponding to the statistical results determine the mapping relationship between the image and the map. Therefore, the computational complexity when determining the above mapping relationship can be reduced.

In some embodiments, the statistics include at least one of a variance and a length of a distribution interval.

In some embodiments, determining the spatial coordinates of the target object includes: based on the pixel coordinates and the mapping relationship of the target object, determining the first coordinate in the dimension corresponding to the first statistical result and the first coordinate of the target object in the spatial coordinates of the target object The second coordinate on the dimension corresponding to the second statistical result. In this way, the computational complexity of determining the above mapping relationship can be reduced.

In some embodiments, determining the mapping relationship between the image and the map includes determining a homography transformation relationship between the pixel coordinates of the plurality of first control points and the spatial coordinates of the plurality of corresponding points.

In a second aspect of the present disclosure, an apparatus for determining spatial coordinates of a target object is provided. The device includes an acquisition unit, a mapping relation determination unit and a space coordinate determination unit. The acquiring unit is configured to acquire map data of images and maps. The image records a target object and a reference object in a spatial region. The spatial coordinates of the reference objects are included in the map data. The mapping relationship determination unit is configured to determine the mapping relationship between the image and the map according to the pixel coordinates of the reference object in the image and the spatial coordinates of the reference object. The spatial coordinate determining unit is configured to determine the spatial coordinates of the target object based on the pixel coordinates of the target object in the image and the mapping relationship.

In some embodiments, the device further includes an updating unit configured to update the spatial coordinates of the target object to the map data.

In some embodiments, the target object includes entities newly added in the spatial region after map data collection is performed on the spatial region; the reference object includes entities existing in the spatial region before map data collection is performed on the spatial region.

In some embodiments, the target object includes a first part of a building in the spatial region, and the reference object includes a second part of the building; the first part is collected by a data collection device that collects map data, and the second part is not collected by the data collection device arrive.

In some embodiments, the mapping relationship determination unit is further configured to determine the mapping relationship according to the pixel coordinates of the plurality of first control points on the reference object and the spatial coordinates of corresponding points of the plurality of first control points in the map.

In a third aspect of the present disclosure, a computing device is provided. The computing device includes a processor and memory. The memory is used to store program codes, and the processor is used to execute the program codes in the memory to execute the above-mentioned first aspect and the method in combination with any one of the above-mentioned first aspects.

In a fourth aspect of the present disclosure, a computer readable storage medium is provided. A computer readable storage medium stores a computer program. When the computer program is executed by the processor, the above first aspect and the function of determining the spatial coordinates of the target object provided in combination with any one of the implementation manners of the above first aspect can be realized.

In a fifth aspect of the present disclosure, a computer program product is provided. The computer program product includes instructions. When the computer program product is executed by a computer, the computer can execute the above first aspect and the flow of the method for determining the spatial coordinates of the target object provided in combination with any one of the implementation manners of the above first aspect.

Description of drawings

Figure 1A shows a block diagram of an environment in which embodiments of the present disclosure can be implemented;

FIG. 1B shows a block diagram of an example software architecture of a computing device according to some embodiments of the present disclosure;

Figure 2 shows a schematic diagram of an example image according to some embodiments of the present disclosure;

Figure 3 shows a schematic diagram of an example map according to some embodiments of the present disclosure;

FIG. 4 shows a flowchart of a method for determining spatial coordinates of a target object according to some embodiments of the present disclosure;

Fig. 5 shows a flowchart of a method for determining spatial coordinates of a target object according to other embodiments of the present disclosure;

Fig. 6 shows a flow chart of a method for determining spatial coordinates of a target object according to still other embodiments of the present disclosure;

Fig. 7 shows a schematic diagram of an example image according to other embodiments of the present disclosure;

FIG. 8 shows a schematic block diagram of an apparatus 800 according to an embodiment of the present disclosure; and

FIG. 9 shows a block diagram of a computing device 900 of an embodiment of the disclosure.

Detailed ways

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the drawings, it should be understood that the disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein; A more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for exemplary purposes only, and are not intended to limit the protection scope of the present disclosure.

The term "spatial calibration" used herein refers to determining the corresponding relationship of the positions of the same object in different spaces. "Homography transformation" refers to the spatial position transformation relationship between two central projection planes.

In the description of the embodiments of the present disclosure, the term "comprising" and its similar expressions should be interpreted as an open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be read as "at least one embodiment". The terms "first", "second", etc. may refer to different or the same object. Other definitions, both express and implied, may also be included below.

As mentioned earlier, traditional ways of determining the spatial coordinates of an object mainly include lidar measurement and oblique photography. Although laser radar measurement can be used to obtain spatial coordinates with centimeter-level accuracy, the cost of laser radar mapping vehicles is relatively high, usually as high as millions of yuan. Especially when using lidar to measure small areas, the cost is even prohibitively high. In addition, the lidar mapping vehicle needs to reach the location of the target object for surveying and mapping, and long-distance operation may cause damage to the sensors on the lidar mapping vehicle. Furthermore, lidar surveying and mapping requires surveying and mapping qualifications, and currently only a small number of manufacturers have such surveying and mapping qualifications. When the environment changes, such as the renewal of traffic signs, the reinstallation of traffic monitoring equipment, etc., the rapid response to environmental changes cannot be achieved by using LiDAR measurement.

Although UAVs based on oblique photography are relatively cheap, they take a long time to collect, resulting in high labor costs. Additionally, the use of drones based on oblique photography is limited. There is a no-fly zone in the city, which makes it impossible for drones to be used, and the urban area happens to be the key deployment area for smart transportation. Therefore, the current update of high-precision maps using oblique photography technology is very slow, and it is impossible to achieve rapid response to environmental changes.

