Method and device for binding goods shelf camera to goods shelf

Abstract

The invention discloses a method and a device for binding a goods shelf with a goods shelf camera. The method comprises the following steps: determining a first type of color bound with each electronic price tag at the edge of the goods shelf; screening the electronic price tags for binding from the electronic price tags except the electronic price tags at the edge of the goods shelf, performing binary coding on the flashing light colors of the electronic price tags for binding based on the second type of colors, and determining the corresponding relationship between the binary codes and the goods shelf; sending a flashing instruction to the electronic price tags at the edge of the goods shelf and the electronic price tags for binding; sending a shooting instruction to a store camera; identifying the shooting result of each camera, determining the edge of each goods shelf according to the electronic price tag of the first type of color, and taking a region formed in the edge of each goods shelf as a region of interest of each camera; and recognizing a binary code corresponding to the flashing light color of the electronic price tag for binding in each region of interest, and binding the camera with the shelf corresponding to the binary code. The goods shelf camera can be automatically bound to the goods shelf.

Description

Technical Field

[0001] The present invention relates to the field of communication technologies, and in particular to a method and device for binding a shelf camera to a shelf. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. No statement herein is admitted to be prior art by virtue of its inclusion in this section.

[0003] Electronic price tags (ESTs) are digital price display devices used in the retail industry, primarily replacing traditional paper price tags and enabling remote, real-time price updates and management. As the retail industry evolves towards digitalization and intelligentization, ESTs are becoming a crucial component of smart retail due to their high efficiency, environmental friendliness, and low maintenance costs. ESTs with positioning capabilities utilize specialized technology to identify their shelf and shelf location.

[0004] Shelf cameras are intelligent vision devices deployed on retail shelves or in supermarket display areas, primarily used for product identification and inventory management. With the advancement of computer vision, artificial intelligence, and edge computing technologies, shelf cameras have become core sensing terminals for smart retail.

[0005] When using a shelf camera, it needs to know information about the shelf it's photographing, primarily the shelf number. The shelf itself doesn't have information that the camera can use to identify it. Generally, manual binding is used. This involves manually entering the shelf number into the inspection software during camera installation. Alternatively, a visible barcode, QR code, or other information is affixed to the shelf, allowing identification through photos captured by the camera. However, this method requires manual labeling, and the camera can't guarantee clear photos, making the recognition results uncertain.

[0006] After completing shelf binding and registration, it's generally necessary to determine the shelf's boundaries to determine the shelf camera's area of ​​interest. One solution is to manually define the boundaries when the shelf camera's application captures the image, but this method is labor-intensive and inefficient. Another solution is to use computer vision to automatically identify shelf boundaries or areas of interest. However, given the wide variety of shelf types and the complex real-world scenarios, existing algorithms struggle to accurately identify them.

[0007] In summary, there is currently a need for a solution that effectively implements the binding of shelves and shelf cameras, so that the shelf cameras can be bound to the shelves and the regions of interest of the shelf cameras can be determined. Summary of the Invention

[0008] An embodiment of the present invention provides a method for binding a shelf camera to a shelf, which enables the shelf camera to automatically bind to the shelf without manual intervention and can determine the area of ​​interest of the shelf camera, including:

[0009] Obtaining electronic price tags at the edge of the shelf based on the relationship between the electronic price tags and the shelf, and determining a first color category bound to each electronic price tag at the edge of the shelf, where the first color category includes at least one randomly selected color;

[0010] Selecting an electronic price tag for binding from the electronic price tags other than the electronic price tags at the edge of the shelf, binary-coding the flashing light color of the selected electronic price tag for binding based on a second type of color, and determining a correspondence between the binary code and the shelf, wherein the second type of color is a color other than the first type of color;

[0011] At a preset time point, a flashing instruction is sent to the electronic price tags at the edge of the shelf and the electronic price tags used for binding, so that the electronic price tags at the edge of the shelf flash according to the first color of the binding electronic price tags at the edge of the shelf in the flashing instruction, and the electronic price tags used for binding flash according to the order in the binary code in the flashing instruction;

[0012] Send shooting instructions to all cameras in the store so that all cameras can shoot shelves according to the shooting instructions, and receive shooting results from all cameras;

[0013] Identify the shooting results of each camera, determine the edge of each shelf based on the first type of color electronic price tags identified from the shooting results, and use the area formed within the edge of each shelf as the area of ​​interest of each camera;

[0014] For each camera, the binary code corresponding to the flashing color of the electronic price tag used for binding in each area of ​​interest is identified from the shooting results, and the camera is bound to the shelf corresponding to the binary code.

