Commodity image recognition result de-weighting method and system

Abstract

The invention provides a commodity image recognition result de-duplication method and system, and the method comprises the steps: firstly, rapidly filtering dissimilar images through the image similarity, reducing the number of subsequent processing images, reducing the requirements for the calculation power, and improving the processing speed. Then, according to the method, a key point matching strategy is adopted to determine an overlapping region, and secondary verification is performed on the overlapping region by using intersection and comparison of commodity identification results in the overlapping region, so that misidentification of the overlapping region caused by key point matching errors is reduced, and the duplicate removal accuracy is improved. Finally, according to the method, the overlapped commodities are marked, the commodity recognition summary result is subjected to deduplication according to the marking result, and the fast and accurate commodity deduplication effect is achieved.

Description

Technical Field

[0001] The present invention relates to the field of computers, and in particular to a method and system for removing duplicates from commodity image recognition results. Background Art

[0002] Customer visits are an important task in the fast-moving consumer goods sector. Salesmen visit customers, take images of shelves, and use artificial intelligence to detect products in the images to complete tasks such as display detection and distribution rate statistics. However, for many large supermarkets, there will be many extra-long shelves or horizontal cabinets, and multiple images need to be taken to capture the entire shelf. When taking multiple images, it is inevitable that there will be overlapping areas between the images. If the recognition results in the overlapping areas of the images are not deduplicated, the summary results of multiple images will be greater than the actual display results, that is, accurate product distribution details cannot be obtained. In order to achieve product image deduplication, the current main method of image stitching is to obtain panoramic images of shelves or freezers, but image stitching is highly complex and has strict requirements for taking pictures, which will reduce the efficiency of salesmen's visits. Summary of the invention

[0003] Purpose of the invention: The present invention aims to propose a method and system for deduplicating product image recognition results, which can obtain accurate product distribution details without reducing the efficiency of salesperson visits.

[0004] Invention content: To achieve the above objectives, the present invention proposes the following technical solutions: In a first aspect, a method for removing duplicate product image recognition results is provided, comprising: Capture images of the target shelf to obtain a group of product images to be detected; Inputting the group of commodity images to be detected into a pre-trained commodity recognition model to obtain commodity recognition results for each commodity image to be detected; For each product image to be detected, based on the similarity between the product image to be detected and other product images to be detected, preliminarily determine whether the product image to be detected has an overlapping area; the product image to be detected with the overlapping area is used as the first product image, and the remaining product images to be detected are used as the second product image; For each second product image, perform key point matching on the second product image and other second product images, and determine whether the second product image has an overlapping area based on the key point matching result; for the second product image with an overlapping area, determine the position of the overlapping area in the second product image based on the key point matching result; For two second product images with overlapping areas, count the product sets in the overlapping areas of the two second product images respectively, and calculate the intersection-and-union ratio of the two product sets; If the IoU corresponding to the two second product images is greater than a preset IoU threshold, marking the products in the overlapping area of ​​any one of the two second product images as overlapping products; The commodity recognition results of the commodity images to be detected are summarized, and the commodity recognition summary results are deduplicated based on the marking results of the overlapping commodities.

[0005] As an optional implementation manner of the method of the first aspect, for each commodity image to be detected, preliminarily determining whether the commodity image to be detected has an overlapping area based on the similarity between the commodity image to be detected and other commodity images to be detected, specifically includes: For each product image to be detected, extract the image features of the product image to be detected; Based on the image features of the commodity image to be detected, calculating the similarity between the commodity image to be detected and other commodity images to be detected; If the similarity between the two commodity images to be detected is greater than a preset similarity threshold, it is preliminarily determined that there is an overlapping area between the two commodity images to be detected; otherwise, it is determined that there is no overlapping area between the two commodity images to be detected.

[0006] As an optional implementation manner of the method of the first aspect, for each second product image, performing key point matching on the second product image with other second product images, and determining whether the second product images have overlapping areas based on the key point matching results, specifically includes: For each second product image, perform key point detection on the second product image and extract key point features; Based on the key point features, the second product image is matched with other second product images in key points, and the ratio of the number of key point matches successfully to the number of key points of the second product images is calculated as the key point matching value; If the key point matching value between the two second product images is greater than a preset key point matching threshold, it is determined that there is an overlapping area between the two second product images; otherwise, it is determined that there is no overlapping area between the two second product images.

