Image acquisition guidance method and device

Abstract

The present application provides an image acquisition guidance method and device, wherein the image acquisition guidance method includes: obtaining a case image stream of case materials collected based on an image acquisition guidance template displayed on a member terminal of a project member participating in the project; fusing the case images into key image frames according to the case images contained in the case image stream and the acquisition perspectives corresponding to the case images; detecting the key image frames in at least one image detection dimension; if the detection fails, displaying a collection guidance prompt corresponding to the image detection dimension that failed the detection based on the image acquisition guidance template. The image acquisition guidance method provided by the present application guides project members to conduct more targeted case image acquisition, making the case images collected by project members more accurate, reducing the number of cases that require re-collection due to low quality of collected case images, and improving the interactive experience of project members during the case image acquisition process.

Description

[0001] This application is a divisional application of application number "201910442039.1", application date May 24, 2019, and invention name "Image acquisition guidance method and device". Technical Field

[0002] The present application relates to the field of image processing technology, and in particular to an image acquisition guidance method. The present application also relates to an image acquisition guidance device, a computing device, and a computer-readable storage medium. Background Art

[0003] With the rapid development of Internet technology, insurance sales, after-sales, claims and other routine services can be operated online more conveniently. By combining Internet scenarios with various insurance scenarios, customized insurance services are provided for the scenarios. For example, in insurance projects, when applying for claims, the insured can upload the claims materials online, and the claims will be processed online based on the claims materials uploaded by the insured.

[0004] At present, when the insured person uploads claim materials such as vouchers, the corresponding guidance process will be set up according to the insurance type to guide the insured person to collect and upload the corresponding materials, and guide the user to take images of claim materials such as vouchers and upload them at the corresponding stage; however, when the insured person uploads the claim materials and uses the native camera to take pictures, the pictures taken often have problems such as the wrong type of pictures, unclear pictures, and incomplete pictures, which have a great impact on the subsequent claims review, the material return and retransmission rate is relatively high, and the user experience is poor. Summary of the invention

[0005] In view of this, the embodiment of the present application provides an image acquisition guidance method to solve the technical defects existing in the prior art. The embodiment of the present application also provides an image acquisition guidance device, a computing device, and a computer-readable storage medium.

[0006] The present application provides an image acquisition guidance method, comprising:

[0007] Acquire a case image stream of case materials collected based on an image collection guide template displayed on a member terminal of a project member participating in the project;

[0008] According to the case images contained in the case image stream and the acquisition angles corresponding to the case images, the case images are merged into key image frames;

[0009] Detecting the key image frame in at least one image detection dimension;

[0010] If the detection fails, a capture guidance prompt corresponding to the image detection dimension that failed the detection is displayed based on the image capture guidance template.

[0011] Optionally, before the step of obtaining the case image stream of case materials collected based on the image collection guidance template displayed by the member terminals of the project members participating in the project is performed, the step includes:

[0012] Using the same-layer rendering technology to render the image acquisition guide template on the image acquisition page of the member terminal;

[0013] The rendering result of the image acquisition page is displayed on the member terminal.

[0014] Optionally, the image acquisition guidance template carries acquisition guidance prompts for acquiring case images at at least two acquisition viewing angles;

[0015] Correspondingly, the case image stream is composed of case images collected from the at least two collection perspectives for the case materials.

[0016] Optionally, the fusing the case images into key image frames according to the case images contained in the case image stream and the acquisition angles corresponding to the case images includes:

[0017] According to the case images of at least two acquisition perspectives contained in the case image stream, determining overlapping feature blocks having a feature overlapping relationship and non-overlapping feature blocks having no feature overlapping relationship in the case images of each acquisition perspective;

[0018] Using an image clarity evaluation algorithm to evaluate the image clarity of the overlapping feature blocks;

[0019] Selecting an overlapping feature block with the highest image clarity from a plurality of overlapping feature blocks with feature overlapping relations as the feature block to be fused;

[0020] The case image is fused by splicing the non-overlapping feature blocks with the feature blocks to be fused, and the splicing result is used as the key image frame.

[0021] Optionally, the determining, based on the case images of at least two acquisition perspectives contained in the case image stream, overlapping feature blocks having a feature overlapping relationship and non-overlapping feature blocks having no feature overlapping relationship in the case images of each acquisition perspective includes:

[0022] Using an image distance measurement algorithm to detect the image acquisition distance of the case images of the at least two acquisition viewing angles;

[0023] Determining whether the image acquisition distances are consistent;

[0024] If so, the overlapping feature blocks and non-overlapping feature blocks in the case images of each acquisition perspective are calculated with reference to the perspective reference points of the case images of the at least two acquisition perspectives;

[0025] If not, scaling the case image at the acquisition perspective with the visual reference point of the case image at the acquisition perspective as the center to obtain at least two case images at the acquisition perspectives with the same image acquisition distance;

[0026] The overlapping feature blocks and non-overlapping feature blocks in the case images of each captured perspective are calculated with reference to the perspective reference point.

[0027] Optionally, the detecting the key image frame in at least one image detection dimension includes:

[0028] Determining the image clarity of the key image frame based on an image clarity evaluation algorithm;

[0029] Determining whether the image clarity of the key image frame is greater than a preset clarity threshold;

[0030] If so, determining that the detection result of the key image frame is detection passed;

[0031] If not, it is determined that the detection result of the key image frame is that the image clarity detection fails, and the acquisition guidance prompt step corresponding to the image detection dimension that fails the detection based on the image acquisition guidance template is performed.

[0032] Optionally, displaying the acquisition guidance prompt corresponding to the image detection dimension that failed the detection based on the image acquisition guidance template includes:

[0033] Rendering a first acquisition guidance prompt that fails the image clarity detection on the image acquisition guidance template based on a same-layer rendering technology;

[0034] The image acquisition guide template after rendering the first acquisition guide prompt is displayed on the image acquisition page of the member terminal.

[0035] Optionally, after the step of displaying the acquisition guidance prompt corresponding to the image detection dimension that failed the detection based on the image acquisition guidance template is executed, the method includes:

[0036] Acquire a secondary collection case image of the case material collected based on the image collection guidance template after rendering the first collection guidance prompt displayed on the image collection page;

[0037] The key image frame and the secondary collected case image are subjected to image fusion, and the case image after the image fusion is used as the first target case image of the case material.

[0038] Optionally, the detecting the key image frame in at least one image detection dimension includes:

[0039] Determining the image clarity of the key image frame based on an image clarity evaluation algorithm;

[0040] Determining whether the image clarity of the key image frame is greater than a preset clarity threshold;

[0041] If yes, detecting the image acquisition distance of the key image frame based on an image ranging algorithm;

[0042] Determine whether the image acquisition distance is less than a preset acquisition distance threshold;

[0043] If the distance is less than the preset acquisition distance threshold, determining that the detection result of the key image frame is detection passed;

[0044] If it is greater than or equal to the preset acquisition distance threshold, it is determined that the detection result of the key image frame is that the image acquisition distance detection fails, and the acquisition guidance prompt step corresponding to the image detection dimension that failed the detection based on the image acquisition guidance template is executed.

[0045] Optionally, displaying the acquisition guidance prompt corresponding to the image detection dimension that failed the detection based on the image acquisition guidance template includes:

[0046] Rendering a second acquisition guidance prompt for failing the image acquisition distance detection on the image acquisition guidance template based on the same-layer rendering technology;

[0047] The image acquisition guide template after rendering the second acquisition guide prompt is displayed on the image acquisition page of the member terminal.

[0048] Optionally, after the step of displaying the acquisition guidance prompt corresponding to the image detection dimension that failed the detection based on the image acquisition guidance template is executed, the method includes:

[0049] Acquire a secondary collection case image of the case material collected based on the image collection guidance template after rendering the second collection guidance prompt displayed on the image collection page;

[0050] The key image frame and the second-collected case image are subjected to image fusion, and the case image after the image fusion is used as the second target case image of the case material.