[0015] An embodiment of the present invention provides a device for binding a shelf camera to a shelf, which enables the shelf camera to automatically bind to the shelf without manual intervention and can determine the area of ​​interest of the shelf camera, including:

[0016] a shelf edge color determination module, configured to obtain the electronic price tags at the shelf edge based on the ownership relationship between the electronic price tags and the shelf, and determine a first color category bound to each electronic price tag at the shelf edge, wherein the first color category includes at least one randomly selected color;

[0017] a binary encoding module, configured to select an electronic price tag for binding from electronic price tags other than those on the edge of the shelf, binary encode the flashing color of the selected electronic price tag for binding based on a second type of color, and determine a correspondence between the binary code and the shelf, wherein the second type of color is a color other than the first type of color;

[0018] A flashing module is configured to send a flashing instruction to the electronic price tags at the edge of the shelf and the electronic price tags used for binding at a preset time point, so that the electronic price tags at the edge of the shelf flash according to the first color of the electronic price tags at the edge of the shelf bound to the electronic price tags in the flashing instruction, and the electronic price tags used for binding flash according to the order in the binary code in the flashing instruction;

[0019] The shooting module is used to send shooting instructions to all cameras in the store so that all cameras can shoot shelves according to the shooting instructions, and receive the shooting results fed back by all cameras;

[0020] A region of interest recognition module is used to recognize the shooting results of each camera, determine the edge of each shelf based on the electronic price tags of the first color identified from the shooting results, and use the area formed within each shelf edge as the region of interest of each camera;

[0021] The binding module is used to identify the binary code corresponding to the flashing color of the electronic price tag used for binding in each area of ​​interest from the shooting results for each camera, and bind the camera to the shelf corresponding to the binary code.

[0022] An embodiment of the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method of binding a shelf camera to a shelf is implemented.

[0023] An embodiment of the present invention further provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the method of binding a shelf camera to a shelf is implemented.

[0024] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the above-mentioned method of binding shelf cameras to shelves.

[0025] In an embodiment of the present invention, based on the ownership relationship between the electronic price tags and the shelves, the electronic price tags at the edge of the shelf are obtained, and the first type of color bound to each electronic price tag at the edge of the shelf is determined; the electronic price tags for binding are screened out from the electronic price tags other than the electronic price tags at the edge of the shelf, the flashing colors of the screened electronic price tags for binding are binary-coded based on the second type of color, and the corresponding relationship between the binary code and the shelf is determined; at a preset time point, a flashing instruction is sent to the electronic price tags at the edge of the shelf and the electronic price tags for binding, so that the electronic price tags at the edge of the shelf flash according to the first type of color bound to the electronic price tags at the edge of the shelf in the flashing instruction. The electronic price tags used for binding flash in the order of the binary codes in the flashing instructions; a shooting instruction is sent to all cameras in the store so that all cameras shoot the shelves according to the shooting instruction, and the shooting results fed back by all cameras are received; the shooting results of each camera are identified, and the edge of each shelf is determined based on the electronic price tags of the first type of color identified from the shooting results, and the area formed within each shelf edge is used as the area of ​​interest of each camera; for each camera, the binary code corresponding to the flashing color of the electronic price tags used for binding in each area of ​​interest is identified from the shooting results, and the camera is bound to the shelf corresponding to the binary code. Compared with the manual binding method and the manual boundary demarcation method in the prior art, the present invention uses the first type of color to enable the electronic price tag to identify the area of ​​interest based on the shooting results of the camera after the flashing; and also uses the binary code designed for the second type of color (the binary code has a corresponding relationship with the shelf) to bind the camera to the shelf corresponding to the binary code, thereby automatically and efficiently completing the automatic binding of the shelf camera to the shelf without manual intervention. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0027] Figure 1 This is a flow chart of a method for binding a shelf camera to a shelf in an embodiment of the present invention;

[0028] Figure 2 Schematic diagram of different first-category colors of electronic price labels on shelf edges according to an embodiment of the present invention;

[0029] Figure 3 Schematic diagram of binary coding of flashing light colors of multiple electronic price tags according to an embodiment of the present invention;

[0030] Figure 4This is a schematic diagram of binary encoding of an electronic price tag at the center of a shelf according to an embodiment of the present invention;

[0031] Figure 5 is a schematic diagram of a new camera field of view in an embodiment of the present invention;

[0032] Figure 6 This is a schematic diagram showing the codes of all electronic price tags on the shelves according to an embodiment of the present invention;

[0033] Figure 7 This is a schematic diagram of the structure of a device for binding a shelf camera to a shelf in an embodiment of the present invention;

[0034] Figure 8 Schematic diagram of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0035] To make the purpose, technical solutions and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0036] Figure 1 This is a flow chart of a method for binding a shelf camera to a shelf in an embodiment of the present invention, including:

[0037] Step 101: obtaining electronic price tags at the edge of the shelf based on the relationship between the electronic price tags and the shelf, and determining a first color category bound to each electronic price tag at the edge of the shelf, wherein the first color category includes at least one randomly selected color;

[0038] Step 102: Filter out electronic price tags for binding from the electronic price tags other than those at the edge of the shelf, binary-code the flashing colors of the filtered electronic price tags for binding based on a second color category, and determine a correspondence between the binary code and the shelf, where the second color category is a color other than the first color category.

