WO2025010899A1 - Stitching method, apparatus and device for deep-sea cold spring area image, and storage medium - Google Patents

Abstract

Disclosed in the present application are a stitching method, apparatus and device for deep-sea cold spring area images, and a storage medium. The method comprises: according to a set period, screening a plurality of images to be stitched, so as to obtain a set of images sorted in the order of acquisition times, wherein a stitching module is used for setting, in the set of images, retention areas of the images and matching points corresponding to the retention areas of the images, and the matching points are indicated as points having the same feature in two adjacent images; and sequentially stitching the images in the set of images according to the retention areas and the matching points corresponding to the retention areas of the images. Thus, retention areas of images are set, and the retention areas serve as selection areas of matching points, that is, a set of images and the retention areas of the images can be used in an underwater environment, so as to realize the coherence of image stitching, avoid the mismatching of picture stitching, and select the matching points in the retention areas, thereby ensuring that the images can be accurately stitched and are continuous.

Description

Method, device, equipment and storage medium for stitching images of deep-sea cold seep areas

This application claims the priority of the Chinese patent application filed with the China Patent Office on July 10, 2023, with application number 2023108385779 and application name “Stitching method, device, equipment and storage medium for deep-sea cold spring area images”, all contents of which are incorporated by reference in this application.

Technical Field

The present application relates to the technical field of underwater image processing, and in particular to a method, device, equipment and storage medium for stitching images of deep-sea cold spring areas.

Background Art

The accuracy of underwater image stitching technology is an important prerequisite for its application in biometrics, which can improve the accuracy and robustness of underwater biometrics.

There have been many related studies on underwater image stitching, such as stitching methods based on feature matching, stitching methods based on panoramic images, etc. These methods usually involve the steps of registration, correction, fusion, etc. of multiple images, aiming to obtain wider and clearer underwater images.

For special underwater application scenarios, such as images of deep-sea cold springs, the deep-sea cold springs are located in areas that are difficult to reach by natural light. The brightness difference of images obtained from this area is not obvious, and factors such as color and texture in the deep-sea environment may also cause image distortion and interference, resulting in quality problems after underwater image stitching.

Therefore, there is an urgent need for a stitching method for deep-sea cold spring images to improve the above problems.

Summary of the invention

The purpose of the present application is to provide a method, device, equipment and storage medium for stitching images of deep-sea cold spring areas, which achieves the continuity of image stitching by utilizing image sets and reserved areas of each image in a deep-sea environment, avoids mismatching of image stitching, and selects matching points in the reserved area so that images can be accurately and continuously stitched, thereby improving the quality problem of underwater image stitching.

In a first aspect, the present application discloses a method for stitching images of a deep-sea cold seep area, comprising the following steps:

S1, obtaining multiple images to be stitched;

S2, screening multiple images to be stitched according to a set period to obtain a set of images sorted in the order of image acquisition time;

S3, setting the reserved area of each image and the matching points corresponding to the reserved area of each image in the image set, wherein the matching points are indicated as points with the same features in two adjacent images;

S4. According to the reserved area and the matching points corresponding to the reserved area of each image, the reserved areas and matching points in two temporally adjacent pictures are obtained to align and sequentially stitch the images in the image set.

Based on the above technical content, multiple images to be stitched can be screened according to a set period to obtain a set of images sorted in time order, where the time order is the time order of the images to be stitched. Then, set The reserved area of each image and the matching points corresponding to each image are set. The matching points are points with the same features in two adjacent images. The image set and the reserved area of each image can be used in an underwater environment to achieve the continuity of image stitching, avoid mismatching of image stitching, and select matching points in the reserved area to ensure that the images can be accurately stitched and continuous, thereby improving the quality of underwater image stitching.

Optionally, before screening multiple images to be stitched according to a set period to obtain a set of images sorted by acquisition time, it also includes: formulating a coordinate system according to the specifications of one of the images to be stitched, and adjusting the specifications of the remaining images based on the coordinate system, so as to obtain multiple images to be stitched of the same scale.

By formulating a coordinate system and adjusting the specifications of the images to be stitched based on the coordinate system, multiple images to be stitched of the same scale are obtained, and the sizes of the images are further adjusted according to user needs, which is beneficial to image stitching in subsequent steps.