[0051] The present application also provides an image acquisition guiding device, comprising:

[0052] A case image stream acquisition module, configured to acquire a case image stream of case materials acquired based on an image acquisition guidance template displayed by a member terminal of a project member participating in the project;

[0053] a key image frame fusion module, configured to fuse the case images into key image frames according to the case images contained in the case image stream and the acquisition angles corresponding to the case images;

[0054] A key image frame detection module, configured to detect the key image frame in at least one image detection dimension;

[0055] The acquisition guidance prompt display module is configured to display the acquisition guidance prompt corresponding to the image detection dimension that failed the detection based on the image acquisition guidance template when the detection fails.

[0056] The present application also provides a computing device, including:

[0057] Memory and processor;

[0058] The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions:

[0059] Acquire a case image stream of case materials collected based on an image collection guide template displayed on a member terminal of a project member participating in the project;

[0060] According to the case images contained in the case image stream and the acquisition angles corresponding to the case images, the case images are merged into key image frames;

[0061] Detecting the key image frame in at least one image detection dimension;

[0062] If the detection fails, a capture guidance prompt corresponding to the image detection dimension that failed the detection is displayed based on the image capture guidance template.

[0063] The present application also provides a computer-readable storage medium storing computer instructions, which implement the steps of the image acquisition guidance method when executed by a processor.

[0064] Compared with the prior art, this application has the following advantages:

[0065] The present application provides an image acquisition guidance method, including: obtaining a case image stream of case materials collected based on an image acquisition guidance template displayed on a member terminal of a project member participating in the project; fusing the case images into key image frames according to the case images contained in the case image stream and the acquisition perspectives corresponding to the case images; detecting the key image frames in at least one image detection dimension; and if the detection fails, displaying a capture guidance prompt corresponding to the image detection dimension that failed the detection based on the image acquisition guidance template.

[0066] The image acquisition guidance method provided in the present application, during the process of the project members collecting case images, collects case images of case materials in the project by collecting case image streams under the guidance of the image acquisition guidance template, analyzes and fuses high-definition case images based on the collected case image streams, and detects the key image frames obtained by image fusion. Based on the image acquisition guidance template, prompts are given to the project members for the image detection dimensions that fail to pass the detection of the key image frames, thereby guiding the project members to perform more targeted case image acquisition, making the case images collected by the project members more accurate, reducing the need to re-collect due to low quality of the collected case images, and improving the interactive experience of the project members during the case image acquisition process. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 This is a processing flow chart of an image acquisition guidance method provided in an embodiment of the present application;

[0068] Figure 2 is a schematic diagram of a first image acquisition guidance template provided in an embodiment of the present application;

[0069] Figure 3 is a schematic diagram of a second image acquisition guidance template provided in an embodiment of the present application;

[0070] Figure 4 is a schematic diagram of overlapping feature blocks and non-overlapping feature blocks provided in an embodiment of the present application;

[0071] Figure 5 It is a schematic diagram of a collection guidance prompt in the first image collection guidance template provided in an embodiment of the present application;

[0072] Figure 6 is a schematic diagram of a collection guidance prompt in a second image collection guidance template provided in an embodiment of the present application;

[0073] Figure 7 is a schematic diagram of an image acquisition and guidance device provided in an embodiment of the present application;

[0074] Figure 8 It is a structural block diagram of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0075] Many specific details are described in the following description to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of the present application, so the present application is not limited by the specific implementation disclosed below.

[0076] The terms used in one or more embodiments of this specification are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of this specification. The singular forms of "a", "said" and "the" used in one or more embodiments of this specification 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 in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0077] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0078] The present application provides an image acquisition guidance method, and the present application also provides an image acquisition guidance device, a computing device, and a computer-readable storage medium. The following is a detailed description of each of the embodiments provided by the present application, and each step of the method is described.

[0079] An embodiment of an image acquisition guidance method provided by the present application is as follows:

[0080] See attached Figure 1 , which shows a processing flow chart of an image acquisition guidance method provided by this embodiment, refer to the attached Figure 2 , which shows a schematic diagram of the first image acquisition guidance template provided in an embodiment of the present application, refer to the attached Figure 3 , which shows a schematic diagram of a second image acquisition guidance template provided in an embodiment of the present application, refer to the attached Figure 4 , which shows a schematic diagram of an overlapping feature block and a non-overlapping feature block provided in an embodiment of the present application, refer to the attached Figure 5 , which shows a schematic diagram of the acquisition guidance prompt in the first image acquisition guidance template provided in the embodiment of the present application, refer to the attached Figure 6 , which shows a schematic diagram of acquisition guidance prompts in the second image acquisition guidance template provided in an embodiment of the present application.

[0081] Step S102 , obtaining a case image stream of case materials collected based on an image collection guidance template displayed on a member terminal of a project member participating in the project.

[0082] In actual applications, when project members are participating in the project, for example, when project members are participating in the insurance project, if a project member (insured person) participating in the insurance project encounters an accident and needs to apply for a claim, a corresponding claim case will be generated, and the project member needs to upload the corresponding case materials of the claim case. After the case materials are uploaded, the claim case will be reviewed based on the uploaded case materials, that is, whether to pay the claim case; if the review is passed, the project member who submitted the claim application will be paid; if the review is not passed, the project member who submitted the claim application will be refused to be paid.

[0083] Among them, during the process of uploading claim materials, if the project members are not guided in the operation of collecting case images of claim materials, the case images of case materials collected by the project members may not match the collected image types, and the collected case images may also be unclear or not meet the requirements; specifically, in the process of project members collecting case images, project members are required to manually operate the cameras configured on their respective member terminals to collect case images, and when project members manually operate the member terminals to collect case images, it is more prone to errors, jitters, unclear shots, etc., which puts higher requirements on guiding project members to collect case images.

[0084] The image acquisition guidance method provided by the present application collects case images of case materials in the project by collecting video streams of case materials (case image streams composed of multiple case images) during the stage of project members collecting case images, and then extracts case images with higher clarity based on the collected video streams, performs image fusion processing on the extracted case images, and obtains key image frames. In addition, based on the key image frames, the project members can be further guided to collect case images with higher clarity and accuracy, thereby making the case images collected by the project members more accurate, making the processing of claims cases more convenient and more effective, reducing or even avoiding the requirement to re-collect due to poor quality of the collected case images, and improving the interactive experience of project members during the case image collection process.

[0085] The case materials described in the embodiment of the present application refer to case materials related to the case to be reviewed submitted by the project members. For example, after a project member submits a claim application due to illness during the participation in the health insurance project, the project member needs to submit case materials for the claim to the insurance company. The case materials specifically include the project member's identity document, medical records of the project member's illness, hospitalization certificates, and payment receipts during the treatment of the illness after becoming ill.

[0086] It should be noted that the embodiment of the present application stores image acquisition guidance templates that guide project members to perform case image acquisition by setting up an image acquisition guidance template library. During specific implementation, project members select image acquisition guidance templates from the image acquisition guidance template library. After the project members select the image acquisition guidance templates, optionally, the same-layer rendering technology is used to render the selected image acquisition guidance template on the image acquisition page of the project member's member terminal, and the rendering results of the image acquisition page are displayed on the member terminal. Based on this, project members perform case image acquisition in the form of video streams under the guidance of the image acquisition guidance templates displayed on the image acquisition page of the member terminal and follow the prompts of the image acquisition guidance templates to obtain case image streams of the case materials after acquisition.

[0087] Optionally, the image acquisition guidance template described in the embodiment of the present application carries acquisition guidance prompts for acquiring case images from at least two acquisition perspectives; accordingly, the case image stream is composed of case images acquired from the at least two acquisition perspectives for the case materials.