To at least address the above problems and potentially other related problems, embodiments of the present disclosure propose a solution for determining the spatial coordinates of a target object. By acquiring an image including a target object and a reference object (which defines a plane on which the target object is located) from an image capture device, based on pixel coordinates of a plurality of control points on the reference object corresponding to a plurality of control points of the reference object in the map The spatial coordinates of the points determine the mapping relationship between them. Furthermore, the spatial coordinates of the target object in the map can be determined according to the mapping relationship. This solution can efficiently and accurately determine the spatial coordinates of the target object without the need for professional surveying and mapping equipment such as lidar mapping vehicles and drones, thereby greatly reducing costs.

FIG. 1A shows a block diagram of an environment 100 in which embodiments of the present disclosure can be implemented. As shown in FIG. 1A , environment 100 includes image capture device 110 , computing device 130 , and storage device 140 .

Image capture device 110 may be any suitable device having image capture functionality. For example, the image capture device 110 may be an electronic device capable of taking pictures with a camera or camera, such as a smart camera, a mobile phone, a digital camera, and the like. The image captured by the image capture device 110 records the target object and the reference object in a spatial region. The target object is any appropriate object whose spatial coordinates need to be determined, and the reference object may be any appropriate object used to determine the plane where the target object is located. For example, in the case where the target object is a traffic monitoring device (such as an electric police camera, traffic radar) added in a spatial area, the reference object can be an electric police pole, a street light pole, a billboard, a traffic light installed with the traffic monitoring device, etc. pole etc. For another example, in the case that the target object is a traffic sign line, the reference object may be the traffic sign lines around the traffic sign line. For another example, in case the target object is a high-rise part of a building, the reference object may be a low-rise part of the building. The target object and the reference object will be described in detail below with reference to the embodiments in FIG. 2 and FIG. 3 .

The storage device 140 may be any suitable device having a storage function. For example, storage device 140 may be a solid state disk (SSD), mechanical storage disk (HDD), hybrid storage disk (SSHD), or other similar storage devices.

The map database 120 is stored in the storage device 140 . The map database 120 is a database based on digitized map data, including digital information files of each element of map content stored in a computer, a database management system, and other software and hardware. Various objects can be included in the map, such as control points, landforms, land types, settlements, hydrology, vegetation, transportation, boundaries, etc. It should be understood that the object examples listed above are merely descriptive and not limiting, and any suitable type and number of objects may be included in the map.

Computing device 130 may be any suitable electronic device having computing capabilities. In some embodiments, computing device 130 may be deployed in a cloud environment. The cloud environment refers to the central computing equipment cluster owned by the cloud service provider and used to provide computing, storage, and communication resources. For example, computing device 130 may be a central server in a cloud environment. In other embodiments, computing device 130 may be deployed in an edge environment. The edge environment refers to an edge computing device cluster that is geographically close to the image capture device and is used to provide computing, storage, and communication resources. For example, computing device 130 may be an edge computing device in an edge environment. An edge computing device may be a server, for example. In some other embodiments, the computing device 130 may be a desktop computer, a notebook computer, a tablet computer, a personal digital assistant (PDA), an intelligent terminal, etc. with strong processing capabilities.

Computing device 130 may acquire image 111 from image capture device 110 . Image 111 records a target object and a reference object in a spatial region. Computing device 130 may determine pixel coordinates of various points in image 111 , such as pixel coordinates of a target object and pixel coordinates of points on a reference object. An image is composed of pixels, and pixel coordinates refer to the position of the pixel in the image.

Optionally, the computing device 130 may also acquire the image 111 from other storage devices or user interfaces. In some embodiments, the target object and the reference object in the image 111 have been selected manually or automatically. Further, in some embodiments, in the image 111, the pixel coordinates of the control points on the reference object have been marked. Similarly, in some embodiments, in the image 111, the pixel coordinates of the target object have also been marked.

Computing device 130 may also obtain map 121 that matches image 111 from map database 120 . The map 121 can be, for example, a satellite map, a real scene map, and the like. Map 121 may include map data and/or other suitable map elements or information. The map data may include, for example, spatial position data (hereinafter also referred to as “spatial coordinates”) and the like of various points on the map 121 . According to the pixel coordinates of the reference object in the image 111 and the spatial coordinates of the reference object in the map 121 , the computing device 130 can determine the mapping relationship between the image 111 and the map 121 . Then, the computing device 130 determines the spatial coordinates of the target object in the map 121 based on the pixel coordinates of the target object and the mapping relationship.

The space coordinates of a point usually include the coordinates of the point in three dimensions of space, for example, it can be expressed in the form of (x, y, z). Specifically, if the spatial coordinates of a point are (x ₀ , y ₀ , z ₀ ), then it can be considered that x ₀ is the first coordinate of the spatial coordinates of the point, and y ₀ is the second coordinate of the spatial coordinates of the point , and z ₀ is the third coordinate of the spatial coordinates of the point. It should be understood that the above examples are only descriptive and not limiting, and in some other embodiments, y ₀ or z ₀ may also be used as the first coordinate of the spatial coordinates of the point.

In various embodiments of the present disclosure, the mapping relationship between the image and the map is determined according to the pixel coordinates and spatial coordinates of the reference object, and then the spatial coordinates of the target object in the map are determined based on the mapping relationship. This significantly reduces costs by eliminating the need for specialized mapping equipment such as lidar mapping vehicles and drones.

Additionally, in some embodiments, the computing device 130 may update the spatial coordinates of the target object to the map data, so as to obtain the updated map 131 . Furthermore, the computing device 130 stores the updated map 131 in the map database 120 . In this way, fast updating of the map can be achieved.

It should be understood that map database 120 and computing device 130 are shown in FIG. 1A as two separate entities for purposes of illustration only. In some embodiments, map database 120 may be stored in computing device 130 .

FIG. 1B shows a block diagram of an example software architecture of computing device 130 according to some embodiments of the present disclosure. As shown in the figure, the computing device 130 includes an acquiring unit 132 , a mapping relationship determining unit 134 and a space coordinate determining unit 136 .