Optionally, multiple images to be stitched are screened according to a set period to obtain a set of images sorted by acquisition time, specifically including: obtaining motion parameters of an image acquisition device; calculating a set period for screening multiple images to be stitched according to the motion parameters of the image acquisition device and the specifications of the images to be stitched; obtaining and recording the acquisition time of the first image acquired through the screening, and taking the acquisition time as a reference, extracting images to be stitched at intervals of a set period to obtain a set of images sorted in order of image acquisition time.

By reserving enough reserved areas when stitching images in a reference filtered image set, the problem of ghosting in stitched images and the problem of different sizes of images acquired by a camera device are further solved.

Optionally, the method of setting a reserved area for each image in the image set specifically includes: under the condition of filtering images at a set period, when it is detected that the overlapping partial areas of two images in the image set with adjacent acquisition times account for a set proportion in the two images, highlighting the overlapping partial areas of the two adjacent images; using the overlapping partial areas as the reserved areas of the two images in the image set with adjacent acquisition times.

By setting the reserved area of each image, it is equivalent to constraining the position of the splicing between the images to be fuzzy determined, highlighting the overlapping area of the two adjacent images, and further selecting the images to be spliced to avoid splicing errors due to multiple overlapping parts when stitching subsequent images.

Optionally, setting matching points corresponding to the reserved areas of each image in the image set specifically includes: using a scale-invariant feature transform (SIFT) method to extract key points in each image in the image set; matching the key points in each image in the image set, and determining matching points from the key points of multiple images to be spliced.

By adopting the scale-invariant feature transform (SIFT) method, the key points in each image in the image set are extracted, and then the key points in each image in the image set are matched, and the matching points are determined from the key points of the multiple images to be spliced, so as to further achieve precise docking.

In a second aspect, the present application discloses a splicing device for deep-sea cold seep images, comprising:

A first acquisition module, the first acquisition module is used to acquire a plurality of images to be stitched;

A second acquisition module, the second acquisition module is used to screen a plurality of images to be stitched according to a set period to obtain an image set sorted in the order of image acquisition time;

A stitching module is used to set a reserved area for each image and matching points corresponding to the reserved area of each image in an image set, wherein a matching point indicates a point with the same features in two adjacent images, and based on the reserved area and the matching points corresponding to the reserved area of each image, the reserved area and matching points in two temporally adjacent images are obtained to align and stitch each image in the image set in sequence.

Based on the above technical content, a plurality of images to be stitched are acquired through a first acquisition module, and then a second acquisition module is used to According to the set period, multiple images to be stitched are screened to obtain an image set, which is sorted according to the acquisition time sequence of the multiple images to be stitched. Then, the reserved area of each image and the matching points corresponding to the reserved area of each image are set in the image through the stitching module. The matching points indicate the points with the same features in two adjacent images. According to the reserved area and the matching points, the images whose reserved areas and matching points are aligned in the two images with adjacent acquisition times are stitched in sequence. The image set and the reserved area of each image can be used in an underwater environment to achieve the coherence of image stitching, avoid mismatching of image stitching, and select matching points in the reserved area to ensure that the images can be accurately spliced and continuous, thereby improving the quality of underwater image stitching.

Optionally, the stitching device further includes: a first processing module, which is used to formulate a coordinate system according to the specifications of one of the images to be stitched, and adjust the specifications of the remaining images based on the coordinate system, so as to obtain multiple images to be stitched of the same scale.

A coordinate system is drawn up by the first processing module, and the image specifications are adjusted based on the coordinate system to obtain multiple images to be stitched of the same scale, and the image size is further adjusted according to user needs, which is beneficial to image stitching in subsequent steps.

Optionally, the stitching module includes: a first acquisition subunit, which is used to acquire motion parameters of an image acquisition device; a second acquisition subunit, which is used to calculate a set period for screening multiple images to be stitched according to the motion parameters of the image acquisition device and the specifications of the images to be stitched; a third acquisition subunit, which is used to acquire and record the acquisition time of the first image acquired through screening, and extract the image to be stitched at intervals of a set period based on the acquisition time to acquire a set of images sorted in order of image acquisition time; the stitching module also includes: a first detection subunit, which is used to detect, under the condition of screening images at a set period, that the overlapping partial areas of two images with adjacent acquisition times in the image set have a proportion in the two images, respectively, and highlight the overlapping partial areas of the two adjacent images; a first determination subunit, which is used to use the overlapping partial areas as reserved areas of the two images with adjacent acquisition times in the image set.