[0088] For example, after a project member opens the camera configured on their smartphone, the rendered image acquisition guide template will be displayed on the camera page (image acquisition page), as shown in the attached figure. Figure 2 The image acquisition guidance template shown in the figure carries the collection guidance prompts for collecting case images at three collection angles. Among them, the collection guidance prompts for collecting images of the voucher at the middle angle of the camera are first displayed in the image acquisition guidance template, as shown in the attached figure. Figure 2 As shown in (a), under the guidance of this collection guidance prompt, the project member collects the first voucher image of the voucher at the middle perspective;

[0089] Secondly, after the first credential image of the credential is captured at the middle viewing angle, a capture guidance prompt for capturing an image of the credential at the upper viewing angle of the camera is displayed in the image capture guidance template, as shown in the attached figure. Figure 2 As shown in (b), under the guidance of this collection guide prompt, the project member collects the second voucher image of the voucher at the upper perspective;

[0090] Finally, after the second credential image of the credential is captured at the upper viewing angle, a capture guidance prompt for capturing an image of the credential at the lower viewing angle of the camera is displayed in the image capture guidance template, as shown in the attached figure. Figure 2 As shown in (c), under the guidance of this collection guide prompt, the project member collects the third voucher image of the voucher at the lower perspective;

[0091] The first voucher image, the second voucher image and the third voucher image collected above constitute a voucher image stream (case image stream) of the voucher.

[0092] In addition to the above Figure 2 In addition to the image acquisition guidance template shown in the figure carrying the acquisition guidance prompts for case image acquisition at three acquisition viewing angles, the image acquisition guidance template can also carry the acquisition guidance prompts for case image acquisition at two, four, five, nine or even more acquisition viewing angles. There is no essential difference in the number of acquisition guidance prompts carried by the image acquisition guidance template. For example, Figure 3 The image acquisition guidance template shown carries the acquisition guidance prompts for collecting case images at 4 acquisition angles. For the specific implementation method of the image acquisition guidance template carrying the acquisition guidance prompts for collecting case images at 2, 4, 5, 9 or even more acquisition angles in the case image acquisition process, see the above-mentioned Appendix. Figure 2 The image acquisition guidance template shown carries the acquisition guidance prompts for case image acquisition at three acquisition perspectives, which can be specifically implemented in the voucher image acquisition process, and this embodiment will not be described in detail here.

[0093] Step S104: According to the case images contained in the case image stream and the acquisition angles corresponding to the case images, the case images are merged into key image frames.

[0094] As described above, the image acquisition guidance template carries acquisition guidance prompts for acquiring case images at least two acquisition perspectives. Accordingly, the case image stream acquired under the guidance of the image acquisition guidance template includes case images acquired for the case materials at the at least two acquisition perspectives. After the case image stream is acquired under the guidance of the image acquisition guidance template, the case images are fused into key image frames according to the case images contained in the case image stream and the acquisition perspectives corresponding to the case images, so as to obtain key frame images with higher clarity and accuracy.

[0095] In an optional implementation manner provided in the embodiment of the present application, the case images are fused into key image frames according to the case images contained in the case image stream and the acquisition angles corresponding to the case images, which is specifically implemented in the following manner:

[0096] 1) Based on the case images of at least two acquisition perspectives contained in the case image stream, overlapping feature blocks having feature overlapping relationships and non-overlapping feature blocks having no feature overlapping relationships in the case images of each acquisition perspective are determined.

[0097] In actual applications, when project members manually collect case images under the guidance of the collection guidance prompts in the image collection guidance template, in the process of switching from the previous collection perspective to the next collection perspective, the distance between the member terminal of the project member collecting the case image and the collected case material is likely to change. Once the distance between the member terminal and the case material changes, the size of the image features contained in the collected case image may also change, which will bring difficulties to the subsequent image fusion. In order to avoid this situation and to improve the accuracy of the subsequent image fusion process, optionally, the overlapping feature blocks and the non-overlapping feature blocks are determined in the following manner:

[0098] a) using an image distance measurement algorithm to detect the image acquisition distance of the case images of the at least two acquisition viewing angles;

[0099] b) determining whether the image acquisition distances are consistent;

[0100] c) if yes, calculating the overlapping feature blocks and non-overlapping feature blocks in the case images of each acquisition perspective with reference to the perspective reference points of the case images of the at least two acquisition perspectives;

[0101] d) If not, scaling the case image at the acquisition perspective with the visual reference point of the case image at the acquisition perspective as the center to obtain at least two case images at the acquisition perspectives with consistent image acquisition distances; and calculating overlapping feature blocks and non-overlapping feature blocks in the case images at each acquisition perspective with the view reference point as a reference.

[0102] For example, when the focal length of the camera in the smartphone carried by the project member does not change, after the project member captures the first voucher image at the middle viewing angle through the camera configured on the smartphone, once the project member's movement changes, such as the image capture distance (object distance) from the camera to the captured case materials becomes longer, the proportion of image features contained in the second voucher image captured by the camera at the upper viewing angle becomes smaller. By enlarging the second voucher image, the proportion of image features contained in the enlarged second voucher image can be made consistent with the proportion of image features contained in the first voucher image.

[0103] 2) Using an image clarity evaluation algorithm to evaluate the image clarity of the overlapping feature blocks.

[0104] For example, common image clarity evaluation algorithms include: Brenner gradient function, Tenengrad gradient function, variance function, and energy gradient function.

[0105] 3) Select an overlapping feature block with the highest image clarity from multiple overlapping feature blocks with feature overlapping relationship as the feature block to be fused.

[0106] 4) The case image is fused by splicing the non-overlapping feature blocks with the feature blocks to be fused, and the splicing result is used as the key image frame.

[0107] For example, as attached Figure 2 The image acquisition guidance template shown in the figure carries the acquisition guidance prompts for collecting case images at three acquisition perspectives. Project members collect voucher image streams according to the three acquisition guidance prompts. The collected voucher image streams include the first voucher image, the second voucher image and the third voucher image. The image acquisition ranges corresponding to the three voucher images are shown in the attached figure. Figure 4 As shown, the image acquisition range 401 is the image acquisition range corresponding to the first credential image, that is, the image acquisition range covered by the camera when the camera configured by the project member's smartphone acquires an image of the credential at a middle viewing angle; the image acquisition range 402 is the image acquisition range corresponding to the second credential image, that is, the image acquisition range covered by the camera when the camera of the project member's smartphone acquires an image of the credential at an upper viewing angle; the image acquisition range 403 is the image acquisition range corresponding to the third credential image, that is, the image acquisition range covered by the camera when the camera of the project member's smartphone acquires an image of the credential at a lower viewing angle;

[0108] As attached Figure 4 As shown, the non-overlapping area in the image acquisition range 401 corresponding to the first voucher image is 407 (the area in the image acquisition range 401 that does not overlap with the image acquisition range 402 and the image acquisition range 403), and the image feature area (image feature block) corresponding to the non-overlapping area 407 in the first voucher image is a non-overlapping feature block in the first voucher image that does not have a feature overlapping relationship;

[0109] The non-overlapping area in the image acquisition range 402 corresponding to the second voucher image is 408 (an area in the image acquisition range 402 that does not overlap with the image acquisition range 401 and the image acquisition range 403), and the non-overlapping area 408 is in the image feature area (image feature block) corresponding to the second voucher image, that is, a non-overlapping feature block in the second voucher image that does not have a feature overlapping relationship;

[0110] The non-overlapping area in the image acquisition range 403 corresponding to the third voucher image is 409 (an area in the image acquisition range 403 that does not overlap with the image acquisition range 401 and the image acquisition range 402), and the non-overlapping area 409 is in the image feature area (image feature block) corresponding to the third voucher image, that is, a non-overlapping feature block in the third voucher image that does not have a feature overlapping relationship;

[0111] An overlapping area between the image acquisition range 401 corresponding to the first voucher image and the image acquisition range 402 corresponding to the second voucher image is an area 404, and the overlapping area 404 is composed of two sub-areas, namely, a sub-area 404-1 and a sub-area 404-2.