The acquisition unit 132 is configured to acquire the image 111 . Image 111 records a target object and a reference object in a spatial region. In some embodiments, the acquiring unit 132 can acquire the image 111 from the image capturing device 110 . In some other embodiments, the obtaining unit 132 may obtain the image 111 uploaded by the user through the network. In yet other embodiments, the obtaining unit 132 may obtain the image 111 from a storage device (such as the storage device 140 ).

The acquiring unit 132 is also configured to acquire the map 121 . The map 121 includes map data including spatial coordinates of reference objects. In some embodiments, the acquiring unit 132 can acquire the map 121 from the map database 120 .

In some embodiments, computing device 130 may further include a storage unit (not shown) configured to store image 111 and map 121 . In such an embodiment, the obtaining unit 132 may obtain the image 111 and the map 121 from the storage unit.

The mapping relationship determination unit 134 is configured to determine the mapping relationship between the image 111 and the map 121 according to the pixel coordinates of the reference object in the image 111 and the spatial coordinates of the reference object.

The spatial coordinate determining unit 136 is configured to determine the spatial coordinates of the target object based on the pixel coordinates and the mapping relationship of the target object in the image 111 .

FIG. 2 shows an example of an image 111 captured by an image capture device 110 according to some embodiments of the present disclosure. In this example, image 111 is an image of a traffic intersection. However, it should be understood that this is done for illustration purposes only. In other embodiments, the image 111 may be an image including the target object and any suitable spatial region of the target object.

As shown in FIG. 2 , an electric police pole 210 is arranged at the traffic intersection. Traffic monitoring equipment 220 , 221 and 222 are installed on the electric police pole 210 . In the embodiment shown in FIG. 2 , the traffic monitoring devices 220 and 222 are, for example, electric police cameras, and the traffic monitoring device 221 is, for example, a traffic radar. One or more of the traffic monitoring devices 220, 221 and 222 may be relocated and reinstalled. The traffic monitoring equipment may also be newly added on the electric police pole 210. In these cases, the spatial coordinates of reinstalled or newly added traffic monitoring devices need to be determined. In the following, the determination of the spatial coordinates of the traffic monitoring device 222 will be taken as an example for description. In this example, the target object is the newly added traffic monitoring device 222 in the spatial area of the traffic intersection, and the reference object is the electric police pole 210 . Therefore, in the following, the traffic monitoring device 222 can be used interchangeably with the target object 222 , and the electric police pole 210 can be used interchangeably with the reference object 210 .

In some embodiments, the reference object 210 defines a plane on which the target object 222 resides (hereinafter also referred to as a "first plane"). In this example, the first plane defined by the reference object 210 is perpendicular to the ground. However, it should be understood that this is done for illustration purposes only. In other examples, the reference object may define any suitable plane. Control points 211 , 212 , 213 , 214 and 215 are located on reference object 210 . It can be understood that a "control point" is also called a marker point, which refers to a coordinate point that is easy to distinguish and has no ambiguity in positioning. Hereinafter, the control points 211 , 212 , 213 , 214 and 215 on the reference object 210 are also referred to as first control points 211 , 212 , 213 , 214 and 215 . In the context of the present disclosure, where the target object 222 occupies a small space, the target object 222 may be treated as a single point.

FIG. 3 shows an example of a map 121 according to some embodiments of the present disclosure. The map 121 is a map matching the image 111 shown in FIG. 2 . By way of example only, map 121 is shown in FIG. 3 as a reality map. However, it should be understood that map 121 may take any other suitable form. The computing device 130 can determine the map 121 in various ways, for example, it can determine the map 121 matching the image 111 by jumping paths from the road network to the traffic intersection and from the traffic intersection to the police pole 210 . Alternatively, computing device 130 may retrieve maps 121 that match image 111 by keywords of traffic intersections. It should be understood that this is an example only. Computing device 130 may determine map 121 that matches image 111 in any suitable manner.

In FIG. 3 , corresponding points in the map 121 of the plurality of first control points are denoted by reference numerals 311 , 312 , 313 , 314 and 315 .

In some embodiments, the first control points 211, 212, 213, 214, and 215 on the image 111 and the corresponding points 311, 312, 313, 314, and 315 on the map 121 can be annotated manually, so as to determine Pixel coordinates of the plurality of first control points and the plurality of corresponding points. In other embodiments, the first control points 211, 212, 213, 214, and 215 on the image 111 and the corresponding point 311 on the map 121 can be automatically marked by algorithms such as feature matching and point cloud registration in computer vision , 312, 313, 314 and 315, and then determine the pixel coordinates of a plurality of first control points and a plurality of corresponding points. It can be understood that it is also possible to adopt any other suitable marking method and method of determining pixel coordinates.

FIG. 4 shows a flowchart of an example method 400 according to some embodiments of the present disclosure. Method 400 may be performed by computing device 130 in FIG. 1A . For ease of discussion, the method 400 will be described with reference to FIGS. 1A , 2 and 3 . It should be understood that method 400 may also include additional steps not shown and/or steps shown may be omitted, and that the scope of the present disclosure is not limited in this regard.

At block 410 , computing device 130 acquires image 111 . Image 111 records target object 222 and reference object 210 in a spatial region. In some embodiments of the present disclosure, the image capture device 110 is used to capture images instead of professional surveying and mapping equipment, such as lidar surveying vehicles, drones, etc., thereby greatly reducing costs. In addition, the use of the image capture device 110 does not require qualifications, and is not restricted by conditions such as no-fly zones, collection time, and weather, so that a rapid response to environmental changes can be achieved.

At block 420 , the computing device 130 obtains map data of the map 121 including the spatial coordinates of the reference object 210 .

In block 430 , the computing device 130 determines a mapping relationship between the image 111 and the map 121 according to the pixel coordinates of the reference object 210 in the image 111 and the spatial coordinates of the reference object 210 .

In some embodiments, the computing device 130 may determine the mapping relationship between the image 111 and the map 121 according to the pixel coordinates of the plurality of first control points on the reference object 210 and the spatial coordinates of corresponding points in the map 121 . It can be understood that the computing device 130 may use any other suitable manner to determine the mapping relationship between the image 111 and the map 121 . The scope of the present disclosure is not limited in this respect.