Setting the reserved area of each image through the stitching module is equivalent to constraining the stitching position between each image to be fuzzily determined, highlighting the overlapping area of the two adjacent images, and further selecting the image to be stitched to avoid stitching errors caused by multiple overlapping parts during subsequent image stitching.

In a third aspect, the present application discloses a stitching device for deep-sea cold seep images, comprising:

processor;

a memory for storing processor-executable instructions;

The processor is configured to execute the splicing method described in the first aspect.

In a fourth aspect, the present application discloses a computer-readable storage medium, wherein the computer storage medium stores computer-executable instructions, and when the computer-executable instructions are executed, the steps of the method described in the first aspect are implemented.

In a fifth aspect, the present application discloses a computer program product, characterized in that it includes a computer program, which, when executed by a processor, implements the splicing method described in the first aspect.

In combination with the above technical solution, the present application obtains an image set sorted by acquisition time by screening multiple images to be stitched according to a set period, sets a reserved area of each image and a matching point corresponding to the reserved area of each image in the image set, wherein the matching point indicates a point with the same features in two adjacent images; according to the reserved area and the matching point corresponding to the reserved area of each image, the images in the image set are stitched in sequence, thereby achieving the goal of setting the reserved area of each image, and using the reserved area as a selection area for the matching point Domain, that is, it can use the image set and the reserved area of each image in the deep sea environment to achieve the coherence of image stitching, avoid mismatching of image stitching, and select matching points in the reserved area to ensure that the images can be accurately stitched and continuous.

For better understanding and implementation, the present application is described in detail below with reference to the accompanying drawings.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a flowchart of a method for stitching images of a deep-sea cold seep area provided by an embodiment of the present application;

FIG2 is a second flowchart of a method for stitching images of a deep-sea cold seep area provided by an embodiment of the present application;

FIG3 is a schematic diagram 1 of the stitching states of various images when ghosting occurs when stitching images together in a stitching method for deep-sea cold seep images provided by an embodiment of the present application;

FIG4 is a second schematic diagram showing the splicing state between images in a method for splicing images of a deep-sea cold seep area provided by an embodiment of the present application;

FIG5 is a structural block diagram 1 of a splicing device for deep-sea cold seep images provided by an embodiment of the present application;

FIG6 is a second structural block diagram of a device for stitching images of a deep-sea cold seep area provided by an embodiment of the present application;

FIG. 7 is a structural block diagram of an indication splicing module in a splicing device for deep-sea cold spring area images provided by an embodiment of the present application.

DETAILED DESCRIPTION

In order to better illustrate the present application, the present application is further described in detail below with reference to the accompanying drawings.

It should be clear that the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the embodiments of the present application.

The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the embodiments of the present application. The singular forms of "a", "said" and "the" used in the embodiments of the present application and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and/or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the attached claims. In the description of the present application, it should be understood that the terms "first", "second", "third", etc. are only used to distinguish similar objects, and do not have to be used to describe a specific order or sequence, nor can they be understood as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to the specific circumstances.

In addition, in the description of this application, unless otherwise specified, "plurality" means two or more. "And/or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and/or B can mean: A exists alone, A and B exist at the same time, and B exists alone. The character "/" generally indicates that the associated objects are in an "or" relationship.

There have been many related studies on underwater image stitching, such as stitching methods based on feature matching, These methods usually involve the steps of registration, correction, fusion, etc. of multiple images, aiming to obtain wider and clearer underwater images.

For special underwater application scenarios, such as images of deep-sea cold seeps, the deep-sea cold seeps are located in areas that are difficult to reach by natural light. The brightness difference of images obtained from this area is not obvious, and factors such as color and texture in the deep-sea environment may also cause image distortion and interference, resulting in a small number of optional feature points in the connection areas of each image of the deep-sea cold seep. It can be seen from the above that image stitching in the deep-sea cold seep area is more difficult.