[0112] Wherein, sub-region 404-1 is the common overlapping region of image acquisition range 401, image acquisition range 402 and image acquisition range 403; accordingly, the image feature region (image feature block) corresponding to sub-region 404-1 in the first voucher image, the second voucher image and the third voucher image is an overlapping feature block having a feature overlapping relationship in the first voucher image, the second voucher image and the third voucher image; the image clarity of the overlapping feature block in the first voucher image, the image clarity of the overlapping feature block in the second voucher image and the image clarity of the overlapping feature block in the third voucher image are evaluated by using an image clarity evaluation algorithm, the image clarity of the overlapping feature block in the third voucher image is compared, and the overlapping feature block with the highest clarity is used as the feature block to be fused required for subsequent image fusion; if the image clarity of the overlapping feature block contained in the first voucher image is the highest, the overlapping feature block contained in the first voucher image is used as the feature block to be fused for subsequent image fusion;

[0113] Sub-region 404-2 is an overlapping region between image acquisition range 401 and image acquisition range 402; accordingly, the image feature region (image feature block) corresponding to sub-region 404-2 in the first voucher image and the second voucher image is an overlapping feature block having a feature overlapping relationship between the first voucher image and the second voucher image; the image clarity of the overlapping feature block in the first voucher image and the image clarity of the overlapping feature block in the second voucher image are evaluated by using an image clarity evaluation algorithm, and the image clarity of the overlapping feature block in the second voucher image is compared, and the overlapping feature block with the highest clarity is used as the feature block to be fused required for subsequent image fusion; if the image clarity of the overlapping feature block contained in the second voucher image is higher, the overlapping feature block contained in the second voucher image is used as the feature block to be fused required for subsequent image fusion;

[0114] Similarly, the overlapping area of ​​the image acquisition range 401 corresponding to the first voucher image and the image acquisition range 403 corresponding to the third voucher image is area 405, the overlapping feature blocks corresponding to the sub-area 405-2 contained in the overlapping area 405 in the first voucher image and the third voucher image are determined, and the image clarity evaluation algorithm is used to evaluate the image clarity of the overlapping feature blocks contained in the first voucher image and the third voucher image, and finally the overlapping feature blocks with higher image clarity are determined to be the overlapping feature blocks contained in the first voucher image, and the overlapping feature blocks contained in the first voucher image are used as the feature blocks to be fused required for subsequent image fusion;

[0115] The overlapping area of ​​the image acquisition range 402 corresponding to the second voucher image and the image acquisition range 403 corresponding to the third voucher image is area 406, the overlapping feature blocks corresponding to the sub-area 406-2 contained in the overlapping area 406 in the second voucher image and the third voucher image are determined, and the image clarity evaluation algorithm is used to evaluate the image clarity of the overlapping feature blocks contained in the second voucher image and the third voucher image, and finally the overlapping feature blocks with higher image clarity are determined to be the overlapping feature blocks contained in the third voucher image, and the overlapping feature blocks contained in the third voucher image are used as the feature blocks to be fused required for subsequent image fusion;

[0116] In summary, there are 3 non-overlapping feature blocks in total: the non-overlapping feature block corresponding to the non-overlapping area 407 in the first voucher image, the non-overlapping feature block corresponding to the non-overlapping area 408 in the second voucher image, and the non-overlapping feature block corresponding to the non-overlapping area 409 in the third voucher image;

[0117] There are 4 feature blocks to be fused as determined above: the feature block to be fused corresponding to sub-region 404-1 in the first voucher image, the feature block to be fused corresponding to sub-region 404-2 in the second voucher image, the feature block to be fused corresponding to sub-region 405-2 in the second voucher image, and the feature block to be fused corresponding to sub-region 406-2 in the third voucher image;

[0118] The three non-overlapping feature blocks and the four feature blocks to be fused are spliced ​​together, and the spliced ​​image is used as a key image frame.

[0119] Step S106: Detect the key image frame in at least one image detection dimension.

[0120] After the case images are fused into the key image frames according to the case images contained in the case image stream and the acquisition angles corresponding to the case images, a more in-depth detection is further performed on the key image frames obtained by the image fusion, such as detecting the key image frames from the dimension of image acquisition distance, or detecting the key image frames from the dimension of image clarity. In addition, the key image frames may also be detected from dimensions other than image acquisition distance and image clarity, which is not limited in the present embodiment.

[0121] Based on the above-mentioned fusion of the case images into key image frames according to the case images contained in the case image stream and the acquisition angles corresponding to the case images, in a first optional implementation manner provided in the embodiment of the present application, the key image frames are detected in the following manner:

[0122] 1) determining the image clarity of the key image frame based on an image clarity evaluation algorithm;

[0123] 2) determining whether the image clarity of the key image frame is greater than a preset clarity threshold;

[0124] If so, it indicates that the key image frame passes the detection of the image clarity dimension, and it is determined that the detection result of the image clarity detection performed on the key image frame is passed;

[0125] If not, it indicates that the key image frame fails the detection of the image clarity dimension, and the detection result of the image clarity detection on the key image frame is determined to be that the image clarity detection fails, and the following step S108 is executed to display the acquisition guidance prompt that the image clarity dimension detection fails based on the image acquisition guidance template.

[0126] For example, the key image frame obtained by splicing the above-mentioned 3 non-overlapping feature blocks and 4 feature blocks to be fused is evaluated by using an image clarity evaluation algorithm to obtain the image clarity of the key image frame, and further determine whether the image clarity of the key image frame is greater than a preset clarity threshold; if greater than, it indicates that the key image frame obtained after the above-mentioned image fusion has passed the detection of the image clarity dimension, and the detection result of the image clarity detection of the key image frame is determined to be passed; if not greater than, it indicates that the key image frame obtained by the above-mentioned splicing has not passed the detection of the image clarity dimension, and the detection result of the image clarity detection of the key image frame is determined to be failed, and the key image frame is further improved by subsequent processing of the collected case images.

[0127] Based on the above-mentioned fusion of the case images into key image frames according to the case images contained in the case image stream and the acquisition angles corresponding to the case images, in a second optional implementation manner provided in the embodiment of the present application, the key image frames are detected in the following manner:

[0128] 1) determining the image clarity of the key image frame based on an image clarity evaluation algorithm;

[0129] 2) determining whether the image clarity of the key image frame is greater than a preset clarity threshold;

[0130] If yes, it indicates that the key image frame passes the detection of the dimension of image clarity, then the following step 3) is performed to further detect the key image frame in the dimension of image acquisition distance;

[0131] If not, the table indicates that the key image frame fails to pass the detection of the image clarity dimension, determines that the detection result of the image clarity detection on the key image frame is that the image clarity detection fails, and executes the following step S108 to display a capture guidance prompt that the image clarity dimension detection fails based on the image capture guidance template;

[0132] 3) detecting the image acquisition distance of the key image frame based on an image ranging algorithm;

[0133] 4) determining whether the image acquisition distance is less than a preset acquisition distance threshold;

[0134] If yes, it indicates that the key image frame passes the detection of the dimension of image acquisition distance, then the detection result of the image clarity detection and the image acquisition distance detection performed on the key image frame is determined to be passed;

[0135] If not, it is determined that the image acquisition distance detection result of the key image frame is that the image acquisition distance detection has failed, and the following step S108 is executed to display an acquisition guidance prompt that the image acquisition distance dimension detection has failed based on the image acquisition guidance template.

[0136] Step S108: If the detection fails, displaying a capture guidance prompt corresponding to the image detection dimension that failed the detection based on the image capture guidance template.

[0137] The premise for the implementation of this step is that the detection result of the key image frame in the image detection dimension is failed, indicating that the performance of the key image frame obtained by the above-mentioned image fusion in the image detection dimension does not meet expectations. Therefore, it is necessary to further use the image acquisition guidance template to guide project members to collect case images of case materials, and optimize the key image frame based on the collected case images to improve the accuracy of case image acquisition.

[0138] Corresponding to the two optional implementations of detecting the key image frame provided in the above step S106, the embodiment of the present application provides the following two optional implementations of displaying acquisition guidance prompts corresponding to the image detection dimensions that failed the detection based on the image acquisition guidance template.

[0139] Specifically, based on the first optional implementation of detecting the key image frame provided in the above step S106, optionally, the following method is used to display the acquisition guidance prompt corresponding to the image detection dimension that failed the detection based on the image acquisition guidance template:

[0140] Rendering a first acquisition guidance prompt that fails the image clarity detection on the image acquisition guidance template based on a same-layer rendering technology;

[0141] The image acquisition guide template after rendering the first acquisition guide prompt is displayed on the image acquisition page of the member terminal.