[0007] Specifically, for the second product image with the overlapping area, determining the position of the overlapping area of ​​the second product image based on the key point matching result specifically includes: For the second product image with the overlapping area, the convex hull including all the key points that are successfully matched is calculated, and the coverage area of ​​the convex hull is used as the overlapping area of ​​the second product image.

[0008] Furthermore, for two second product images with overlapping areas, counting the product sets in the overlapping areas of the two second product images respectively includes: For two second product images with overlapping areas, calculate the intersection area of ​​each product location box on each second product image and the convex hull on the second product image. If the intersection area is greater than 50% of the area of ​​the corresponding product location box, it means that the current product is located in the overlapping area of ​​the second product image. The commodity sets in the overlapping area of ​​the two second commodity images are counted respectively.

[0009] In a second aspect, a system for removing duplicate product image recognition results is provided, comprising: A data acquisition module is configured to collect images of a target shelf to obtain an image group of commodities to be detected; A commodity recognition module is configured to input the commodity image group to be detected into a pre-trained commodity recognition model to obtain a commodity recognition result of each commodity image to be detected; The filtering module is configured to preliminarily determine, for each commodity image to be detected, whether the commodity image to be detected has an overlapping area based on the similarity between the commodity image to be detected and other commodity images to be detected; the commodity image to be detected with the overlapping area is used as the first commodity image, and the remaining commodity images to be detected are used as the second commodity image; a key point matching module configured to, for each second product image, perform key point matching on the second product image with other second product images, and determine whether the second product images have overlapping areas based on the key point matching results; and for the second product images with overlapping areas, determine the positions of the overlapping areas of the second product images based on the key point matching results; The overlapping product detection module is configured to, for two second product images having overlapping areas, respectively count the product sets in the overlapping areas of the two second product images, and calculate the intersection-and-union ratio of the two product sets; if the intersection-and-union ratio corresponding to the two second product images is greater than a preset intersection-and-union ratio threshold, mark the products in the overlapping area of ​​any one of the two second product images as overlapping products; The deduplication module is configured to summarize the commodity recognition results of the commodity images to be detected, and to deduplicate the commodity recognition summary results based on the marking results of the overlapping commodities.

[0010] As an optional implementation manner of the system according to the second aspect, the filtering module is specifically used for: For each product image to be detected, extract the image features of the product image to be detected; Based on the image features of the commodity image to be detected, calculating the similarity between the commodity image to be detected and other commodity images to be detected; If the similarity between the two commodity images to be detected is greater than a preset similarity threshold, it is preliminarily determined that there is an overlapping area between the two commodity images to be detected; otherwise, it is determined that there is no overlapping area between the two commodity images to be detected.

[0011] As an optional implementation manner of the system according to the second aspect, the key point matching module is specifically used for: For each second product image, perform key point detection on the second product image and extract key point features; Based on the key point features, the second product image is matched with other second product images in key points, and the ratio of the number of key point matches successfully to the number of key points of the second product images is calculated as the key point matching value; If the key point matching value between the two second product images is greater than a preset key point matching threshold, it is determined that there is an overlapping area between the two second product images; otherwise, it is determined that there is no overlapping area between the two second product images.

[0012] Specifically, the overlapping commodity detection module is specifically used for: For the second product image with the overlapping area, the convex hull including all the key points that are successfully matched is calculated, and the coverage area of ​​the convex hull is used as the overlapping area of ​​the second product image.

[0013] Furthermore, the key point matching module is also specifically used for: For two second product images with overlapping areas, calculate the intersection area of ​​each product location box on each second product image and the convex hull on the second product image. If the intersection area is greater than 50% of the area of ​​the corresponding product location box, it means that the current product is located in the overlapping area of ​​the second product image. The commodity sets in the overlapping area of ​​the two second commodity images are counted respectively.

[0014] Beneficial effects: Compared with the prior art, the present invention has the following advantages: The present invention first uses image similarity to quickly filter out dissimilar images (i.e., there is no overlapping area), thereby reducing the number of images to be processed subsequently, lowering the requirements for computing power, and improving processing speed. Next, the present invention uses a key point matching strategy to determine the overlapping area, and uses the intersection and union comparison of the product recognition results in the overlapping area to perform a secondary check on the overlapping area, thereby reducing the misidentification of overlapping areas caused by key point matching errors and improving the accuracy of deduplication. Finally, the present invention achieves a fast and accurate product deduplication effect by marking overlapping products and deduplicating the product recognition summary results based on the marking results.