Therefore, based on the above, the technical problem actually solved by the present application is to propose a solution that can realize the stitching of images acquired in the deep-sea cold spring area, so as to improve the quality of the stitched images.

First of all, it should be noted that in this embodiment, a camera device is used to acquire images, and the surrounding underwater environment images are acquired at a fixed point in the underwater environment. Images with different pixels or different resolutions can also be obtained according to the focus size of the camera device.

Based on this, a specific embodiment is described below.

FIG1 is a flowchart of a method for stitching images of deep-sea cold seep areas provided by an embodiment of the present application.

FIG2 is a second flowchart of a method for stitching images of deep-sea cold seep areas provided by an embodiment of the present application.

FIG3 is a schematic diagram showing the stitching states of various images when ghosting occurs when stitching images together in a stitching method for deep-sea cold spring images provided by an embodiment of the present application.

In a first aspect of an embodiment of the present application, as shown in FIG1 , a method for stitching images of a deep-sea cold seep area is provided, comprising the following steps:

Step S1, obtaining a plurality of images to be stitched;

An illustrative example of the present application: the images to be stitched may be images acquired by a camera in a deep-sea cold seep area.

Before processing the images to be stitched, the images acquired by the camera are not of the same specifications. Specifically, the resolution or pixels of each image are different due to the different focus sizes when the camera acquires the image. If the images are not matched during stitching, the key images will be eliminated before the image stitching is performed, resulting in distortion of the stitched image. Therefore, after completing the acquisition of the images to be stitched, the following steps need to be performed:

Step S10: A coordinate system is prepared according to the specifications of one of the images to be stitched, and the specifications of the remaining images are adjusted based on the coordinate system, thereby obtaining multiple images to be stitched of the same scale. The executed steps are shown in FIG2 .

First of all, it is necessary to understand that the images acquired by the camera equipment are enlarged and reduced in proportion. A coordinate system is formulated by selecting the specifications of an image to be stitched from the images to be stitched. In fact, the coordinate system can also be set according to the needs of the user, and then the size of the image can be adjusted according to the needs of the user. For example, the specifications of the selected image to be stitched are 300dpi, and the length and width of the image are 35mmX45mm. The coordinate system is established with the length and width of the selected image, and the remaining images to be stitched can be enlarged and reduced in proportion according to the established standards, which is conducive to subsequent stitching.

Step S2, screening multiple images to be stitched according to a set period to obtain an image set sorted according to the image acquisition time;

The camera equipment acquires images of the underwater environment in a time sequence. When stitching, in order to avoid stitching errors caused by multiple overlapping parts when stitching images, for example, the images to be stitched are set to be the first image, the second image, ..., the Nth image, where N is an integer; when the first image A1 and the second image B2 are stitched together and then stitched with the third image C3, as shown in FIG3 , each image is sorted according to the acquisition time. If the feature point for stitching is not the edge of the image, multiple overlapping areas will appear, which will cause the stitched image to be distorted and have obvious ghosting.

Then it is necessary to select the images to be stitched.

Therefore, specifically, in step S2, the motion parameters of the image acquisition device are obtained;

A set period for screening a plurality of images to be spliced is calculated based on motion parameters of an image acquisition device and specifications of images to be spliced;

The acquisition time of the first image obtained through screening is obtained and recorded. Based on the acquisition time, the image to be stitched is extracted at every set period to obtain a set of images sorted in the order of image acquisition time.

The motion parameters of the device specifically include the rotation speed of the camera device, etc. When stitching the images in the reference filtered image set, sufficient reserved areas are reserved to solve the problem of ghosting of the stitched images and the size of the pictures obtained by the camera device.

FIG4 is a schematic diagram showing the stitching status between images in a stitching method for deep-sea cold seep images provided by an embodiment of the present application.

Specifically, the set period for screening multiple images to be stitched is calculated according to the rotation speed of the camera device and the specifications of the picture, and the screening time of each image in the image set is calculated, such as acquiring images at intervals of 15s, that is, 15s, 30s, 45s... and acquiring images at arithmetic intervals of 15s, and the interval time of 15s is the set period. Finally, the picture set situation shown in Figure 4 must be met, satisfying that the overlapping part between the first image A1 and the second image B2 is unique, the overlapping part between the second image B2 and the third image C3 is unique, and there is no overlapping part between the first image A1 and the third image C3.