[0142] By displaying the first acquisition guidance prompt that the image clarity test fails in the image acquisition guidance template of the image acquisition page, the project members can more intuitively know the deficiencies of the case images previously acquired, and on this basis, guide the project members to acquire case images in a targeted manner, so as to further improve the key image frame using the acquired case image, so that the improved case image has higher clarity and accuracy. Optionally, the case image is acquired and the key image frame is improved based on the first acquisition guidance prompt in the following manner:

[0143] Acquire a secondary collection case image of the case material collected based on the image collection guidance template after rendering the first collection guidance prompt displayed on the image collection page;

[0144] The key image frame and the secondary collected case image are subjected to image fusion, and the case image after the image fusion is used as the first target case image of the case material.

[0145] For example, if the key image frame obtained after the above-mentioned image fusion does not pass the detection of the image clarity dimension, then after determining that the detection result of the key image frame for the image clarity detection is that the detection fails, the same-layer rendering technology is used to render the first acquisition guidance prompt (prompt information of low image clarity) that the key image frame does not pass the clarity dimension detection on the image acquisition guidance template, and the rendered image acquisition guidance template is displayed on the image acquisition page of the project member's smartphone, as shown in the attached figure. Figure 5 As shown;

[0146] After the image acquisition guidance template for rendering the first acquisition guidance prompt is displayed on the image acquisition page of the smartphone, project members can obtain the displayed first acquisition guidance prompt through the image acquisition page, and collect credential images in a targeted manner under the guidance of the first acquisition guidance prompt, such as by adjusting the camera focal length of the smartphone or changing the shooting angle and orientation to make the image clarity of the collected credential image higher. After obtaining the credential image collected by the project members, the image fusion algorithm is used to fuse the collected credential image with the above-mentioned key image frame, so that the fused target credential image has higher clarity.

[0147] Based on the second optional implementation of detecting the key image frame provided in the above step S106, optionally, the following method is used to display the acquisition guidance prompt corresponding to the image detection dimension that failed the detection based on the image acquisition guidance template:

[0148] Rendering a second acquisition guidance prompt for failing the image acquisition distance detection on the image acquisition guidance template based on the same-layer rendering technology;

[0149] The image acquisition guide template after rendering the second acquisition guide prompt is displayed on the image acquisition page of the member terminal.

[0150] By displaying the second acquisition guidance prompt that the image acquisition distance detection fails in the image acquisition guidance template of the image acquisition page, the project members can also be more intuitively informed of the deficiencies of the previously acquired images, and on this basis, the project members can be targeted to acquire case images, so as to further improve the key image frame using the acquired case image, so that the improved case image has higher clarity and accuracy. Optionally, the case image acquisition is performed based on the second acquisition guidance prompt and the key image frame is improved in the following manner:

[0151] Acquire a secondary collection case image of the case material collected based on the image collection guidance template after rendering the second collection guidance prompt displayed on the image collection page;

[0152] The key image frame and the second-collected case image are subjected to image fusion, and the case image after the image fusion is used as the second target case image of the case material.

[0153] For example, if the key image frame obtained after the above-mentioned image fusion does not pass the image acquisition distance detection, then after determining that the detection result of the key image frame for the image acquisition distance detection is that the detection fails, the same-layer rendering technology is used to render the second acquisition guidance prompt (prompt information that the acquisition distance is farther or closer) that the key image frame does not pass the image acquisition distance detection on the image acquisition guidance template, and the rendered image acquisition guidance template is displayed on the image acquisition page of the project member's smartphone, as shown in the attached figure. Figure 6 As shown;

[0154] After the image acquisition guidance template for rendering the second acquisition guidance prompt is displayed on the image acquisition page, project members can obtain the displayed second acquisition guidance prompt through the image acquisition page, and collect credential images in a targeted manner under the guidance of the second acquisition guidance prompt. For example, the image acquisition distance of the collected credential image can be made more accurate by adjusting the image acquisition distance between the camera of the smartphone and the collected credential. After obtaining the credential image collected by the project member, the image fusion algorithm is used to fuse the collected credential image with the above-mentioned key image frame, so that the fused target credential image has a higher and more accurate image acquisition distance.

[0155] To summarize, the image acquisition guidance method provided by the present application, during the process of the project members collecting case images, collects case images of case materials in the project by collecting case image streams under the guidance of the image acquisition guidance template, performs analysis and fusion of high-definition case images based on the collected case image streams, and detects the key image frames obtained by image fusion. Based on the image acquisition guidance template, prompts are given to the project members for the image detection dimensions that fail to pass the detection of the key image frames, thereby guiding the project members to perform more targeted case image acquisition, making the case images collected by the project members more accurate, reducing the need to re-collect due to low quality of the collected case images, and improving the interactive experience of the project members during the case image acquisition process.

[0156] An embodiment of an image acquisition guiding device provided by the present application is as follows:

[0157] In the above-mentioned embodiment, an image acquisition guidance method is provided. Correspondingly, the present application also provides an image acquisition guidance device, which is described below in conjunction with the accompanying drawings.

[0158] See attached Figure 7 , which shows a schematic diagram of an embodiment of an image acquisition and guidance device provided by the present application.

[0159] Since the device embodiment is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the corresponding description of the method embodiment provided above. The device embodiment described below is only illustrative.

[0160] The present application provides an image acquisition guiding device, comprising:

[0161] The case image stream acquisition module 702 is configured to acquire a case image stream of case materials acquired based on an image acquisition guidance template displayed by a member terminal of a project member participating in the project;

[0162] The key image frame fusion module 704 is configured to fuse the case images into key image frames according to the case images contained in the case image stream and the acquisition angles corresponding to the case images;

[0163] A key image frame detection module 706 is configured to detect the key image frame in at least one image detection dimension;

[0164] The acquisition guidance prompt display module 708 is configured to display the acquisition guidance prompt corresponding to the image detection dimension that failed the detection based on the image acquisition guidance template when the detection fails.

[0165] Optionally, the image acquisition guiding device further includes:

[0166] An image acquisition guide template rendering module is configured to render the image acquisition guide template on the image acquisition page of the member terminal using a same-layer rendering technology;

[0167] The rendering result display module is configured to display the rendering result of the image acquisition page on the member terminal.

[0168] Optionally, the image acquisition guidance template carries acquisition guidance prompts for acquiring case images at at least two acquisition viewing angles;

[0169] Correspondingly, the case image stream is composed of case images collected from the at least two collection perspectives for the case materials.

[0170] Optionally, the key image frame fusion module 704 includes:

[0171] The feature block determination submodule is configured to determine, based on the case images of at least two acquisition perspectives contained in the case image stream, overlapping feature blocks having feature overlapping relationships in the case images of each acquisition perspective, and non-overlapping feature blocks having no feature overlapping relationships;

[0172] An image clarity evaluation submodule is configured to evaluate the image clarity of the overlapping feature blocks using an image clarity evaluation algorithm;

[0173] The feature block selection submodule to be fused is configured to select an overlapping feature block with the highest image clarity from a plurality of overlapping feature blocks having a feature overlapping relationship as the feature block to be fused;

[0174] The key image frame fusion submodule is configured to fuse the case image by splicing the non-overlapping feature blocks with the feature blocks to be fused, and use the splicing result as the key image frame.

[0175] Optionally, the feature block determination submodule includes:

[0176] An image acquisition distance detection subunit is configured to detect the image acquisition distances of the case images of the at least two acquisition viewing angles by using an image distance measurement algorithm;

[0177] An image acquisition distance determination subunit is configured to determine whether the image acquisition distance is consistent;

[0178] If yes, run the first feature block calculation subunit; the first feature block calculation subunit is configured to calculate the overlapping feature blocks and non-overlapping feature blocks in the case images of each acquisition perspective with reference to the perspective reference points of the case images of the at least two acquisition perspectives;

[0179] If not, run the case image scaling subunit and the second feature block calculation subunit;

[0180] The case image zooming subunit is configured to zoom the case image at the acquisition perspective with the visual reference point of the case image at the acquisition perspective as the center, to obtain at least two case images at the acquisition perspectives with the same image acquisition distance;

[0181] The second feature block calculation subunit is configured to calculate overlapping feature blocks and non-overlapping feature blocks in the case image of each captured perspective with reference to the perspective reference point.