[0015] The present invention has low requirements for taking photos during implementation, has high deduplication accuracy, can meet the needs of various business scenarios, and is particularly suitable for the needs of commodity statistics in extra-long shelves or horizontal cabinets. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flowchart of a method for removing duplicates from product image recognition results according to an embodiment of the present invention; Figure 2 The present invention is a structural diagram of a system for removing duplicate product image recognition results according to an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments. However, it should be understood that the present invention can be implemented in various forms, and some exemplary and non-limiting embodiments shown in the accompanying drawings and described below are not intended to limit the present invention to the specific embodiments described.

[0018] It should be understood that, where technically feasible, the technical features listed above for different embodiments can be combined with each other to form other embodiments within the scope of the present invention. In addition, the specific examples and embodiments described in the present invention are non-limiting, and the structures, steps, and sequences described above can be modified accordingly without departing from the scope of protection of the present invention.

[0019] Please refer to Figure 1 , this embodiment proposes a method for removing duplicate product image recognition results, which includes steps S100 to S100 to S110.

[0020] S100: Capture images of a target shelf to obtain an image group of commodities to be detected.

[0021] The above-mentioned commodity image group to be detected may include one or more images, and the commodity image group to be detected should include images of all commodities on the target shelf.

[0022] S102: Inputting the group of commodity images to be detected into a pre-trained commodity recognition model to obtain commodity recognition results of each commodity image to be detected.

[0023] The above-mentioned commodity recognition result includes the commodity location and commodity code, and the commodity code is used to represent the category of the commodity.

[0024] Before executing this step, you need to pre-train a product recognition model so that the model has the ability to recognize the product location and product code from the input product image. The above product recognition model can be implemented by selecting a target detection model, such as the Faster R-CNN model or SSD target detection algorithm. The specific steps for training the product recognition model may include: (1) Collect product image samples in various product display or placement scenarios and construct a training sample set.

[0025] (2) Add product location box mark and product code to each product image sample.

[0026] (3) Input the product image samples in the training sample set into the product recognition model one by one to obtain the predicted product detection box and product code. Construct the first loss function based on the predicted product detection box and the actual product location box, and construct the second loss function based on the predicted product code and the actual product code. Then, perform a weighted sum of the first loss function and the second loss function to obtain a total loss function, and use this total loss function to update the parameters of the product recognition model until a product recognition model that meets the requirements is obtained.

[0027] The trained product recognition model can be used to recognize the product image to be detected, and the product position and product code in the product image to be detected can be obtained.

[0028] S104: For each product image to be detected, based on the similarity between the product image to be detected and other product images to be detected, preliminarily determine whether the product image to be detected has an overlapping area; the product image to be detected with the overlapping area is used as the first product image, and the remaining product images to be detected are used as the second product image.

[0029] Specifically, deep learning models such as VGG16, ResNet, and VIT can be used to extract image features of the product images to be detected. Then, the feature vector similarity between the product images to be detected is calculated. The feature vector similarity calculation methods include cosine distance, Euclidean distance, etc. It is determined whether the similarity between the product images to be detected is greater than the preset similarity threshold. If it is greater than the preset similarity threshold, it means that the two product images to be detected are highly similar and there is a possible overlapping area, which needs further judgment; otherwise, it means that the two product images to be detected are not similar and there is no overlapping area.

[0030] In this step, the similarity between the images to be detected is used to preliminarily screen out the images to be detected that may have overlapping areas, and the product images to be detected with overlapping areas are used as the first product images, and the remaining product images to be detected are used as the second product images. For the product images to be detected without overlapping areas, there is no need to perform subsequent steps such as determining the location of the overlapping area and deduplication processing, which reduces the number of subsequent processed images, reduces the requirements for computing power, and improves the processing speed of the entire solution.

[0031] S106: For each second product image, perform key point matching on the second product image with other second product images, and determine whether the second product images have overlapping areas based on the key point matching results; for second product images with overlapping areas, determine the overlapping areas in the second product images based on the key point matching results.

[0032] For the second product images whose similarity is greater than the similarity threshold, methods such as SIFT or SuperPoint can be used to extract image key points and calculate key point features. Key point matching is performed between the second product images using image key point matching methods such as SuperGlue, and the ratio of the number of key point matches to the number of key points of the corresponding second product images is calculated. This ratio can be called the key point matching value. If this ratio is greater than the preset key point matching threshold, it means that there is an overlapping area between the two second product images; otherwise, it means that there is no overlapping area between the two second product images.