Step S3, setting the reserved area of each image and the matching points corresponding to the reserved area of each image in the image set, wherein the matching points are indicated as points with the same features in two adjacent images;

The step of setting a reserved area for each image in the image set specifically includes:

Under the condition of screening images at a set period, when it is detected that the overlapping partial areas of two images acquired at adjacent times in the image set account for a set proportion in the two images respectively, the overlapping partial areas of the two adjacent images are highlighted;

The overlapping partial areas are respectively used as the reserved areas of two images with adjacent acquisition times in the image set.

The step of setting matching points corresponding to the reserved areas of each image in the image set specifically includes:

The scale-invariant feature transform (SIFT) method is used to extract key points in each image in the image set;

As an illustrative example of the present application, the SIFT (Scale Invariant Feature Transform) method can be used to detect key points in the retained area in the first image A1 and key points in the retained area in the second image B2.

Key points in each image in the image set are matched, and matching points are determined from the key points of the plurality of images to be spliced.

From the above, an illustrative example of the present application sets the reserved area of each image, which is equivalent to constraining the fuzzy determination of the stitching position between each image. In Figure 4, the preliminary stitching position of the first image A1 and the second image B2 is determined by overlapping the reserved area between the first image A1 and the second image B2, and then the alignment position of the first image A1 and the second image B2 is accurately determined through specific feature points, thereby completing precise stitching.

Each image has two reserved areas to enable sequential stitching to form a panoramic image after stitching.

Step S4: According to the reserved area and the matching points corresponding to the reserved areas of each image, the reserved areas and matching points in two temporally adjacent pictures are obtained to align and sequentially stitch the images in the image set.

In this embodiment, an illustrative example of the present application: according to the relationship between the first image A1 and the second image B2 The reserved area is used to determine the approximate position of the splicing between the first image A1 and the second image B2, and the first image and the second image are accurately spliced according to the matching points between the first image A1 and the second image B2 in the reserved area. For the same reason, the second image B2 and the third image C3 are spliced in the same splicing alignment method.

In this embodiment, a stitching method for deep-sea cold spring area images is used. By screening multiple images to be stitched according to a set period, a set of images sorted according to the acquisition time is obtained. The stitching module is used to set a reserved area for each image and matching points corresponding to the reserved area of each image in the image set, wherein the matching point indicates a point with the same feature in two adjacent images; according to the reserved area and the matching points corresponding to the reserved area of each image, the images in the image set are stitched in sequence. The above can be achieved by setting the reserved area of each image, and the reserved area is used as the selection area of the matching point, that is, the image set and the reserved area of each image can be used in an underwater environment to achieve the coherence of image stitching, avoid mismatching of picture stitching, and select matching points in the reserved area to ensure that the images can be accurately stitched and continuous.

FIG5 is a structural block diagram 1 of a stitching device for deep-sea cold seep images provided by an embodiment of the present application.

For the second aspect of the embodiment of the present application, as shown in FIG5 , a stitching device 100 for deep-sea cold seep images is provided, comprising:

A first acquisition module 101, wherein the first acquisition module 101 is used to acquire a plurality of images to be stitched;

A second acquisition module 102, the second acquisition module 102 is used to screen a plurality of images to be stitched according to a set period to obtain an image set sorted in the order of image acquisition time;

The stitching module 103 is used to set the reserved area of each image and the matching points corresponding to the reserved area of each image in the image set, wherein the matching points indicate points with the same features in two adjacent images, and the reserved areas and matching points corresponding to the reserved areas of each image are obtained according to the reserved areas and the matching points in the two temporally adjacent pictures to align the reserved areas and matching points, and stitch the images in the image set in sequence.

The various modules in the splicing device for deep-sea cold spring area images of this embodiment can be integrated and loaded into a chip to realize the various functions as described above to realize this embodiment.

FIG6 is a second structural block diagram of a device for stitching images of deep-sea cold spring areas provided in one embodiment of the present application.