[0182] Optionally, the key image frame detection module 706 includes:

[0183] A first image definition determination submodule is configured to determine the image definition of the key image frame based on an image definition evaluation algorithm;

[0184] A first image definition judgment submodule is configured to judge whether the image definition of the key image frame is greater than a preset definition threshold;

[0185] If so, determining that the detection result of the key image frame is detection passed;

[0186] If not, it is determined that the detection result of the key image frame is that the image clarity detection fails, and the acquisition guidance prompt display module 708 is run.

[0187] Optionally, the collection guidance prompt display module 708 includes:

[0188] A first acquisition guidance prompt rendering submodule is configured to render the first acquisition guidance prompt that fails the image clarity detection on the image acquisition guidance template based on the same-layer rendering technology;

[0189] The first acquisition guide prompt display submodule is configured to display the image acquisition guide template after rendering the first acquisition guide prompt on the image acquisition page of the member terminal.

[0190] Optionally, the image acquisition guiding device comprises:

[0191] A secondary acquisition module is configured to obtain a secondary acquisition case image of the case material acquired based on the image acquisition guidance template after rendering the first acquisition guidance prompt displayed on the image acquisition page;

[0192] The image fusion module is configured to perform image fusion on the key image frame and the secondary collected case image, and use the case image after the image fusion as the first target case image of the case material.

[0193] Optionally, the key image frame detection module 706 includes:

[0194] A second image definition determination submodule is configured to determine the image definition of the key image frame based on an image definition evaluation algorithm;

[0195] A second image definition judgment submodule is configured to judge whether the image definition of the key image frame is greater than a preset definition threshold;

[0196] If yes, run the image acquisition distance submodule and the image acquisition distance judgment submodule;

[0197] The image acquisition distance submodule is configured to detect the image acquisition distance of the key image frame based on an image distance measurement algorithm;

[0198] The image acquisition distance judgment submodule is configured to determine whether the image acquisition distance is less than a preset acquisition distance threshold; if so, determine that the detection result of the key image frame is a passed detection; if not, determine that the detection result of the key image frame is a failed image acquisition distance detection, and run the acquisition guidance prompt display module 708.

[0199] Optionally, the collection guidance prompt display module 708 includes:

[0200] A second acquisition guidance prompt rendering submodule is configured to render the second acquisition guidance prompt that fails the image acquisition distance detection on the image acquisition guidance template based on the same-layer rendering technology;

[0201] The second acquisition guide prompt display submodule is configured to display the image acquisition guide template after rendering the second acquisition guide prompt on the image acquisition page of the member terminal.

[0202] Optionally, the image acquisition guiding device comprises:

[0203] An image secondary acquisition module is configured to obtain a secondary acquisition case image of the case material acquired based on the image acquisition guidance template after rendering the second acquisition guidance prompt displayed on the image acquisition page;

[0204] The secondary acquisition image fusion module is configured to perform image fusion on the key image frame and the secondary acquisition case image, and use the case image after the image fusion as the second target case image of the case material.

[0205] An embodiment of a computing device provided by the present application is as follows:

[0206] Figure 88 is a block diagram showing a computing device 800 according to an embodiment of the present specification. The components of the computing device 800 include but are not limited to a memory 810 and a processor 820. The processor 820 is connected to the memory 810 via a bus 830, and a database 850 is used to store data.

[0207] The computing device 800 also includes an access device 840 that enables the computing device 800 to communicate via one or more networks 860. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 840 may include one or more of any type of network interface (e.g., a network interface card (NIC)) that is wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a World Wide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, a near field communication (NFC) interface, and the like.

[0208] In one embodiment of the present specification, the above components of the computing device 800 and Figure 8 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Figure 8 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0209] The computing device 800 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or PC. The computing device 800 may also be a mobile or stationary server.

[0210] The present application provides a computing device, including a memory 810, a processor 820, and computer instructions stored in the memory and executable on the processor, wherein the processor 820 is configured to execute the following computer executable instructions:

[0211] Acquire a case image stream of case materials collected based on an image collection guide template displayed on a member terminal of a project member participating in the project;

[0212] According to the case images contained in the case image stream and the acquisition angles corresponding to the case images, the case images are merged into key image frames;

[0213] Detecting the key image frame in at least one image detection dimension;

[0214] If the detection fails, a capture guidance prompt corresponding to the image detection dimension that failed the detection is displayed based on the image capture guidance template.

[0215] Optionally, before the instruction for obtaining a case image stream of case materials collected based on an image collection guidance template displayed on a member terminal of a project member participating in the project is executed, the processor 820 is further configured to execute the following computer executable instructions:

[0216] Using the same-layer rendering technology to render the image acquisition guide template on the image acquisition page of the member terminal;

[0217] The rendering result of the image acquisition page is displayed on the member terminal.

[0218] Optionally, the image acquisition guidance template carries acquisition guidance prompts for acquiring case images at at least two acquisition viewing angles;

[0219] Correspondingly, the case image stream is composed of case images collected from the at least two collection perspectives for the case materials.

[0220] Optionally, the fusing the case images into key image frames according to the case images contained in the case image stream and the acquisition angles corresponding to the case images includes:

[0221] According to the case images of at least two acquisition perspectives contained in the case image stream, determining overlapping feature blocks having a feature overlapping relationship and non-overlapping feature blocks having no feature overlapping relationship in the case images of each acquisition perspective;

[0222] Using an image clarity evaluation algorithm to evaluate the image clarity of the overlapping feature blocks;

[0223] Selecting an overlapping feature block with the highest image clarity from a plurality of overlapping feature blocks with feature overlapping relations as the feature block to be fused;

[0224] The case image is fused by splicing the non-overlapping feature blocks with the feature blocks to be fused, and the splicing result is used as the key image frame.

[0225] Optionally, the determining, based on the case images of at least two acquisition perspectives contained in the case image stream, overlapping feature blocks having a feature overlapping relationship and non-overlapping feature blocks having no feature overlapping relationship in the case images of each acquisition perspective includes:

[0226] Using an image distance measurement algorithm to detect the image acquisition distance of the case images of the at least two acquisition viewing angles;

[0227] Determining whether the image acquisition distances are consistent;

[0228] If so, the overlapping feature blocks and non-overlapping feature blocks in the case images of each acquisition perspective are calculated with reference to the perspective reference points of the case images of the at least two acquisition perspectives;

[0229] If not, scaling the case image at the acquisition perspective with the visual reference point of the case image at the acquisition perspective as the center to obtain at least two case images at the acquisition perspectives with the same image acquisition distance;

[0230] The overlapping feature blocks and non-overlapping feature blocks in the case images of each captured perspective are calculated with reference to the perspective reference point.

[0231] Optionally, the detecting the key image frame in at least one image detection dimension includes:

[0232] Determining the image clarity of the key image frame based on an image clarity evaluation algorithm;

[0233] Determining whether the image clarity of the key image frame is greater than a preset clarity threshold;

[0234] If so, determining that the detection result of the key image frame is detection passed;

[0235] If not, it is determined that the detection result of the key image frame is that the image clarity detection fails, and the acquisition guidance prompt instruction corresponding to the image detection dimension that fails the detection based on the image acquisition guidance template is executed.

[0236] Optionally, displaying the acquisition guidance prompt corresponding to the image detection dimension that failed the detection based on the image acquisition guidance template includes:

[0237] Rendering a first acquisition guidance prompt that fails the image clarity detection on the image acquisition guidance template based on a same-layer rendering technology;

[0238] The image acquisition guide template after rendering the first acquisition guide prompt is displayed on the image acquisition page of the member terminal.

[0239] Optionally, after the acquisition guidance prompt instruction corresponding to the image detection dimension that failed the detection based on the image acquisition guidance template is executed, the processor 820 is further configured to execute the following computer executable instructions:

[0240] Acquire a secondary collection case image of the case material collected based on the image collection guidance template after rendering the first collection guidance prompt displayed on the image collection page;

[0241] The key image frame and the secondary collected case image are subjected to image fusion, and the case image after the image fusion is used as the first target case image of the case material.