[0033] For the second product images with overlapping areas, the specific location of the overlapping areas in the second product images can be determined based on the key point matching results. Specifically, for the two second product images with overlapping areas, the convex hulls containing all the successfully matched key points in the two second product images are calculated respectively, which are the overlapping areas on the two second product images.

[0034] S108: For two second product images with overlapping areas, count the product sets in the overlapping areas of the two second product images respectively, and calculate the intersection-and-union ratio of the two product sets; if the intersection-and-union ratio corresponding to the two second product images is greater than a preset intersection-and-union ratio threshold, mark the products in the overlapping area of ​​any one of the two second product images as overlapping products.

[0035] Specifically, the commodity position and commodity code of each commodity in the image to be detected have been obtained in step S102. In this step, the intersection area of ​​each commodity position box on each second commodity image and the convex hull in the second commodity image can be calculated. If the intersection area is greater than 50% of the area of ​​the commodity position box, it means that the current commodity is located in the overlapping area, otherwise, it means that the current commodity is not in the overlapping area. Count all commodity sets located in the overlapping area, and calculate the intersection and union ratio of the commodity sets in the overlapping area of ​​the two second commodity images with overlapping areas. The calculation method is: assuming that the commodity set in the overlapping area on image A is {'a':3, 'b':2, 'c':1}, and the commodity set in the overlapping area on image B is {'a':2, 'b':2,'d':1}, 'a':3 means that the number of commodity a is 3, 'b':2 means that the number of commodity b is 2, and so on. Then A∪B={'a':3,'b'2','c':1,'d':1}, A∩B={'a':2,'b':2}. Then the intersection and union ratio of the product sets in the overlapping area of ​​image A and image B is This IoU is compared with a preset IoU threshold, which can be adaptively set according to the requirements, for example, it can be set to 50%.

[0036] If the intersection-over-union ratio is greater than or equal to the preset intersection-over-union ratio threshold, it means that there is indeed overlap in the two second product images, and the products in the overlapping area of ​​the two second product images are marked to indicate that these products are overlapping products, and these overlapping products are removed in subsequent statistics. More specifically, for two second product images that do have an overlapping area, only the overlapping products in one of the second product images can be marked.

[0037] If the intersection-over-union ratio is less than the preset intersection-over-union ratio threshold, it means that the previous judgment that the two second product images have overlapping areas is incorrect, which may be caused by the similar scenes and similar displayed products of the two second product images. In this case, the two second product images are not marked as overlapping. By calculating the intersection-over-union ratio of the product set in the overlapping area, the misidentification of the overlapping area caused by similar scenes and similar displayed products can be reduced, and the recognition accuracy of the overlapping area can be improved.

[0038] S110: Summarize the commodity recognition results of the commodity images to be detected, and remove duplicates from the commodity recognition summary results based on the marking results of overlapping commodities.

[0039] In step S102, the commodity recognition results of each image to be detected have been obtained. At this time, these commodity recognition results can be summarized to obtain a preliminary commodity recognition summary result.

[0040] Next, according to the overlapping marks in step S108, the overlapping commodities are removed from the preliminary commodity identification summary result, so as to obtain an accurate commodity identification summary result.

[0041] Corresponding to the above-mentioned method for removing duplicate product image recognition results, this embodiment also provides a system for removing duplicate product image recognition results, which can be used to implement the above-mentioned method for removing duplicate product image recognition results. Figure 2 As shown, the system includes: The data acquisition module is configured to collect images of the target shelf to obtain an image group of the commodity to be detected.

[0042] The commodity recognition module is configured to input the commodity image group to be detected into a pre-trained commodity recognition model to obtain a commodity recognition result of each commodity image to be detected.

[0043] The filtering module is configured to preliminarily determine, for each product image to be detected, whether there is an overlapping area of ​​the product image to be detected based on the similarity between the product image to be detected and other product images to be detected; use the product image to be detected with the overlapping area as the first product image, and use the remaining product images to be detected as the second product image.

[0044] The key point matching module is configured to perform key point matching on each second product image with other second product images, and determine whether the second product images have overlapping areas based on the key point matching results; for second product images with overlapping areas, determine the position of the overlapping areas in the second product images based on the key point matching results.