As mentioned above, the pixel coordinates of the multiple first control points in the image 111 can be determined manually or by using algorithms such as feature matching and point cloud registration. For example, in the example shown in FIG. 2 , the plurality of first control points include control points 211 , 212 , 213 , 214 and 215 . The pixel coordinates of the control points 211 , 212 , 213 , 214 and 215 can be determined manually or by using algorithms such as feature matching and point cloud registration. Certainly, any suitable method may be used to determine the pixel coordinates of the plurality of first control points.

Still as mentioned above, the map 121 includes map data, and the map data includes at least the spatial coordinates of each point on the map 121 . Thus, based on the map data of map 121 , computing device 130 may determine the spatial coordinates of a plurality of corresponding points on map 121 . For example, in the example shown in FIG. 3 , computing device 130 may determine the spatial coordinates of a plurality of corresponding points 311 , 312 , 313 , 314 , and 315 based on map data.

In some embodiments, in order to reduce computational complexity, the computing device 130 may select coordinates in two dimensions whose values vary greatly from the spatial coordinates of multiple corresponding points. Furthermore, the computing device 130 may determine the above mapping relationship based on the pixel coordinates of the multiple first control points and the coordinates in the two dimensions in which the numerical values of the multiple corresponding points vary greatly. For example, in the example shown in FIG. 3 , the X-axis, Y-axis, and Z-axis define the coordinate system used by map 121 . In some embodiments, the coordinate system is a world class geographic coordinate system (WGS84). In this coordinate system, the origin of the coordinate system is located at the centroid of the earth, the Z-axis points to the direction of the protocol earth pole (CTP) defined by (International Time Bureau) BIH1984.0, and the X-axis points to the intersection of the zero-degree meridian plane of BIH1984.0 and the CTP equator , the Y-axis is determined by the right-hand rule. It should be understood that it is also possible to use any other appropriate coordinate system, such as Mars coordinate system (ie GCJ02 coordinate system), Baidu coordinate system (ie BD09 coordinate system) and so on.

Continuing to refer to the example shown in FIG. 3 , when the electric police pole 210 is located in the east direction, the y-coordinate and the z-coordinate of the points on the electric police pole 210 vary greatly, but the x-coordinate varies very little, so the computing device 130 can select the y-coordinate and z-coordinate of the point on the police pole 210 . When the electric police pole 210 is located in the north direction, the x-coordinate and the z-coordinate of the point on the electric police pole 210 vary greatly, but the y-coordinate varies very little, so the computing device 130 can select the point on the electric police pole 210 The x-coordinate and z-coordinate of the point.

In some embodiments, in order to select the coordinates in the two dimensions with large numerical changes from the spatial coordinates of multiple corresponding points, and then based on the pixel coordinates of multiple first control points and the numerical changes of multiple corresponding points The above-mentioned mapping relationship is determined by coordinates in the two dimensions with larger magnitudes, and the computing device 130 may execute the method 500 shown in FIG. 5 . Method 500 may be viewed as a specific implementation of the actions at block 430 described above. The actions at block 430 may also be carried out in any other suitable manner. For ease of discussion, the method 500 will be described with reference to FIGS. 1A , 2 and 3 .

In block 510, a first statistical result, a second statistical result and a third statistical result of the spatial coordinates of the plurality of corresponding points on the three dimensions of the spatial coordinate system are determined.

In some embodiments, the above statistical results include variance. For example, in the example shown in FIG. 3 , computing device 130 may determine a first variance of y-coordinates, a second variance of z-coordinates, and a third variance of x-coordinates of corresponding points 311, 312, 313, 314, and 315. variance.

In some other embodiments, the above statistical results include the length of the distribution interval. In such an embodiment, the computing device 130 determines the length of the first distribution interval, the length of the second distribution interval, and the length of the third distribution interval of the spatial coordinates of the plurality of corresponding points in the three dimensions of the spatial coordinate system. For example, in the example shown in FIG. 3 , the computing device 130 may determine that the distribution interval of the y-coordinates of the plurality of corresponding points 311, 312, 313, 314, and 315 is from y ₁ to y ₅ (where y ₅ >y ₁ ) , that is, the length of the distribution interval of the y coordinate is y ₅ -y ₁ ; the distribution interval of the z coordinates of a plurality of corresponding points 311, 312, 313, 314 and 315 is from z ₁ to z ₅ (where z ₅ > z ₁ ) , that is, the length of the distribution interval of z coordinates is z ₅ -z ₁ ; the distribution interval of x coordinates of multiple corresponding points 311, 312, 313, 314 and 315 is from x ₁ to x ₅ (wherein x ₅ > x ₁ ) , that is, the length of the distribution interval of the x coordinate is x ₅ -x ₁ .

It should be understood that the distribution intervals of the spatial coordinates of the multiple corresponding points described above are only examples. Depending on the specific application scenario, any suitable distribution interval may be used. The scope of the present disclosure is not limited in this respect.

In block 520, the computing device 130 compares the first statistical result, the second statistical result, and the third statistical result to determine whether the first statistical result and the second statistical result are greater than the third statistical result. For example, in the above embodiment where the statistical results include the length of the distribution interval, the calculation device 130 calculates the length of the distribution interval of the y coordinate (y ₅ -y ₁ ), the length of the distribution interval of the z coordinate (z ₅ -z ₁ ), and The length (x ₅ -x ₁ ) of the distribution interval of the x coordinate is compared.

If the computing device 130 determines at block 520 that both the first statistical result and the second statistical result are greater than the third statistical result, it means that among the spatial coordinates of a plurality of corresponding points, corresponding to the first statistical result and the second statistical result The numerical variation ranges of the coordinates on the dimension are larger than the numerical variation ranges of the coordinates on the dimension corresponding to the third statistical result. In this case, in block 530, the computing device 130 determines the above-mentioned Mapping relations.