[0039] Step 103: at a preset time, sending a flashing instruction to the electronic price tags at the edge of the shelf and the electronic price tags used for binding, so that the electronic price tags at the edge of the shelf flash according to the first color of the electronic price tags at the edge of the shelf bound to the electronic price tags in the flashing instruction, and the electronic price tags used for binding flash according to the order in the binary code in the flashing instruction;

[0040] Step 104: Sending a shooting instruction to all cameras in the store so that all cameras shoot the shelves according to the shooting instruction, and receiving shooting results fed back by all cameras;

[0041] Step 105: Identify the shooting results of each camera, determine the edge of each shelf based on the electronic price tags of the first color identified from the shooting results, and use the area formed within each shelf edge as the area of ​​interest of each camera;

[0042] Step 106 : For each camera, identify the binary code corresponding to the flashing color of the electronic price tag for binding in each area of ​​interest from the shooting results, and bind the camera to the shelf corresponding to the binary code.

[0043] Compared with the manual binding method and manual boundary demarcation method in the prior art, the present invention uses the first type of color to enable the electronic price tag to identify the area of ​​interest through the camera's shooting results after the flashing light; and also uses the binary code designed by the second type of color (the binary code has a corresponding relationship with the shelf) to bind the camera to the shelf corresponding to the binary code, thereby automatically and efficiently completing the automatic binding of the shelf camera to the shelf without human intervention.

[0044] The embodiment of the present invention is applied to a background server for managing electronic price tags.

[0045] In step 101, based on the relationship between the electronic price tags and the shelves, the electronic price tags at the edge of the shelf are obtained, and a first category of colors bound to each electronic price tag at the edge of the shelf is determined, where the first category of colors includes at least one randomly selected color.

[0046] The electronic price tags mentioned in the embodiments of the present invention are positioning electronic price tags. This type of positioning electronic price tags can know the shelf to which they belong and their position on each shelf, including the shelf (vertical position) and the sequential position or physical coordinates within the shelf. This information will be stored in the background system of the electronic price tag and can be updated in real time according to the changes in the price tags on the shelf. That is, the background system can obtain the vertical and horizontal position of the shelf where any bound electronic price tag is located in real time. If the position of the electronic price tag changes, the data will also be updated in real time.

[0047] Shelf cameras are deployed on the opposite side of the target shelf. These cameras use computer vision to monitor and analyze the status of merchandise on the shelf, including but not limited to display and stock-out conditions. Camera types include, but are not limited to, closed-circuit surveillance cameras, miniature battery-powered cameras, and robot-mounted cameras. In addition to the conventional cameras listed above, embodiments of the present invention propose shelf cameras with neighboring price tag location awareness, similar to electronic price tags. These shelf cameras are aware of all electronic price tags within a certain range.

[0048] Specifically, the electronic price tags on the edge of the shelf are electronic price tags that can determine the shape of the shelf. For example, if the shelf is rectangular or square, the electronic price tags at the four corners of the shelf can be used as electronic price tags on the edge of the shelf. The four corners of the shelf are connected by straight lines to obtain the shelf range. In addition to the electronic price tags at the four corners, the edge price tags can still be used as electronic price tags for binding; if the shelf is circular, multiple electronic price tags with circular points can be used, and the multiple points are connected by curves to obtain the shelf range.

[0049] In the embodiment of the present invention, a rectangular shelf is taken as an example. The electronic price tags on the edge of the shelf can be four: the upper left corner, the upper right corner, the lower left corner, and the lower right corner of the shelf. Of course, electronic price tags on other edges of the shelf can also be added to achieve a more accurate location description.

[0050] In one embodiment, determining the first color of each electronic shelf label bound to the shelf edge includes:

[0051] Determine the first color bound to all electronic price tags on the left edge of the shelf among the electronic price tags on the edge of the shelf;

[0052] Determine the first color bound to all electronic price tags on the right edge of the shelf among the electronic price tags on the shelf edge, wherein the first color bound to the electronic price tags on the left edge of the shelf is different from the first color bound to the electronic price tags on the right edge of the shelf.

[0053] That is, as long as the first color of the electronic price tags on the left edge of the shelf is different from the first color of the electronic price tags on the right edge of the shelf, different shelves can be completely distinguished. For the electronic price tags on the same side of the shelf, the first colors of the bindings can be the same or different.

[0054] Figure 2 Schematic diagram of different first-category colors of electronic price labels on the edge of a shelf according to an embodiment of the present invention. Figure 2 In this example, shelf 0001 is used, using first-class colors A, B, C, and D. Each price tag in the upper left corner is assigned to first-class color A, the upper right corner is assigned to first-class color B, the lower left corner is assigned to first-class color C, and the lower right corner is assigned to first-class color D. In addition to A, B, C, and D, which represent four different colors, other colors such as X, Y, and Z are called second-class colors.

[0055] In step 102, electronic price tags for binding are screened out from the electronic price tags other than the electronic price tags at the edge of the shelf, the flashing colors of the screened electronic price tags for binding are binary-coded based on the second category of colors, and the correspondence between the binary codes and the shelves is determined, where the second category of colors is a color other than the first category of colors;

[0056] In one embodiment, electronic price tags for binding are selected from electronic price tags other than those on the edge of the shelf, and the flashing colors of the selected electronic price tags for binding are binary-coded based on the second color category, including:

[0057] Selecting a preset number of electronic price tags for binding from the electronic price tags other than the electronic price tags at the edge of the shelf in a preset spatial order;

[0058] Represent the binary coded 0 with the first second color;

[0059] The binary coded 1 is represented by the second second color;

[0060] The flashing color of each electronic price tag used for binding is determined to be the first second-category color or the second second-category color, and a binary code formed by the second-category color of the electronic price tag used for binding is obtained, where the length of the binary code is the length of a preset number.