As shown in FIG6 , further, the splicing device 100 further includes:

The first processing module 104 is used to formulate a coordinate system according to the specifications of one of the images to be stitched, and adjust the specifications of the remaining images based on the coordinate system, so as to obtain multiple images to be stitched of the same scale.

FIG. 7 is a structural block diagram of an indication splicing module in a splicing device for deep-sea cold spring area images provided by an embodiment of the present application.

As shown in FIG. 7 , further, the splicing module 103 includes:

A first acquisition subunit 1031, the first acquisition subunit 1031 is used to acquire motion parameters of the image acquisition device;

A second acquisition subunit 1032, the second acquisition subunit 1032 is used to calculate and obtain a set period for screening multiple images to be spliced according to the motion parameters of the image acquisition device and the specifications of the images to be spliced;

The third acquisition subunit 1033 is used to acquire and record the acquisition time of the first image acquired through screening, and extract the image to be spliced at each set period based on the acquisition time. Get a collection of images sorted by the time they were acquired.

The splicing module 103 also includes:

A first detection subunit 1034, which is used to highlight the overlapping partial area of two adjacent images when the proportions of the overlapping partial areas of two images acquired at adjacent times in the image set reach a set proportion respectively under the condition of filtering images at a set period;

The first determining subunit 1035 is used to use the overlapping partial areas as the reserved areas of two images with adjacent acquisition times in the image set.

For the third aspect of the embodiment of the present application, a stitching device for deep-sea cold seep images is provided, comprising:

a processor; a memory for storing instructions executable by the processor;

Wherein, the processor is configured to execute the splicing method as described above.

For the fourth aspect of the embodiments of the present application, a computer-readable storage medium is provided, characterized in that the computer storage medium stores computer-executable instructions, and when the computer-executable instructions are executed, the steps of the method as described above are implemented.

For the fifth aspect of the embodiments of the present application, the embodiments of the present application further provide a computer program product, including a computer program, which implements the splicing method as described above when executed by a processor.

Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, devices, equipment (systems), storage media or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

The present application is described with reference to the flowchart and/or block diagram of the method, device (system) and computer program product according to the embodiment of the present application. It should be understood that each process and/or box in the flowchart and/or block diagram, and the combination of the process and/or box in the flowchart and/or block diagram can be realized by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for realizing the function specified in one process or multiple processes in the flowchart and/or one box or multiple boxes in the block diagram.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device that implements the functions specified in one or more processes in the flowchart and/or one or more boxes in the block diagram.

These computer program instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and/or one or more boxes in the block diagram.

In a typical configuration, a computing device includes one or more processors (CPU), input/output interfaces, network interfaces, and memory.

Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and/or non-volatile memory in the form of read-only memory (ROM) or flash memory (flashRAM). Memory is a computer-readable medium. .

Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

According to the disclosure and teaching of the above description, those skilled in the art to which the present application belongs may also change and modify the above implementation. Therefore, the present application is not limited to the specific implementation disclosed and described above, and some modifications and changes to the present application should also fall within the scope of protection of the claims of the present application. In addition, although some specific terms are used in this specification, these terms are only for the convenience of description and do not constitute any limitation to the present application.

Claims (13)