For example, in the above embodiment where the statistical results include the length of the distribution interval, if the computing device 130 determines that both y ₅ -y ₁ and z ₅ -z ₁ are greater than x ₅ -x ₁ , then the computing device 130 determines the Both the length of the distribution interval of the y coordinate and the length of the distribution interval of the z coordinate are greater than the length of the distribution interval of the x coordinate. Furthermore, the computing device 130 determines the above-mentioned mapping based on the pixel coordinates of the plurality of first control points and the coordinates of the plurality of corresponding points on a dimension corresponding to the length of the distribution interval of the y coordinate and the length of the distribution interval of the z coordinate relation. In other words, the computing device 130 determines the above-mentioned mapping relationship based on the pixel coordinates of the plurality of first control points and the y-coordinates and z-coordinates of the plurality of corresponding points.

On the other hand, if the computing device 130 determines at block 520 that neither the first statistical result nor the second statistical result is greater than the third statistical result, at block 540 the computing device 130 calculates based on the pixel coordinates of the plurality of first control points, and the plurality of The coordinates on the dimension corresponding to the first statistical result and the third statistical result of the corresponding point are used to determine the above-mentioned mapping relationship, or based on the pixel coordinates of a plurality of first control points, and the second statistical result and the second statistical result of a plurality of corresponding points The coordinates on the dimension corresponding to the third statistical result are used to determine the above mapping relationship.

Specifically, if the computing device 130 determines at block 520 that both the first statistical result and the third statistical result are greater than the second statistical result, it means that the spatial coordinates of the multiple corresponding points are consistent with the first statistical result and the third statistical result. The numerical variation range of the coordinates on the dimension corresponding to the result is larger than the numerical variation range of the coordinate on the dimension corresponding to the second statistical result. In this case, in block 540, the computing device 130 determines the above-mentioned Mapping relations.

For example, in the above embodiment where the statistical results include the length of the distribution interval, if the computing device 130 determines that both y ₅ -y ₁ and x ₅ -x ₁ are greater than z ₅ -z ₁ , then the computing device 130 determines the Both the length of the distribution interval of the y coordinate and the length of the distribution interval of the x coordinate are greater than the length of the distribution interval of the z coordinate. Furthermore, the computing device 130 determines the above-mentioned mapping based on the pixel coordinates of the plurality of first control points and the coordinates of the plurality of corresponding points in a dimension corresponding to the length of the distribution interval of the y coordinate and the length of the distribution interval of the x coordinate relation. In other words, the computing device 130 determines the above mapping relationship based on the pixel coordinates of the multiple first control points and the y-coordinates and x-coordinates of the multiple corresponding points.

If the computing device 130 determines that both the second statistical result and the third statistical result are greater than the first statistical result at block 520, it means that among the spatial coordinates of a plurality of corresponding points, corresponding to the second statistical result and the third statistical result The numerical variation ranges of the coordinates on the dimension are larger than the numerical variation ranges of the coordinates on the dimension corresponding to the first statistical result. In this case, at block 540, the computing device 130 determines the above-mentioned Mapping relations.

For example, in the above embodiment where the statistical results include the length of the distribution interval, if the computing device 130 determines that both z ₅ -z ₁ and x ₅ -x ₁ are greater than y ₅ -y ₁ , then the computing device 130 determines the Both the length of the distribution interval of the z coordinate and the length of the distribution interval of the x coordinate are greater than the length of the distribution interval of the y coordinate. Furthermore, the computing device 130 determines the above-mentioned mapping based on the pixel coordinates of the plurality of first control points and the coordinates of the plurality of corresponding points on a dimension corresponding to the length of the distribution interval of the z coordinate and the length of the distribution interval of the x coordinate relation. In other words, the computing device 130 determines the above-mentioned mapping relationship based on the pixel coordinates of the plurality of first control points and the z-coordinates and x-coordinates of the plurality of corresponding points.

In some embodiments, the above mapping relationship includes a homography transformation relationship. For the purpose of illustration, in the following, how to determine the above mapping relationship will be described by taking the homography transformation relationship as an example. It should be understood that the mapping relationship between the image 111 and the map 121 may be any appropriate mapping relationship.

Consider the following example. In this example, it is assumed that the pixel coordinates of a first control point on the reference object 210 are denoted by u, v, and the spatial coordinates of the corresponding point of the first control point on the map 121 are denoted by x, y, z. In addition, it is also assumed that the computing device 130 determines that the values of the first coordinate (for example, the y coordinate) and the second coordinate (for example, the z coordinate) among the spatial coordinates of the corresponding point vary greatly. In this case, the pixel coordinates u, v of the first control point and the y-coordinate and z-coordinate of the corresponding point satisfy the following relationship:

where H represents the homography transformation matrix. Specifically, H is a 3×3 matrix and can be expressed as follows:

When calculating the homography transformation matrix H, h ₃₃ can be set to 1 or the modulus of the homography transformation matrix H can be changed to 1. In this case, H has eight degrees of freedom, so the homography transformation matrix H can be calculated by selecting at least four pairs of corresponding points on the reference object 210 and on the map 121 that lie on the same plane and are not collinear. In other words, at least four first control points are selected on the reference object 210 , the at least four first control points are located on the first plane and are not collinear. It should be understood that the values of the parameters of the homography transformation matrix described above are only examples, not limitations. Depending on specific application scenarios, each parameter in the homography transformation matrix can take any appropriate value.

In addition, in some application scenarios, the position of the control points may deviate by several pixels, and there may even be cases where control point pairs are mis-matched. If only four pairs of corresponding points are used to calculate the homography transformation matrix H, large errors may occur. Therefore, in order to make the calculation more accurate, more pairs of corresponding points can be selected to calculate the homography transformation matrix H. For example, in the example of FIG. 2 , five first control points 211 , 212 , 213 , 214 and 215 are selected. Accordingly, in the example of FIG. 3 , five corresponding points 311 , 312 , 313 , 314 and 315 corresponding to the first control point are selected. It should be understood that although Figures 2 and 3 each show five control points, this is for exemplary purposes only and is not intended to suggest any limitation. According to actual needs, any appropriate number of control points can be arranged on the reference object and the map.