[0061] Figure 3 This is a schematic diagram of binary coding the flashing colors of multiple electronic price tags in an embodiment of the present invention. For example, taking a rectangular shelf as a unit, excluding the electronic price tags at the four corners of the shelf, four price tags are selected in a preset spatial order and binary coded, where the binary coded 0 is represented by the first second-category color X, and the binary coded 1 is represented by the second second-category color Y. These four electronic price tags with a spatial order are made to light up in the X light color or the Y light color according to the binary coding form, for example Figure 3 The four electronic price tags flash in the color of X, X, X, Y, then the binary code is 0001, and the subsequent four electronic price tags flash in the corresponding color of X, X, X, Y. This binary code can represent up to 2 4 = 16 different shelves. The preset space order can be selected from left to right or from top to bottom.

[0062] The binary code length of the electronic price tag can be dynamically adjusted based on factors such as shelf size and camera resolution. For example, for large shelves or high-resolution cameras, the number of code bits can be increased to improve shelf recognition accuracy; for small shelves, the number of code bits can be reduced to save resources.

[0063] In addition to existing colors, more colors can be introduced for mixed coding. Different color combinations can represent different shelf information, further improving coding capacity and shelf differentiation. For example, the RGB color model can be used to encode shelf numbers using a combination of multiple colors.

[0064] In addition to color, you can also consider using the flashing frequency and duration of the electronic price tag for coding. For example, different flashing frequencies correspond to different shelf groups, and different flashing durations correspond to specific shelf numbers. Combining this with color coding can create a more complex coding system. I won't go into details here.

[0065] In one embodiment, electronic price tags for binding are selected from electronic price tags other than those on the edge of the shelf, and the flashing light colors of the selected electronic price tags for binding are binary-coded based on the second color category, including:

[0066] Selecting at least one electronic price tag at the center of the shelf as the electronic price tag for binding;

[0067] Select the third second-category color as the initial light color of the electronic price tag used for binding;

[0068] The sequence of the flashing light colors of the electronic price tag used for binding is binary-encoded by the first second-category color and the second second-category color.

[0069] Figure 4 This is a schematic diagram of binary encoding of an electronic price tag located at the center of a shelf in an embodiment of the present invention. For example, a price tag located near the center of a rectangular shelf is selected and 4-bit binary encoded. The third second-category color, Z, is selected as its initial light color to indicate the start of flashing for this electronic price tag. Subsequent light colors are represented by the first second-category color, X, and the second second-category color, Y. The order of the flashing colors is X, X, X, Y, resulting in a binary code of 0001. Subsequently, when this electronic price tag flashes, the first flashing color is Z, indicating the start of flashing, and then the colors flash in the order of X, X, X, Y. This method is optional and may conflict with the binary encoding method for a preset number of electronic price tags. In actual use, it can be determined whether to use this step and the binary encoding method for the preset number of electronic price tags simultaneously, or to use them separately.

[0070] In step 103, at a preset time point, a flashing instruction is sent to the electronic price tags at the edge of the shelf and the electronic price tags used for binding, so that the electronic price tags at the edge of the shelf flash according to the first color of the binding electronic price tags at the edge of the shelf in the flashing instruction, and the electronic price tags used for binding flash according to the order in the binary code in the flashing instruction;

[0071] The preset time point can be non-business hours. For the electronic price tags on the edge of the shelf, the flashing instruction includes the first type of color flashing light bound to the electronic price tags on the edge of the shelf, for example, the flashing light color A in the upper left corner of the shelf, the flashing light color B in the upper right corner, the flashing light color C in the lower left corner, and the flashing light color D in the lower right corner. For electronic price tags other than the electronic price tags on the edge of the shelf, the flashing instruction includes binary code.

[0072] In step 104, a shooting instruction is sent to all cameras in the store so that all cameras shoot the shelves according to the shooting instruction, and the shooting results fed back by all cameras are received;

[0073] Typically, after a slight delay after the ESL light flashes, all cameras capture the shelf, producing an image or video. The video is then transmitted back to the backend server for binding confirmation. Based on factors such as ambient light and shelf distance, the camera's shooting parameters (such as exposure time, focal length, and aperture) are automatically adjusted to ensure clear images or videos that are suitable for ESL recognition.

[0074] In step 105, the shooting results of each camera are identified, and the edge of each shelf is determined based on the electronic price tags of the first color identified from the shooting results, and the area formed within each shelf edge is used as the area of ​​interest of each camera;

[0075] Analyze captured images or recorded videos for each camera to confirm that the four light colors (A / B / C / D) are within the camera's field of view. Consider a complete set of flashing price tags as the range of a shelf to obtain the region of interest (ROI) for that shelf within that camera. Note that the same camera can have multiple ROIs.