A method for stitching images of deep-sea cold seeps, characterized in that it comprises the following steps: Get multiple images to be stitched; Screening multiple images to be stitched according to a set period to obtain an image set sorted in the order of image acquisition time; In the image set, a reserved area of each image and matching points corresponding to the reserved area of each image are set, wherein the matching points are points with the same features in two adjacent images; According to the reserved area and the matching points corresponding to the reserved area of each image, the reserved areas and matching points in two temporally adjacent pictures are obtained, and the images in the image set are sequentially spliced to align them. The stitching method according to claim 1 is characterized in that before screening the plurality of images to be stitched according to a set period to obtain a set of images sorted according to acquisition time, it also includes: A coordinate system is prepared according to the specifications of one of the images to be stitched, and the specifications of the remaining images are adjusted based on the coordinate system, thereby obtaining multiple images to be stitched of the same scale. The stitching method according to claim 1 or 2 is characterized in that the plurality of images to be stitched are screened according to a set period to obtain a set of images sorted according to acquisition time, specifically comprising: obtaining motion parameters of an image acquisition device; A set period for screening a plurality of images to be spliced is calculated based on motion parameters of an image acquisition device and specifications of images to be spliced; The acquisition time of the first image obtained through screening is obtained and recorded. Based on the acquisition time, the image to be stitched is extracted at every set period to obtain a set of images sorted in the order of image acquisition time. The stitching method according to claim 3, characterized in that the motion parameter of the image acquisition device includes the rotation speed of the image acquisition device; Accordingly, the step of calculating and obtaining a set period for screening a plurality of images to be spliced according to the motion parameters of the image acquisition device and the specifications of the images to be spliced includes: Calculate and obtain the screening time of each image to be spliced in the image set according to the rotation speed of the image acquisition device and the specifications of the images to be spliced; According to the screening time of each image to be spliced in the image set, a set period for screening the multiple images to be spliced is calculated. The stitching method according to any one of claims 1 to 4, characterized in that the step of setting a reserved area for each image in the image set specifically comprises: Under the condition of filtering images at a set period, when it is detected that the overlapping partial areas of two images acquired at adjacent times in the image set account for a set proportion in the two images, the overlapping partial areas of the two adjacent images are highlighted; The overlapping partial areas are respectively used as the reserved areas of two images with adjacent acquisition times in the image set. The stitching method according to claim 5, characterized in that the step of setting matching points corresponding to the reserved areas of each image in the image set specifically comprises: The scale-invariant feature transform (SIFT) method is used to extract key points in each image in the image set; Key points in each image in the image set are matched, and matching points are determined from the key points of the plurality of images to be spliced. The stitching method according to any one of claims 1 to 6, characterized in that before screening the plurality of images to be stitched according to a set period to obtain a set of images sorted according to acquisition time, it also includes: Obtain user needs; A coordinate system is set according to the user's requirements, and the specifications of the images to be stitched are adjusted based on the coordinate system, thereby obtaining a plurality of images to be stitched of the same scale. A device for stitching images of deep-sea cold seep areas, characterized by comprising: A first acquisition module, the first acquisition module is used to acquire a plurality of images to be stitched; A second acquisition module, the second acquisition module is used to screen a plurality of images to be stitched according to a set period to obtain an image set sorted in the order of image acquisition time; A stitching module is used to set a reserved area for each image and matching points corresponding to the reserved area of each image in an image set, wherein a matching point indicates a point with the same features in two adjacent images, and based on the reserved area and the matching points corresponding to the reserved area of each image, the reserved area and matching points in two temporally adjacent images are obtained to align and stitch each image in the image set in sequence. The splicing device according to claim 8, characterized in that it also includes: The first processing module is used to formulate a coordinate system according to the specifications of one of the images to be stitched, and adjust the specifications of the remaining images based on the coordinate system, so as to obtain multiple images to be stitched of the same scale. The splicing device according to claim 8 is characterized in that: The splicing module comprises: a first acquisition subunit, the first acquisition subunit being used to acquire motion parameters of an image acquisition device; A second acquisition subunit, the second acquisition subunit is used to calculate and obtain a set period for screening multiple images to be spliced according to the motion parameters of the image acquisition device and the specifications of the images to be spliced; A third acquisition subunit, the third acquisition subunit is used to acquire and record the acquisition time of the first image acquired through screening, and based on the acquisition time, extract the image to be spliced at every set period to acquire an image set sorted in the order of image acquisition time; The splicing module also includes: A first detection subunit, the first detection subunit being used for highlighting the overlapping partial areas of two adjacent images when the proportions of the overlapping partial areas of two images acquired at adjacent times in the image set reach a set proportion respectively under the condition of screening images at a set period; The first determining subunit is used to use the overlapping partial areas as the reserved areas of two images in the image set that are acquired adjacently in time. A device for stitching images of deep-sea cold seeps, characterized by comprising: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to execute the splicing method described in any one of claims 1 to 7. A computer-readable storage medium, characterized in that the computer storage medium stores computer-executable instructions, and when the computer-executable instructions are executed, the steps of the splicing method described in any one of claims 1 to 7 are implemented. A computer program product, characterized in that it comprises a computer program, which, when executed by a processor, implements the splicing method as described in any one of claims 1 to 7.