In some embodiments, the homography transformation matrix H can be calculated by least square fitting, singular value decomposition, Levenberg-Marquarat (LM) algorithm, and the like. Alternatively, the homography transformation matrix H can be calculated through the findHomography() interface of the open source computer vision library (OpenCV). The homography transformation matrix H can be calculated using any suitable method currently existing or developed in the future, and the scope of the present disclosure is not limited in this respect.

Return to Figure 4. After determining the mapping relationship between the image 111 and the map 121 , at block 440 , the computing device 130 determines the spatial coordinates of the target object 222 based on the pixel coordinates of the target object 222 in the image 111 and the above mapping relationship.

In various embodiments of the present disclosure, it is not necessary to perform rescanning and mapping of the entire area containing the reference object to determine the spatial coordinates of the target object in the map, as in lidar surveying and oblique photography techniques. Thus, the time required to determine the spatial coordinates of the target object can be greatly shortened. In addition, there is no need to rely on professional operators to perform the method according to the embodiments of the present disclosure since lidar measurement and oblique photography techniques are not required.

In the embodiment in which the above-mentioned mapping relationship is determined based on the pixel coordinates of multiple first control points and the coordinates of multiple corresponding points in two dimensions in which the values vary greatly, the computing device 130 may base on the pixel coordinates of the target object 222 The coordinates and the above-mentioned mapping relationship determine the coordinates in the two dimensions in which the numerical values of the spatial coordinates of the target object 222 vary greatly. For example, in an embodiment where it is determined that both the first statistical result and the second statistical result are greater than the third statistical result, the computing device 130 may determine the relationship between the target object 222 and the above-mentioned first statistical result based on the pixel coordinates of the target object 222 and the above-mentioned mapping relationship. The first coordinate on the dimension corresponding to the statistical result and the second coordinate on the dimension corresponding to the second statistical result.

For example, in the above embodiment where the mapping relationship is a homography transformation relationship, the computing device 130 may determine the first coordinates and the second coordinates of the target object 222 based on the pixel coordinates of the target object 222 and the homography transformation matrix H. For example, the computing device 130 may determine the first coordinate (for example, the y coordinate) and the second coordinate (for example, the z coordinate) of the target object 222 by using the above formula (1).

In some embodiments, the spatial coordinates of the target object 222 further include third coordinates in the dimension corresponding to the above-mentioned third statistical result. The spatial coordinates of the plurality of corresponding points include first coordinates of the plurality of corresponding points on a dimension corresponding to the first statistical result and third coordinates on a dimension corresponding to the third statistical result. In some embodiments, after the first coordinate and the second coordinate of the target object 222 are determined, the computing device 130 may determine the third coordinate of the target object 222 by executing the method 600 shown in FIG. 6 . For ease of discussion, the method 600 will be described with reference to FIGS. 1A , 2 and 3 .

At block 610, computing device 130 selects at least two corresponding points from the plurality of corresponding points. The selected at least two corresponding points are collinear with the target object 222 on the map 121 . For example, in the example shown in FIG. 3, since corresponding points 311, 312, 313 are collinear with target object 222 in map 121, computing device 130 may select corresponding Points 311, 312, 313.

In some embodiments, in order to make the calculation of the third coordinate of the target object 222 more accurate, the computing device 130 may select one of the first coordinates and the second coordinates of the at least two selected corresponding points, which has a larger value change range Coordinates in the dimension. Furthermore, the computing device 130 may determine the third coordinate of the target object 222 based on the coordinates of the at least two corresponding points on the selected dimension, the third coordinates of the at least two corresponding points, and the coordinates of the target object 222 on the selected dimension. Three coordinates.

In some embodiments, in order to select a coordinate in a dimension with a larger value change range from the first coordinates and second coordinates of the selected at least two corresponding points, the computing device 130 may use In the spatial coordinates, the coordinates on the two dimensions whose values vary greatly are selected in a similar way.

Specifically, at block 620, the computing device 130 compares the first statistical result and the second statistical result of the spatial coordinates of at least two corresponding points. If the computing device 130 determines at block 620 that the first statistical result is greater than the second statistical result, at block 630 the computing device 130 determines based on the first and third coordinates of at least two corresponding points and the first coordinate of the target object 222 The third coordinate of the target object 222 .

For example, computing device 130 may compare a first variance of first coordinates and a second variance of second coordinates of at least two corresponding points. If the first variance is greater than the second variance, the computing device 130 may determine that at least two corresponding points have a magnitude of change in value of the first coordinate that is greater than a magnitude of change in value of the second coordinate. In turn, computing device 130 selects first coordinates of at least two corresponding points.

Alternatively, the computing device 130 may compare the length of the first distribution interval and the length of the second distribution interval of at least two corresponding points. If the length of the first distribution interval is greater than the length of the second distribution interval, the computing device 130 may determine that the magnitude of change in the value of the first coordinate of at least two corresponding points is greater than the magnitude of change in value of the second coordinate. In turn, computing device 130 selects first coordinates of at least two corresponding points.

Consider the example shown in Figure 3. Assume that computing device 130 has selected corresponding points 311 , 312 , 313 and has determined the y-coordinate and z-coordinate of target object 222 . When the electric police pole 210 is located in the east direction, the variation range of the y coordinates of the corresponding points 311 , 312 , 313 is larger than the variation range of the z coordinates. In this case, computing device 130 may select the y-coordinates of corresponding points 311 , 312 , 313 . In turn, computing device 130 may determine the x-coordinate of target object 222 based on the y-coordinates and x-coordinates of corresponding points 311 , 312 , 313 and the y-coordinate of target object 222 .