[0076] In step 106, for each camera, the binary code corresponding to the flashing color of the electronic price tag for binding in each area of ​​interest is identified from the shooting results, and the camera is bound to the shelf corresponding to the binary code.

[0077] Taking the region of interest as the unit, the image or video within each region of interest is analyzed separately to obtain the binary code within each region of interest. Then, the camera is bound to the shelf corresponding to the binary code. For example, the binary code of the flash light corresponding to shelf 0001 is XXXY. If the flash light sequence recognized is XXXY, the region of interest can be identified as shelf 0001, and the camera can be bound to shelf 0001.

[0078] In one embodiment, the method further comprises:

[0079] If multiple cameras recognize the same binary code, the positions of the shelves corresponding to the binary code in the images captured by the different cameras are analyzed, and the camera corresponding to the image closest to the center of the image is bound to the shelf corresponding to the binary code. In other words, when multiple cameras capture the same shelf, the positions of the shelves in the images captured by the multiple cameras are first analyzed, and the image closest to the center of the image is selected, and the camera corresponding to that image is bound to the shelf.

[0080] Through the above matching, the camera with the most suitable position can be found, thereby improving the matching accuracy.

[0081] In one embodiment, the method further comprises:

[0082] The pixel coordinates of the shelf in the frame captured by the bound camera are obtained, and the pixel coordinates are used for commodity identification.

[0083] During the entire process, only the installation work needs to be completed manually on site, and the matching process is fully automated, saving manpower and material resources and improving the deployment efficiency of the shelf camera system.

[0084] In one embodiment, the method further comprises:

[0085] After the new camera is installed and deployed in the store, a set of products with a preset number of built-in confidence values ​​greater than a confidence threshold in the new camera's field of view is obtained;

[0086] Obtaining the electronic price tag set corresponding to the product set;

[0087] Bind the new camera to the shelf where the electronic shelf tag is located in the electronic shelf tag collection.

[0088] Specifically, after the complete deployment, if new cameras are installed and deployed in the store, an incremental matching process will be performed. Incremental matching relies on product recognition technology, which identifies a set of products with a high confidence level within the field of view of the new camera. Figure 5 This is a schematic diagram of the new camera's field of view in an embodiment of the present invention. It can be seen that some shelves are outside the camera's field of view. This field of view can be determined by taking pictures with the camera in advance. After obtaining a set of products with a preset confidence level greater than a confidence threshold, the corresponding set of electronic price tags can be directly obtained. Since the electronic price tags are located, the shelf on which the electronic price tag is located can be directly determined, and the new camera can be bound to the shelf on which the electronic price tag in the set of electronic price tags is located.

[0089] In the above embodiment, a preset number of product sets with a confidence level greater than a confidence threshold within the new camera's field of view were selected. A confidence threshold was used, but since the confidence level cannot reach 100%, to further improve the accuracy of shelf binding for the new camera, the following embodiment is provided. In this embodiment, the electronic price tags corresponding to the shelves to which these product sets belong are activated during non-business hours and used with the newly installed camera to take photos or videos. The incremental matching process is exactly the same as above, except that the activated shelves are localized rather than global, and only the newly installed camera performs the photo and matching process.

[0090] In one embodiment, the method further comprises:

[0091] After the new camera is installed and deployed in the store, a set of products with a preset number of built-in confidence values ​​greater than a confidence threshold in the new camera's field of view is obtained;

[0092] At a preset time point, a flashing instruction is sent to the electronic price tag set corresponding to the product set and the electronic price tags at the edge of the shelf where the electronic price tags in the electronic price tag set are located, so that the electronic price tags at the edge of the shelf flash according to the first type of color bound to the electronic price tags at the edge of the shelf in the flashing instruction, and the electronic price tag set corresponding to the product set flashes according to the order in the binary code in the flashing instruction;

[0093] Sending a shooting instruction to the new camera so that the new camera can shoot the shelf according to the shooting instruction, and receiving the shooting result fed back by the new camera;

[0094] Identify the shooting results of the new camera, determine the edge of each shelf based on the electronic price tags of the first color identified from the shooting results, and use the area formed within the edge of each shelf as the area of ​​interest of the new camera;

[0095] Identify the binary code corresponding to the flashing color of the electronic price tag corresponding to the set of products in each area of ​​interest from the shooting results, and bind the new camera to the shelf corresponding to the binary code.

[0096] The above embodiments all achieve binding by flashing the light of the electronic price tag. The embodiment of the present invention also proposes a method for achieving binding by displaying a code on the electronic price tag on the shelf.

[0097] In one embodiment, a method for binding a shelf camera to a shelf includes:

[0098] At a preset time point, a code display instruction is sent to all electronic price tags on the shelf, so that all electronic price tags on the shelf display the shelf code;

[0099] Send shooting instructions to all cameras in the store so that all cameras can shoot shelves according to the shooting instructions, and receive shooting results from all cameras;

[0100] Identify the shooting results of each camera, obtain the codes of all electronic price tag display shelves, and determine the same code as the area of ​​interest, and bind the shelf corresponding to the area of ​​interest to the camera.