[0242] Optionally, the detecting the key image frame in at least one image detection dimension includes:

[0243] Determining the image clarity of the key image frame based on an image clarity evaluation algorithm;

[0244] Determining whether the image clarity of the key image frame is greater than a preset clarity threshold;

[0245] If yes, detecting the image acquisition distance of the key image frame based on an image ranging algorithm;

[0246] Determine whether the image acquisition distance is less than a preset acquisition distance threshold;

[0247] If the distance is less than the preset acquisition distance threshold, determining that the detection result of the key image frame is detection passed;

[0248] If it is greater than or equal to the preset acquisition distance threshold, it is determined that the detection result of the key image frame is that the image acquisition distance detection fails, and the acquisition guidance prompt instruction corresponding to the image detection dimension that failed the detection based on the image acquisition guidance template is executed.

[0249] Optionally, displaying the acquisition guidance prompt corresponding to the image detection dimension that failed the detection based on the image acquisition guidance template includes:

[0250] Rendering a second acquisition guidance prompt for failing the image acquisition distance detection on the image acquisition guidance template based on the same-layer rendering technology;

[0251] The image acquisition guide template after rendering the second acquisition guide prompt is displayed on the image acquisition page of the member terminal.

[0252] Optionally, after the acquisition guidance prompt instruction corresponding to the image detection dimension that failed the detection based on the image acquisition guidance template is executed, the processor 820 is further configured to execute the following computer executable instructions:

[0253] Acquire a secondary collection case image of the case material collected based on the image collection guidance template after rendering the second collection guidance prompt displayed on the image collection page;

[0254] The key image frame and the second-collected case image are subjected to image fusion, and the case image after the image fusion is used as the second target case image of the case material.

[0255] An embodiment of a computer-readable storage medium provided by the present application is as follows:

[0256] The present application provides a computer-readable storage medium storing computer instructions, which are used when executed by a processor to:

[0257] Acquire a case image stream of case materials collected based on an image collection guide template displayed on a member terminal of a project member participating in the project;

[0258] According to the case images contained in the case image stream and the acquisition angles corresponding to the case images, the case images are merged into key image frames;

[0259] Detecting the key image frame in at least one image detection dimension;

[0260] If the detection fails, a capture guidance prompt corresponding to the image detection dimension that failed the detection is displayed based on the image capture guidance template.

[0261] Optionally, before the step of obtaining the case image stream of case materials collected based on the image collection guidance template displayed by the member terminals of the project members participating in the project is performed, the step includes:

[0262] Using the same-layer rendering technology to render the image acquisition guide template on the image acquisition page of the member terminal;

[0263] The rendering result of the image acquisition page is displayed on the member terminal.

[0264] Optionally, the image acquisition guidance template carries acquisition guidance prompts for acquiring case images at at least two acquisition viewing angles;

[0265] Correspondingly, the case image stream is composed of case images collected from the at least two collection perspectives for the case materials.

[0266] Optionally, the fusing the case images into key image frames according to the case images contained in the case image stream and the acquisition angles corresponding to the case images includes:

[0267] According to the case images of at least two acquisition perspectives contained in the case image stream, determining overlapping feature blocks having a feature overlapping relationship and non-overlapping feature blocks having no feature overlapping relationship in the case images of each acquisition perspective;

[0268] Using an image clarity evaluation algorithm to evaluate the image clarity of the overlapping feature blocks;

[0269] Selecting an overlapping feature block with the highest image clarity from a plurality of overlapping feature blocks with feature overlapping relations as the feature block to be fused;

[0270] The case image is fused by splicing the non-overlapping feature blocks with the feature blocks to be fused, and the splicing result is used as the key image frame.

[0271] Optionally, the determining, based on the case images of at least two acquisition perspectives contained in the case image stream, overlapping feature blocks having a feature overlapping relationship and non-overlapping feature blocks having no feature overlapping relationship in the case images of each acquisition perspective includes:

[0272] Using an image distance measurement algorithm to detect the image acquisition distance of the case images of the at least two acquisition viewing angles;

[0273] Determining whether the image acquisition distances are consistent;

[0274] If so, the overlapping feature blocks and non-overlapping feature blocks in the case images of each acquisition perspective are calculated with reference to the perspective reference points of the case images of the at least two acquisition perspectives;

[0275] If not, scaling the case image at the acquisition perspective with the visual reference point of the case image at the acquisition perspective as the center to obtain at least two case images at the acquisition perspectives with the same image acquisition distance;

[0276] The overlapping feature blocks and non-overlapping feature blocks in the case images of each captured perspective are calculated with reference to the perspective reference point.

[0277] Optionally, the detecting the key image frame in at least one image detection dimension includes:

[0278] Determining the image clarity of the key image frame based on an image clarity evaluation algorithm;

[0279] Determining whether the image clarity of the key image frame is greater than a preset clarity threshold;

[0280] If so, determining that the detection result of the key image frame is detection passed;

[0281] If not, it is determined that the detection result of the key image frame is that the image clarity detection fails, and the acquisition guidance prompt step corresponding to the image detection dimension that fails the detection based on the image acquisition guidance template is performed.

[0282] Optionally, displaying the acquisition guidance prompt corresponding to the image detection dimension that failed the detection based on the image acquisition guidance template includes:

[0283] Rendering a first acquisition guidance prompt that fails the image clarity detection on the image acquisition guidance template based on a same-layer rendering technology;

[0284] The image acquisition guide template after rendering the first acquisition guide prompt is displayed on the image acquisition page of the member terminal.

[0285] Optionally, after the step of displaying the acquisition guidance prompt corresponding to the image detection dimension that failed the detection based on the image acquisition guidance template is executed, the method includes:

[0286] Acquire a secondary collection case image of the case material collected based on the image collection guidance template after rendering the first collection guidance prompt displayed on the image collection page;

[0287] The key image frame and the secondary collected case image are subjected to image fusion, and the case image after the image fusion is used as the first target case image of the case material.

[0288] Optionally, the detecting the key image frame in at least one image detection dimension includes:

[0289] Determining the image clarity of the key image frame based on an image clarity evaluation algorithm;

[0290] Determining whether the image clarity of the key image frame is greater than a preset clarity threshold;

[0291] If yes, detecting the image acquisition distance of the key image frame based on an image ranging algorithm;

[0292] Determine whether the image acquisition distance is less than a preset acquisition distance threshold;

[0293] If the distance is less than the preset acquisition distance threshold, determining that the detection result of the key image frame is detection passed;

[0294] If it is greater than or equal to the preset acquisition distance threshold, it is determined that the detection result of the key image frame is that the image acquisition distance detection fails, and the acquisition guidance prompt step corresponding to the image detection dimension that failed the detection based on the image acquisition guidance template is executed.

[0295] Optionally, displaying the acquisition guidance prompt corresponding to the image detection dimension that failed the detection based on the image acquisition guidance template includes:

[0296] Rendering a second acquisition guidance prompt for failing the image acquisition distance detection on the image acquisition guidance template based on the same-layer rendering technology;

[0297] The image acquisition guide template after rendering the second acquisition guide prompt is displayed on the image acquisition page of the member terminal.

[0298] Optionally, after the step of displaying the acquisition guidance prompt corresponding to the image detection dimension that failed the detection based on the image acquisition guidance template is executed, the method includes:

[0299] Acquire a secondary collection case image of the case material collected based on the image collection guidance template after rendering the second collection guidance prompt displayed on the image collection page;

[0300] The key image frame and the second-collected case image are subjected to image fusion, and the case image after the image fusion is used as the second target case image of the case material.

[0301] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the above-mentioned image acquisition guidance method belong to the same concept, and the details not described in detail in the technical scheme of the storage medium can be referred to the description of the technical scheme of the above-mentioned image acquisition guidance method.