As previously mentioned, the selected at least two corresponding points are substantially collinear with the target object 222 in the map 121 . Therefore, a linear relationship is satisfied between at least two corresponding points and the respective first coordinates and third coordinates of the target object 222 . Furthermore, since the first coordinates and the third coordinates of the at least two corresponding points are known, the computing device 130 may determine the linear relationship based on the first coordinates and the third coordinates of the at least two corresponding points. Further, the computing device 130 may determine the third coordinates of the target object 222 based on the linear relationship and the first coordinates of the target object 222 .

In some embodiments, in order to determine the above-mentioned linear relationship, the computing device 130 may fit a straight line equation based on respective first coordinates and third coordinates of at least two corresponding points. Any suitable means now available or developed in the future may be used to fit the equation of a line, as the scope of the present disclosure is not limited in this respect.

It can be understood that the method for determining the spatial coordinates of a target object according to various embodiments of the present disclosure can be executed in parallel for multiple target objects associated with the reference object after the reference object is installed, without Executed individually for each target object after object installation and commissioning. As a result, the efficiency of determining the spatial coordinates of multiple target objects is improved, and the engineering difficulty is greatly reduced.

The above describes the scenario of applying the embodiments of the present disclosure to determine the spatial coordinates of the newly added traffic monitoring device 222 in the spatial area with reference to FIG. 2 . Besides, the embodiments of the present disclosure can also be applied to the scene of determining the spatial coordinates of the high-rise part of the surface of the high-rise building. Details will be described below in conjunction with FIG. 7 .

FIG. 7 shows a schematic diagram of an example image 700 according to other embodiments of the present disclosure. In this example, image 700 is an image of a building surface.

As shown in FIG. 7 , image 700 includes a high-rise portion 710 (also referred to as a first portion) and a low-rise portion 720 (also referred to as a second portion) of the building surface. High level portion 710 includes a "XXX" icon. In this example, the target object is the high-level part 710 and the reference object is the low-level part 720 .

To determine the spatial coordinates of high-level portion 710 , computing device 130 may acquire image 700 from image capture device 110 and acquire map data for a map (not shown) that matches image 700 from map database 120 . The map data includes the spatial coordinates of the lower layer part 720 . The computing device 130 determines the mapping relationship between the image 700 and the above-mentioned map according to the pixel coordinates of the low-level part 720 in the image 700 and the spatial coordinates of the low-level part 720 . In some embodiments, the computing device 130 may determine the above mapping relationship by executing the method 500 described above. The specific details of the method 500 will not be repeated here.

After the above mapping relationship is determined, the computing device 130 determines the spatial coordinates of the high-level part 710 based on the pixel coordinates of the high-level part 710 in the image 700 and the above-mentioned mapping relationship. For example, in the embodiment where the above mapping relationship is a homography transformation relationship, the computing device 130 may use the above formula (1) to determine the first coordinate and the second coordinate of the high-level part 710 . In turn, computing device 130 may determine the third coordinates of high-level portion 710 by performing method 600 described above. The specific details of the method 600 will not be repeated here.

It should be understood that the process of determining the spatial coordinates of the high-level portion 710 including the "XXX" icon is described above as an example only. However, embodiments of the present disclosure may also be applied to determining the spatial coordinates of an arbitrary position of a high-rise portion of a high-rise building surface.

It can be understood that it is usually difficult to determine the spatial coordinates of the high-rise part of the surface of a high-rise building through technologies such as lidar measurement and oblique photography when collecting map data. However, the spatial coordinates of the high-rise part of the high-rise building surface can be determined more conveniently and quickly by using the embodiments of the present disclosure.

FIG. 8 shows a schematic block diagram of an apparatus 800 provided by the present disclosure. As shown in the figure, the apparatus 800 includes an acquiring unit 132 , a mapping relationship determining unit 134 and a space coordinate determining unit 136 . It should be understood that, in some embodiments, the apparatus 800 may be the aforementioned computing device 130 in FIG. 2 or a part of the computing device 130 .

The acquiring unit 132 is configured to acquire images. The image records a target object and a reference object in a spatial region. In some embodiments, the acquisition unit 132 may acquire the image from the image capture device 110 . In some other embodiments, the obtaining unit 132 may obtain the image uploaded by the user through the network. In yet other embodiments, the obtaining unit 132 may obtain images from a storage device (such as the storage device 140 shown in FIG. 1A ).

The obtaining unit 132 is also configured to obtain a map. The map includes map data including spatial coordinates of reference objects. In some embodiments, the acquiring unit 132 can acquire the map from the map database 120 .

In some embodiments, computing device 130 may further include a storage unit (not shown) configured to store images and maps. In such an embodiment, the retrieval unit 132 may retrieve images and maps from the storage unit.

The mapping relationship determination unit 134 is configured to determine the mapping relationship between the image and the map according to the pixel coordinates of the reference object in the image and the spatial coordinates of the reference object.

The spatial coordinate determining unit 136 is configured to determine the spatial coordinates of the target object based on the pixel coordinates and the mapping relationship of the target object in the image.

In some embodiments, the apparatus 800 further includes an updating unit configured to update the spatial coordinates of the target object to the map data.

In some embodiments, the target object includes: entities newly added in the spatial region after map data collection is performed on the spatial region; reference objects include: entities existing in the spatial region before map data collection is performed on the spatial region.

In some embodiments, the target object includes a first part of a building in the spatial region, and the reference object includes a second part of the building; the first part is collected by a data collection device that collects map data, and the second part is not collected by the data collection device arrive.

In some embodiments, the mapping relationship determining unit 134 is further configured to determine the image and the map according to the pixel coordinates of the multiple first control points on the reference object and the spatial coordinates of the corresponding points of the multiple first control points in the map. mapping relationship between them.

The above three units can perform data transmission with each other through communication channels. It should be understood that each unit included in the device 800 can be a software unit, or a hardware unit, or partly software unit and partly hardware unit.