[0101] For example, Figure 6 This is a schematic diagram showing the shelf codes displayed on all electronic price tags of the shelf in an embodiment of the present invention. Figure 5 In the example, the code of shelf 0001 is 0001. If the barcode of any electronic price tag in the area of ​​interest can be identified as 0001, the area of ​​interest can be bound to shelf 0001.

[0102] Similarly, after the new camera is installed and deployed in the store, a set of products with a preset number of built-in confidence values ​​greater than a confidence threshold in the new camera's field of view is obtained; a set of electronic price tags corresponding to the set of products is obtained; and the new camera is bound to the shelf where the electronic price tags in the set of electronic price tags are located.

[0103] After obtaining a set of products with a preset number of built-in confidence values ​​greater than a confidence threshold in the new camera field of view, the following further includes:

[0104] At a preset time point, a code display instruction is sent to the electronic price tag corresponding to the product set and the electronic price tag at the edge of the shelf where the electronic price tag is located, so that the electronic price tag corresponding to the product set displays the shelf code;

[0105] Sending a shooting instruction to the new camera so that the new camera can shoot the shelf according to the shooting instruction, and receiving the shooting result fed back by the new camera;

[0106] Identify the shooting results of each camera, obtain the code of the electronic price tag display shelf corresponding to the product set, and determine the same code as the area of ​​interest, and bind the shelf corresponding to the area of ​​interest to the camera.

[0107] An embodiment of the present invention further provides a device for binding a shelf camera to a shelf, the principle of which is similar to the method for binding a shelf camera to a shelf.

[0108] Figure 7 This is a schematic diagram of the structure of a device for binding a shelf camera to a shelf in an embodiment of the present invention, including:

[0109] The shelf edge color determination module 701 is configured to obtain the electronic price tags at the shelf edge based on the relationship between the electronic price tags and the shelf, and determine a first color category associated with each electronic price tag at the shelf edge, where the first color category includes at least one randomly selected color.

[0110] Binary encoding module 702, configured to select electronic price tags for binding from electronic price tags other than those on the edge of the shelf, binary encode the flashing colors of the selected electronic price tags for binding based on a second category of colors, and determine a correspondence between the binary codes and the shelf; the second category of colors being colors other than the first category of colors;

[0111] The flashing module 703 is configured to send a flashing instruction to the electronic price tags at the edge of the shelf and the electronic price tags for binding at a preset time point, so that the electronic price tags at the edge of the shelf flash according to the first color of the electronic price tags for binding at the edge of the shelf in the flashing instruction, and the electronic price tags for binding flash according to the order in the binary code in the flashing instruction;

[0112] The shooting module 704 is used to send shooting instructions to all cameras in the store so that all cameras can shoot shelves according to the shooting instructions, and receive shooting results fed back by all cameras;

[0113] The region of interest identification module 705 is configured to identify the shooting results of each camera, determine the edge of each shelf based on the electronic price tags of the first color identified from the shooting results, and use the area formed within each shelf edge as the region of interest of each camera;

[0114] The binding module 706 is configured to identify, for each camera, from the shooting results, the binary code corresponding to the flashing color of the electronic price tag for binding in each area of ​​interest, and bind the camera to the shelf corresponding to the binary code.

[0115] In one embodiment, the shelf edge color determination module 701 is configured to:

[0116] Determine the first color bound to all electronic price tags on the left edge of the shelf among the electronic price tags on the edge of the shelf;

[0117] Determine the first color bound to all electronic price tags on the right edge of the shelf among the electronic price tags on the shelf edge, wherein the first color bound to the electronic price tags on the left edge of the shelf is different from the first color bound to the electronic price tags on the right edge of the shelf.

[0118] In one embodiment, the binary encoding module is used to:

[0119] Selecting a preset number of electronic price tags for binding from the electronic price tags other than the electronic price tags at the edge of the shelf in a preset spatial order;

[0120] Represent the binary coded 0 with the first second color;

[0121] The binary coded 1 is represented by the second second color;

[0122] The flashing color of each electronic price tag used for binding is determined to be the first second-category color or the second second-category color, and a binary code formed by the second-category color of the electronic price tag used for binding is obtained, where the length of the binary code is the length of a preset number.

[0123] In one embodiment, the binary encoding module is used to:

[0124] Selecting at least one electronic price tag at the center of the shelf as the electronic price tag for binding;

[0125] Select the third second-category color as the initial light color of the electronic price tag used for binding;

[0126] The sequence of the flashing light colors of the electronic price tag used for binding is binary-encoded by the first second-category color and the second second-category color.

[0127] In one embodiment, the binding module is further configured to:

[0128] If multiple cameras recognize the same binary code, analyze the positions of the shelves corresponding to the binary code in the shooting results of different cameras, and bind the camera corresponding to the shooting result closest to the center of the shooting result to the shelf corresponding to the binary code.