[0302] The computer instructions include computer program codes, which may be in source code form, object code form, executable files or some intermediate forms, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0303] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described action sequence, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0304] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0305] The preferred embodiments of the present application disclosed above are only used to help explain the present application. The optional embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present application, so that those skilled in the art can understand and use the present application well. The present application is limited only by the claims and their full scope and equivalents.

Claims

1. An image acquisition guidance method, characterized in that: include: Acquire a case image stream of case materials collected based on an image collection guide template displayed on a member terminal of a project member participating in the project; According to the case images contained in the case image stream and the multiple acquisition angles corresponding to the case images, the case images are fused into key image frames, wherein the key image frame is an image obtained by splicing non-overlapping feature blocks and feature blocks to be fused, the non-overlapping feature blocks are non-overlapping feature blocks that do not have feature overlapping relationships in the case images of each acquisition angle, and the feature blocks to be fused are overlapping feature blocks with the highest definition; Detecting the key image frame in at least one image detection dimension; If the detection fails, a capture guidance prompt corresponding to the image detection dimension that failed the detection is displayed based on the image capture guidance template.

2. The image acquisition guidance method according to claim 1, characterized in that: Before the step of obtaining the case image stream of case materials collected based on the image collection guide template displayed by the member terminals of the project members participating in the project is performed, the method includes: Using the same-layer rendering technology to render the image acquisition guide template on the image acquisition page of the member terminal; The rendering result of the image acquisition page is displayed on the member terminal.

3. The image acquisition guidance method according to claim 1, characterized in that: The image acquisition guidance template carries acquisition guidance prompts for acquiring case images at at least two acquisition viewing angles; Correspondingly, the case image stream is composed of case images collected from the at least two collection perspectives for the case materials.

4. The image acquisition guidance method according to claim 3, characterized in that: The step of fusing the case images into key image frames according to the case images included in the case image stream and the multiple acquisition angles corresponding to the case images includes: According to the case images of at least two acquisition perspectives contained in the case image stream, determining overlapping feature blocks having a feature overlapping relationship and non-overlapping feature blocks having no feature overlapping relationship in the case images of each acquisition perspective; Using an image clarity evaluation algorithm to evaluate the image clarity of the overlapping feature blocks; Selecting an overlapping feature block with the highest image clarity from a plurality of overlapping feature blocks with feature overlapping relations as the feature block to be fused; The case image is fused by splicing the non-overlapping feature blocks and the feature blocks to be fused, and the splicing result is used as the key image frame.

5. The image acquisition guidance method according to claim 4, characterized in that: The determining, based on the case images of at least two acquisition perspectives contained in the case image stream, overlapping feature blocks having feature overlapping relationships and non-overlapping feature blocks having no feature overlapping relationships in the case images of each acquisition perspective, comprises: Using an image distance measurement algorithm to detect the image acquisition distance of the case images of the at least two acquisition viewing angles; Determining whether the image acquisition distances are consistent; If so, the overlapping feature blocks and non-overlapping feature blocks in the case images of each acquisition perspective are calculated with reference to the perspective reference points of the case images of the at least two acquisition perspectives; If not, scaling the case image at the acquisition perspective with the visual reference point of the case image at the acquisition perspective as the center to obtain at least two case images at the acquisition perspectives with the same image acquisition distance; The overlapping feature blocks and non-overlapping feature blocks in the case images of each captured perspective are calculated with reference to the perspective reference point.

6. The image acquisition guidance method according to claim 1, characterized in that: The detecting the key image frame in at least one image detection dimension comprises: Determining the image clarity of the key image frame based on an image clarity evaluation algorithm; Determining whether the image clarity of the key image frame is greater than a preset clarity threshold; If so, determining that the detection result of the key image frame is detection passed; If not, it is determined that the detection result of the key image frame is that the image clarity detection fails, and the acquisition guidance prompt step corresponding to the image detection dimension that fails the detection based on the image acquisition guidance template is performed.

7. The image acquisition guidance method according to claim 6, characterized in that: The displaying of the acquisition guidance prompt corresponding to the image detection dimension that failed the detection based on the image acquisition guidance template includes: Rendering a first acquisition guidance prompt that fails the image clarity detection on the image acquisition guidance template based on a same-layer rendering technology; The image acquisition guide template after rendering the first acquisition guide prompt is displayed on the image acquisition page of the member terminal.

8. The image acquisition guidance method according to claim 7, characterized in that: After the step of displaying the acquisition guidance prompt corresponding to the image detection dimension that failed the detection based on the image acquisition guidance template is executed, it includes: Acquire a secondary collection case image of the case material collected based on the image collection guidance template after rendering the first collection guidance prompt displayed on the image collection page; The key image frame and the secondary collected case image are subjected to image fusion, and the case image after the image fusion is used as the first target case image of the case material.

9. The image acquisition guidance method according to claim 1, characterized in that: The detecting the key image frame in at least one image detection dimension comprises: Determining the image clarity of the key image frame based on an image clarity evaluation algorithm; Determining whether the image clarity of the key image frame is greater than a preset clarity threshold; If yes, detecting the image acquisition distance of the key image frame based on an image ranging algorithm; Determine whether the image acquisition distance is less than a preset acquisition distance threshold; If the distance is less than the preset acquisition distance threshold, determining that the detection result of the key image frame is detection passed; If it is greater than or equal to the preset acquisition distance threshold, it is determined that the detection result of the key image frame is that the image acquisition distance detection fails, and the acquisition guidance prompt step corresponding to the image detection dimension that failed the detection based on the image acquisition guidance template is executed.

10. The image acquisition guidance method according to claim 9, characterized in that: The displaying of the acquisition guidance prompt corresponding to the image detection dimension that failed the detection based on the image acquisition guidance template includes: Rendering a second acquisition guidance prompt for failing the image acquisition distance detection on the image acquisition guidance template based on the same-layer rendering technology; The image acquisition guide template after rendering the second acquisition guide prompt is displayed on the image acquisition page of the member terminal.

11. The image acquisition guidance method according to claim 10, characterized in that: After the step of displaying the acquisition guidance prompt corresponding to the image detection dimension that failed the detection based on the image acquisition guidance template is executed, it includes: Acquire a secondary collection case image of the case material collected based on the image collection guidance template after rendering the second collection guidance prompt displayed on the image collection page; The key image frame and the second-collected case image are subjected to image fusion, and the case image after the image fusion is used as the second target case image of the case material.

12. An image acquisition guiding device, characterized in that: include: A case image stream acquisition module, configured to acquire a case image stream of case materials acquired based on an image acquisition guidance template displayed by a member terminal of a project member participating in the project; A key image frame fusion module is configured to fuse the case images into key image frames according to the case images contained in the case image stream and the multiple acquisition angles corresponding to the case images, wherein the key image frame is an image obtained by splicing non-overlapping feature blocks and feature blocks to be fused, the non-overlapping feature blocks are non-overlapping feature blocks that do not have feature overlapping relationships in the case images of each acquisition angle, and the feature blocks to be fused are overlapping feature blocks with the highest clarity; A key image frame detection module, configured to detect the key image frame in at least one image detection dimension; The acquisition guidance prompt display module is configured to display the acquisition guidance prompt corresponding to the image detection dimension that failed the detection based on the image acquisition guidance template when the detection fails.

13. A computing device, characterized in that: include: Memory and processor; The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions: Acquire a case image stream of case materials collected based on an image collection guide template displayed on a member terminal of a project member participating in the project; According to the case images contained in the case image stream and the multiple acquisition angles corresponding to the case images, the case images are fused into key image frames, wherein the key image frame is an image obtained by splicing non-overlapping feature blocks and feature blocks to be fused, the non-overlapping feature blocks are non-overlapping feature blocks that do not have feature overlapping relationships in the case images of each acquisition angle, and the feature blocks to be fused are overlapping feature blocks with the highest definition; Detecting the key image frame in at least one image detection dimension; If the detection fails, a capture guidance prompt corresponding to the image detection dimension that failed the detection is displayed based on the image capture guidance template.

14. A computer-readable storage medium storing computer instructions, characterized in that: When the instruction is executed by a processor, the steps of the image acquisition guidance method described in any one of claims 1 to 11 are implemented.

Images