[0045] The overlapping product detection module is configured to count the product sets in the overlapping area of ​​two second product images with overlapping areas, and calculate the intersection-and-union ratio of the two product sets; if the intersection-and-union ratio corresponding to the two second product images is greater than a preset intersection-and-union ratio threshold, the products in the overlapping area of ​​any one of the two second product images are marked as overlapping products.

[0046] The deduplication module is configured to summarize the commodity recognition results of the commodity images to be detected, and to deduplicate the commodity recognition summary results based on the marking results of the overlapping commodities.

[0047] Optionally, the above-mentioned filtering module is specifically used for: For each product image to be detected, extract the image features of the product image to be detected; Based on the image features of the commodity image to be detected, calculating the similarity between the commodity image to be detected and other commodity images to be detected; If the similarity between the two product images to be detected is greater than a preset similarity threshold, it is preliminarily determined that there is an overlapping area between the two product images to be detected; otherwise, it is determined that there is no overlapping area between the two product images to be detected.

[0048] Optionally, the key point matching module is specifically used for: For each second product image, perform key point detection on the second product image and extract key point features; Based on the key point features, the second product image is matched with the other second product images in key points, and the ratio of the number of key point matches successfully to the number of key points of the second product images is calculated as the key point matching value; If the key point matching value between the two second product images is greater than a preset key point matching threshold, it is determined that there is an overlapping area between the two second product images; otherwise, it is determined that there is no overlapping area between the two second product images.

[0049] Optionally, the overlapping product detection module is specifically used to: for the second product image with overlapping areas, calculate the convex hull containing all successfully matched key points, and use the coverage area of ​​the convex hull as the overlapping area of ​​the second product image.

[0050] Optionally, the key point matching module is further used for: For two second product images with overlapping areas, calculate the intersection area of ​​each product location box on each second product image and the convex hull on the second product image. If the intersection area is greater than 50% of the area of ​​the corresponding product location box, it means that the current product is located in the overlapping area of ​​the second product image; count the product sets in the overlapping area of ​​the two second product images respectively.

[0051] The above-mentioned commodity image recognition result deduplication system can include a client and a server in terms of hardware, wherein the client is used as a data acquisition module to collect images of the target shelf and upload the obtained commodity image group to be detected to the server. The server deploys a commodity recognition module, a filtering module, a key point matching module, an overlapping commodity detection module and a deduplication module. The server uses the above-mentioned commodity image recognition result deduplication method to count and deduplication the commodity details in the commodity image group to be detected, and then sends the obtained accurate commodity recognition summary results to the client for the salesperson to view.

[0052] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0053] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A method for removing duplicate product image recognition results, characterized in that: include: Capture images of the target shelf to obtain a group of product images to be detected; Inputting the group of commodity images to be detected into a pre-trained commodity recognition model to obtain commodity recognition results for each commodity image to be detected; For each product image to be detected, based on the similarity between the product image to be detected and other product images to be detected, preliminarily determine whether the product image to be detected has an overlapping area; the product image to be detected with the overlapping area is used as the first product image, and the remaining product images to be detected are used as the second product image; For each second product image, perform key point matching on the second product image and other second product images, and determine whether the second product image has an overlapping area based on the key point matching result; for the second product image with an overlapping area, determine the position of the overlapping area in the second product image based on the key point matching result; For two second product images with overlapping areas, count the product sets in the overlapping areas of the two second product images respectively, and calculate the intersection-and-union ratio of the two product sets; If the IoU corresponding to the two second product images is greater than a preset IoU threshold, marking the products in the overlapping area of ​​any one of the two second product images as overlapping products; The commodity recognition results of the commodity images to be detected are summarized, and the commodity recognition summary results are deduplicated based on the marking results of the overlapping commodities.

2. The method according to claim 1, characterized in that: For each product image to be detected, based on the similarity between the product image to be detected and other product images to be detected, it is preliminarily determined whether the product image to be detected has an overlapping area, specifically including: For each product image to be detected, extract the image features of the product image to be detected; Based on the image features of the commodity image to be detected, calculating the similarity between the commodity image to be detected and other commodity images to be detected; If the similarity between the two commodity images to be detected is greater than a preset similarity threshold, it is preliminarily determined that there is an overlapping area between the two commodity images to be detected; otherwise, it is determined that there is no overlapping area between the two commodity images to be detected.