[0129] In one embodiment, the binding module 706 is further configured to:

[0130] After the new camera is installed and deployed in the store, a set of products with a preset number of built-in confidence values ​​greater than a confidence threshold in the new camera's field of view is obtained; a set of electronic price tags corresponding to the set of products is obtained; and the new camera is bound to the shelf where the electronic price tags in the set of electronic price tags are located.

[0131] In one embodiment, the binding module 706 is further configured to: after the new camera is installed and deployed in the store, obtain a set of a preset number of products whose built-in confidence in the new camera's field of view is greater than a confidence threshold;

[0132] The flashing module is further configured to: at a preset time point, send a flashing instruction to the electronic price tag set corresponding to the product set and the electronic price tags at the edge of the shelf where the electronic price tags in the electronic price tag set are located, so that the electronic price tags at the edge of the shelf flash according to the first color bound to the electronic price tags at the edge of the shelf in the flashing instruction, and the electronic price tag set corresponding to the product set flashes according to the order in the binary code in the flashing instruction;

[0133] The shooting module is further used to: send a shooting instruction to the new camera so that the new camera shoots the shelf according to the shooting instruction, and receive the shooting result fed back by the new camera;

[0134] The region of interest recognition module is further configured to: identify the shooting results of the new camera, determine the edge of each shelf based on the electronic price tags of the first color identified from the shooting results, and use the area formed within the edge of each shelf as the region of interest of the new camera;

[0135] The binding module is also used to: identify the binary code corresponding to the flashing color of the electronic price tag corresponding to the set of goods in each area of ​​interest from the shooting results, and bind the new camera to the shelf corresponding to the binary code.

[0136] In summary, in the method and device proposed in the embodiment of the present invention, based on the ownership relationship between the electronic price tags and the shelves, the electronic price tags at the edge of the shelf are obtained, and the first type of color bound to each electronic price tag at the edge of the shelf is determined; the electronic price tags for binding are screened out from the electronic price tags other than the electronic price tags at the edge of the shelf, the flashing colors of the screened electronic price tags for binding are binary-coded based on the second type of color, and the correspondence between the binary code and the shelf is determined; at a preset time point, a flashing instruction is sent to the electronic price tags at the edge of the shelf and the electronic price tags for binding, so that the electronic price tags at the edge of the shelf are flashed according to the first type of color bound to the electronic price tags at the edge of the shelf in the flashing instruction. The first color flashes, and the electronic price tag used for binding flashes in the order of the binary code in the flashing instruction; a shooting instruction is sent to all cameras in the store so that all cameras shoot the shelves according to the shooting instruction, and the shooting results fed back by all cameras are received; the shooting results of each camera are identified, and the edge of each shelf is determined based on the electronic price tag of the first color identified from the shooting results, and the area formed within each shelf edge is used as the area of ​​interest of each camera; for each camera, the binary code corresponding to the flashing color of the electronic price tag used for binding in each area of ​​interest is identified from the shooting results, and the camera is bound to the shelf corresponding to the binary code. Compared with the manual binding method and the manual boundary demarcation method in the prior art, the present invention uses the first color to enable the electronic price tag to identify the area of ​​interest based on the shooting results of the camera after the flashing; and also uses the binary code designed for the second color (the binary code has a corresponding relationship with the shelf) to bind the camera to the shelf corresponding to the binary code, thereby automatically and efficiently completing the automatic binding of the shelf camera to the shelf without manual intervention.

[0137] An embodiment of the present invention further provides a computer device, Figure 8 This is a schematic diagram of a computer device in an embodiment of the present invention. The computer device 800 includes a memory 810, a processor 820, and a computer program 830 stored in the memory 810 and executable on the processor 820. When the processor 820 executes the computer program 830, the method of binding a shelf camera to a shelf is implemented.

[0138] An embodiment of the present invention further provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the method of binding a shelf camera to a shelf is implemented.

[0139] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the above-mentioned method of binding shelf cameras to shelves.

[0140] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0141] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0142] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0143] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0144] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for binding a shelf camera to a shelf, characterized in that: include: Obtaining electronic price tags at the edge of the shelf based on the relationship between the electronic price tags and the shelf, and determining a first color category bound to each electronic price tag at the edge of the shelf, where the first color category includes at least one randomly selected color; Selecting an electronic price tag for binding from the electronic price tags other than the electronic price tags at the edge of the shelf, binary-coding the flashing light color of the selected electronic price tag for binding based on a second type of color, and determining a correspondence between the binary code and the shelf, wherein the second type of color is a color other than the first type of color; At a preset time point, a flashing instruction is sent to the electronic price tags at the edge of the shelf and the electronic price tags used for binding, so that the electronic price tags at the edge of the shelf flash according to the first color of the binding electronic price tags at the edge of the shelf in the flashing instruction, and the electronic price tags used for binding flash according to the order in the binary code in the flashing instruction; Send shooting instructions to all cameras in the store so that all cameras can shoot shelves according to the shooting instructions, and receive shooting results from all cameras; Identify the shooting results of each camera, determine the edge of each shelf based on the first type of color electronic price tags identified from the shooting results, and use the area formed within the edge of each shelf as the area of ​​interest of each camera; For each camera, the binary code corresponding to the flashing color of the electronic price tag used for binding in each area of ​​interest is identified from the shooting results, and the camera is bound to the shelf corresponding to the binary code.