FIG. 9 shows a block diagram of a computing device 900 capable of implementing embodiments of the present disclosure. As shown in FIG. 9 , the computing device 900 includes: a processor 910 , a communication interface 920 and a memory 930 , and the processor 910 , the communication interface 920 and the memory 930 are connected to each other through an internal bus 940 . It should be understood that the computing device 900 may be a computing device in a cloud environment, or a computing device in an edge environment.

The processor 910 may be composed of one or more general-purpose processors, such as a central processing unit (central processing unit, CPU), or a combination of a CPU and a hardware chip. The aforementioned hardware chip may be an application-specific integrated circuit (application-specific integrated circuit, ASIC), a programmable logic device (programmable logic device, PLD) or a combination thereof. The aforementioned PLD may be a complex programmable logic device (complex programmable logic device, CPLD), a field-programmable gate array (field-programmable gate array, FPGA), a general array logic (generic array logic, GAL) or any combination thereof.

The bus 940 may be a peripheral component interconnect standard (peripheral component interconnect, PCI) bus, an extended industry standard architecture (extended industry standard architecture, EISA) bus, or the like. The bus 940 can be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, only one thick line is used in FIG. 9 , but it does not mean that there is only one bus or one type of bus.

The memory 930 may include a volatile memory (volatile memory), such as a random access memory (random access memory, RAM); the memory 930 may also include a non-volatile memory (non-volatile memory), such as a read-only memory (read-only memory, ROM), flash memory (flash memory), hard disk (hard disk drive, HDD) or solid-state drive (solid-state drive, SSD); the memory 930 may also include a combination of the above types.

It should be noted that the memory 930 of the computing device 900 stores codes corresponding to each unit of the apparatus 800 , and the processor 910 executes these codes to realize the functions of each unit of the apparatus 800 , that is, execute the methods at blocks 410 to 440 .

Program codes for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special purpose computer, or other programmable data processing devices, so that the program codes, when executed by the processor or controller, make the functions/functions specified in the flow diagrams and/or block diagrams Action is implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the above embodiments, all or part of them may be implemented by software, hardware, firmware or any combination thereof. When implemented using a software program, it may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When computer-executed instructions are loaded and executed on a computer, the processes or functions according to the above-mentioned embodiments of the present application are produced in whole or in part. A computer can be a general purpose computer, special purpose computer, computer network, or other programmable device. Computer instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium, e.g. Coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (such as infrared, wireless, microwave, etc.) transmission to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that can be accessed by a computer, or may contain one or more data storage devices such as servers and data centers that can be integrated with the medium. Available media may be magnetic media (eg, floppy disk, hard disk, magnetic tape), optical media (eg, DVD), or semiconductor media (eg, solid state disk (solid state disk, SSD)) and the like.

In addition, while operations are depicted in a particular order, this should be understood to require that such operations be performed in the particular order shown, or in sequential order, or that all illustrated operations should be performed to achieve desirable results. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while the above discussion contains several specific implementation details, these should not be construed as limitations on the scope of the disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single implementation. Conversely, various features that are described in the context of a single implementation can also be implemented in multiple implementations separately or in any suitable subcombination.

Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms of implementing the claims.

Claims (10)

1. A method for determining the spatial coordinates of a target object, comprising: acquiring images recording a target object and a reference object in a spatial region; Obtaining map data of the map, the map data including the spatial coordinates of the reference object, the spatial coordinates of the reference object including coordinates of the reference object in three dimensions of space; determining a mapping relationship between the image and the map based on pixel coordinates of the reference object in the image and spatial coordinates of the reference object; and determining the spatial coordinates of the target object based on the pixel coordinates of the target object in the image and the mapping relationship, where the spatial coordinates of the target object include three-dimensional coordinates of the target object in space; updating the spatial coordinates of the target object to the map data. 2. The method of claim 1, wherein, The target object includes: an entity newly added in the spatial region after map data collection is performed on the spatial region; The reference objects include: entities existing in the spatial region before map data collection is performed on the spatial region. 3. The method of claim 1, wherein, the target object includes a first portion of a building in the spatial region, and the reference object includes a second portion of the building; The first part is collected by the data collection device that collects the map data, and the second part is not collected by the data collection device. 4. The method according to any one of claims 1-3, wherein determining the mapping relationship between the image and the map comprises: The mapping relationship is determined according to the pixel coordinates of the plurality of first control points on the reference object and the spatial coordinates of corresponding points of the plurality of first control points in the map. 5. A device for determining the spatial coordinates of a target object, comprising: An acquisition unit configured to acquire map data of an image and a map, the image records a target object and a reference object in a spatial area, the map data includes the spatial coordinates of the reference object, and the spatial coordinates of the reference object The coordinates include the coordinates of the reference object in three dimensions of space; a mapping relationship determining unit configured to determine a mapping relationship between the image and the map according to the pixel coordinates of the reference object in the image and the spatial coordinates of the reference object; and a spatial coordinate determining unit configured to determine the spatial coordinates of the target object based on the pixel coordinates of the target object in the image and the mapping relationship, the spatial coordinates of the target object including the spatial coordinates of the target object The three-dimensional coordinates of ; An updating unit configured to update the spatial coordinates of the target object to the map data. 6. The device according to claim 5, characterized in that, The target object includes: an entity newly added in the spatial region after map data collection is performed on the spatial region; The reference objects include: entities existing in the spatial region before map data collection is performed on the spatial region. 7. The device of claim 5, wherein: the target object includes a first portion of a building in the spatial region, and the reference object includes a second portion of the building; The first part is collected by the data collection device that collects the map data, and the second part is not collected by the data collection device. 8. The device according to any one of claims 5-7, wherein the mapping relationship determining unit is further configured to: The mapping relationship is determined according to the pixel coordinates of the plurality of first control points on the reference object and the spatial coordinates of corresponding points of the plurality of first control points in the map. 9. A computing device, characterized in that the computing device comprises a memory and a processor, and the processor executes computer instructions stored in the memory, so that the computing device executes any one of claims 1-4. described method. 10. A computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor executes any one of claims 1-4. method described in the item.

Images