3. The method according to claim 1, characterized in that For each second product image, performing key point matching on the second product image and other second product images, and determining whether there is an overlapping area of ​​the second product image based on the key point matching result, specifically includes: For each second product image, perform key point detection on the second product image and extract key point features; Based on the key point features, the second product image is matched with other second product images in key points, and the ratio of the number of key point matches successfully to the number of key points of the second product images is calculated as the key point matching value; If the key point matching value between the two second product images is greater than a preset key point matching threshold, it is determined that there is an overlapping area between the two second product images; otherwise, it is determined that there is no overlapping area between the two second product images.

4. The method according to claim 3, characterized in that For the second product image having the overlapping area, determining the position of the overlapping area in the second product image based on the key point matching result specifically includes: For the second product image with the overlapping area, the convex hull including all the key points that are successfully matched is calculated, and the coverage area of ​​the convex hull is used as the overlapping area in the second product image.

5. The method according to claim 4, characterized in that For two second product images with overlapping areas, counting the product sets in the overlapping areas of the two second product images respectively includes: For two second product images with overlapping areas, calculate the intersection area of ​​each product location box on each second product image and the convex hull on the second product image. If the intersection area is greater than 50% of the area of ​​the corresponding product location box, it means that the current product is located in the overlapping area of ​​the second product image. The commodity sets in the overlapping area of ​​the two second commodity images are counted respectively.

6. A system for removing duplicate product image recognition results, characterized in that: include: A data acquisition module is configured to collect images of a target shelf to obtain an image group of commodities to be detected; A commodity recognition module is configured to input the commodity image group to be detected into a pre-trained commodity recognition model to obtain a commodity recognition result of each commodity image to be detected; The filtering module is configured to preliminarily determine, for each commodity image to be detected, whether the commodity image to be detected has an overlapping area based on the similarity between the commodity image to be detected and other commodity images to be detected; the commodity image to be detected with the overlapping area is used as the first commodity image, and the remaining commodity images to be detected are used as the second commodity image; a key point matching module configured to, for each second product image, perform key point matching on the second product image with other second product images, and determine whether the second product images have overlapping areas based on the key point matching results; and for the second product images with overlapping areas, determine the positions of the overlapping areas in the second product images based on the key point matching results; The overlapping product detection module is configured to, for two second product images having overlapping areas, respectively count the product sets in the overlapping areas of the two second product images, and calculate the intersection-and-union ratio of the two product sets; if the intersection-and-union ratio corresponding to the two second product images is greater than a preset intersection-and-union ratio threshold, mark the products in the overlapping area of ​​any one of the two second product images as overlapping products; The deduplication module is configured to summarize the commodity recognition results of the commodity images to be detected, and to deduplicate the commodity recognition summary results based on the marking results of the overlapping commodities.

7. The system according to claim 6, characterized in that The filtering module is specifically used for: For each product image to be detected, extract the image features of the product image to be detected; Based on the image features of the commodity image to be detected, calculating the similarity between the commodity image to be detected and other commodity images to be detected; If the similarity between the two commodity images to be detected is greater than a preset similarity threshold, it is preliminarily determined that there is an overlapping area between the two commodity images to be detected; otherwise, it is determined that there is no overlapping area between the two commodity images to be detected.

8. The system according to claim 6, characterized in that The key point matching module is specifically used for: For each second product image, perform key point detection on the second product image and extract key point features; Based on the key point features, the second product image is matched with other second product images in key points, and the ratio of the number of key point matches successfully to the number of key points of the second product images is calculated as the key point matching value; If the key point matching value between the two second product images is greater than a preset key point matching threshold, it is determined that there is an overlapping area between the two second product images; otherwise, it is determined that there is no overlapping area between the two second product images.

9. The system according to claim 8, characterized in that The overlapping commodity detection module is specifically used for: For the second product image with the overlapping area, the convex hull including all the key points that are successfully matched is calculated, and the coverage area of ​​the convex hull is used as the overlapping area of ​​the second product image.

10. The system according to claim 9, characterized in that The key point matching module is also specifically used for: For two second product images with overlapping areas, calculate the intersection area of ​​each product location box on each second product image and the convex hull on the second product image. If the intersection area is greater than 50% of the area of ​​the corresponding product location box, it means that the current product is located in the overlapping area of ​​the second product image. The commodity sets in the overlapping areas of the two second commodity images are counted respectively.

Images