2. The method according to claim 1, wherein Determine the first color of each electronic shelf label binding at the shelf edge, including: Determine the first color bound to all electronic price tags on the left edge of the shelf among the electronic price tags on the edge of the shelf; Determine the first color bound to all electronic price tags on the right edge of the shelf among the electronic price tags on the shelf edge, wherein the first color bound to the electronic price tags on the left edge of the shelf is different from the first color bound to the electronic price tags on the right edge of the shelf.

3. The method according to claim 1, wherein Select the electronic price tags for binding from the electronic price tags other than the electronic price tags at the edge of the shelf, and binary-code the flashing colors of the selected electronic price tags for binding based on the second type of color, including: Selecting a preset number of electronic price tags for binding from the electronic price tags other than the electronic price tags at the edge of the shelf in a preset spatial order; Represent the binary coded 0 with the first second color; The binary coded 1 is represented by the second second color; The flashing color of each electronic price tag used for binding is determined to be the first second-category color or the second second-category color, and a binary code formed by the second-category color of the electronic price tag used for binding is obtained, where the length of the binary code is the length of a preset number.

4. The method according to claim 1, wherein Select the electronic price tags for binding from the electronic price tags other than the electronic price tags at the edge of the shelf, and binary-code the flashing colors of the selected electronic price tags for binding based on the second type of color, including: Selecting at least one electronic price tag at the center of the shelf as the electronic price tag for binding; Select the third second-category color as the initial light color of the electronic price tag used for binding; The sequence of the flashing light colors of the electronic price tag used for binding is binary-encoded by the first second-category color and the second second-category color.

5. The method according to claim 1, wherein Also includes: If multiple cameras recognize the same binary code, analyze the positions of the shelves corresponding to the binary code in the shooting results of different cameras, and bind the camera corresponding to the shooting result closest to the center of the shooting result to the shelf corresponding to the binary code.

6. The method according to claim 1, wherein Also includes: After the new camera is installed and deployed in the store, a set of products with a preset number of built-in confidence values ​​greater than a confidence threshold in the new camera's field of view is obtained; Obtaining a set of electronic price tags corresponding to the set of goods; Bind the new camera to the shelf where the electronic shelf tag is located in the electronic shelf tag collection.

7. The method according to claim 1, wherein Also includes: After the new camera is installed and deployed in the store, a set of products with a preset number of built-in confidence values ​​greater than a confidence threshold in the new camera's field of view is obtained; At a preset time point, a flashing instruction is sent to the electronic price tag set corresponding to the product set and the electronic price tags at the edge of the shelf where the electronic price tags in the electronic price tag set are located, so that the electronic price tags at the edge of the shelf flash according to the first type of color bound to the electronic price tags at the edge of the shelf in the flashing instruction, and the electronic price tag set corresponding to the product set flashes according to the order in the binary code in the flashing instruction; Sending a shooting instruction to the new camera so that the new camera can shoot the shelf according to the shooting instruction, and receiving the shooting result fed back by the new camera; Identify the shooting results of the new camera, determine the edge of each shelf based on the electronic price tags of the first color identified from the shooting results, and use the area formed within the edge of each shelf as the area of ​​interest of the new camera; Identify the binary code corresponding to the flashing color of the electronic price tag corresponding to the set of products in each area of ​​interest from the shooting results, and bind the new camera to the shelf corresponding to the binary code.

8. A device for binding a shelf camera to a shelf, characterized in that: include: a shelf edge color determination module, configured to obtain the electronic price tags at the shelf edge based on the ownership relationship between the electronic price tags and the shelf, and determine a first color category bound to each electronic price tag at the shelf edge, wherein the first color category includes at least one randomly selected color; a binary encoding module, configured to select an electronic price tag for binding from electronic price tags other than those on the edge of the shelf, binary encode the flashing color of the selected electronic price tag for binding based on a second type of color, and determine a correspondence between the binary code and the shelf, wherein the second type of color is a color other than the first type of color; A flashing module is configured to send a flashing instruction to the electronic price tags at the edge of the shelf and the electronic price tags used for binding at a preset time point, so that the electronic price tags at the edge of the shelf flash according to the first color of the electronic price tags at the edge of the shelf bound to the electronic price tags in the flashing instruction, and the electronic price tags used for binding flash according to the order in the binary code in the flashing instruction; The shooting module is used to send shooting instructions to all cameras in the store so that all cameras can shoot shelves according to the shooting instructions, and receive the shooting results fed back by all cameras; A region of interest recognition module is used to recognize the shooting results of each camera, determine the edge of each shelf based on the electronic price tags of the first color identified from the shooting results, and use the area formed within each shelf edge as the region of interest of each camera; The binding module is used to identify the binary code corresponding to the flashing color of the electronic price tag used for binding in each area of ​​interest from the shooting results for each camera, and bind the camera to the shelf corresponding to the binary code.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

11. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images