A logistics lighting control method and system based on image recognition

Abstract

The present invention relates to the technical field of logistics sorting, and provides a logistics lighting control method and system based on image recognition, the method comprising: obtaining storage area images before and after the sorting personnel pick up the goods, segmenting the two images according to the lighting positions, and performing image comparison to determine whether the items to be picked are correctly picked up by the sorting personnel, avoiding the lights going out due to missed picking or wrong picking during the picking process of the indicator light, increasing the accuracy of the indicator light indication, reducing the sorting problems caused by lighting errors, and improving the efficiency of material sorting.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics sorting, and in particular to a logistics lighting control method and system based on image recognition. Background Art

[0002] In logistics sorting, picking is guided by light through a light picking system, which enables sorting personnel to quickly locate goods and reduces the time for searching and confirming. However, the indicator light must be turned off manually after picking. During the long and rapid sorting process, personnel are prone to sorting confusion, wrong picking or missing items, which may result in hitting the wrong indicator light and lead to sorting errors. Summary of the invention

[0003] The present invention provides a logistics lighting control method based on image recognition, which is used to solve the problem in the prior art that manual lighting off is prone to errors leading to sorting errors.

[0004] The first aspect of the present invention provides a logistics lighting control method based on image recognition, comprising:

[0005] Receive a light-on signal, obtain a first image of the storage area, and identify the to-be-picked area corresponding to the light-on area; perform image segmentation on the image to obtain multiple to-be-picked area images, and identify corresponding barcode data in each to-be-picked area image;

[0006] Receive the human body passing signal, obtain the second image of the storage area, and identify the picked area corresponding to the lighted area; perform image segmentation on the image to obtain the picked area image, identify the barcode data in the picked area image, and identify the corresponding to-be-picked area image based on the barcode data;

[0007] The image of the picked area is compared with the corresponding image of the to-be-picked area for image similarity. If the similarity is less than a preset threshold, a light-off signal is sent according to the indicator light corresponding to the barcode data in the image.

[0008] Optionally, before receiving the light-on signal, the method further includes:

[0009] Obtain the orders to be sorted, merge the orders to be sorted, and obtain the quantity of each item to be picked; identify the corresponding compartment number according to the information of the items to be picked, and send a lighting command signal to the LED indicator.

[0010] Optionally, if the similarity is less than a preset threshold, sending a light-off signal according to the indicator light corresponding to the barcode data in the image specifically includes:

[0011] Based on the preset machine vision model, the quantity of goods in the image of the to-be-picked area and the corresponding image of the picked area are identified, and the number of picked goods is calculated; the number of picked goods is compared with the number of items to be picked in the corresponding compartment to determine whether they are picked correctly. If not, a prompt will be issued to the sorting personnel.

[0012] Optionally, the identification of the to-be-picked area corresponding to the lighted area, performing image segmentation on the image, and obtaining multiple to-be-picked area images are specifically:

[0013] The first image of the storage area is gray-processed, the pixel area with gray-scale values ​​greater than the gray-scale threshold is identified, and the coordinates of the center point of the indicator light are calculated in the pixel area; a to-be-picked area division model is set according to the shelf structure, a segmentation frame is set based on the coordinates of the center point of the indicator light, and the image is segmented according to the segmentation frame to obtain multiple to-be-picked area images.

[0014] The second aspect of the present application provides a logistics lighting control system based on image recognition, comprising:

[0015] The to-be-picked image processing module is used to receive the light-on signal, obtain the first image of the storage area, and identify the to-be-picked area corresponding to the light-on area; perform image segmentation on the image to obtain multiple to-be-picked area images, and identify the corresponding barcode data in each to-be-picked area image;

[0016] The picked image processing module is used to receive the human body passing signal, obtain the second image of the storage area, and identify the picked area corresponding to the lighted area; perform image segmentation on the image to obtain the picked area image, identify the barcode data in the picked area image, and identify the corresponding to-be-picked area image according to the barcode data;

[0017] The lighting control module is used to compare the image of the picked area with the corresponding image of the to-be-picked area for image similarity. If the similarity is less than a preset threshold, a light-off signal is sent according to the indicator light corresponding to the barcode data in the image.

[0018] Optionally, the to-be-picked image processing module, before receiving the light-on signal, further includes:

[0019] Obtain the orders to be sorted, merge the orders to be sorted, and obtain the quantity of each item to be picked; identify the corresponding compartment number according to the information of the items to be picked, and send a lighting command signal to the LED indicator.

[0020] Optionally, in the lighting control module, if the similarity is less than a preset threshold, a light-off signal is sent according to the indicator light corresponding to the barcode data in the image, specifically including:

[0021] Based on the preset machine vision model, the quantity of goods in the image of the to-be-picked area and the corresponding image of the picked area are identified, and the number of picked goods is calculated; the number of picked goods is compared with the number of items to be picked in the corresponding compartment to determine whether they are picked correctly. If not, a prompt will be issued to the sorting personnel.

[0022] Optionally, in the to-be-picked image processing module, the to-be-picked area corresponding to the lighted area is identified, and the image is segmented to obtain multiple to-be-picked area images, specifically:

[0023] The first image of the storage area is gray-processed, the pixel area with gray-scale values ​​greater than the gray-scale threshold is identified, and the coordinates of the center point of the indicator light are calculated in the pixel area; a to-be-picked area division model is set according to the shelf structure, a segmentation frame is set based on the coordinates of the center point of the indicator light, and the image is segmented according to the segmentation frame to obtain multiple to-be-picked area images.

[0024] The third aspect of the present application provides a logistics lighting control method and device based on image recognition, the device comprising a processor and a memory:

[0025] The memory is used to store program code and transmit the program code to the processor;

[0026] The processor is used to execute a logistics lighting control method based on image recognition according to the instructions in the program code as described in any one of the first aspects of the present invention.

[0027] A fourth aspect of the present application provides a computer-readable storage medium, which is used to store program code, and the program code is used to execute a logistics lighting control method based on image recognition as described in any one of the first aspects of the present invention.

[0028] It can be seen from the above technical scheme that the present invention has the following advantages: by acquiring images of the storage area before and after the sorting personnel pick up the goods, the two images are segmented according to the light positions, and the images are compared to determine whether the items to be picked are correctly picked up by the sorting personnel, thereby avoiding the lights going out due to missed picking or wrong picking during the indicator light picking process, increasing the accuracy of the indicator light indication, reducing the sorting problems caused by light-on errors, and improving the efficiency of material sorting. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0030] Figure 1 This is a flow chart of a logistics lighting control method based on image recognition;

[0031] Figure 2 This is a structural diagram of a logistics lighting control system based on image recognition. DETAILED DESCRIPTION

[0032] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] The present invention provides a logistics lighting control method based on image recognition, which is used to solve the problem in the prior art that manual lighting off is prone to errors leading to sorting errors.

[0034] See also Figure 1 , Figure 1 The first flowchart of a logistics lighting control method based on image recognition provided by an embodiment of the present invention.

[0035] S100, receiving a light-on signal, acquiring a first image of the storage area, and identifying the to-be-picked area corresponding to the light-on area; performing image segmentation on the image to obtain a plurality of to-be-picked area images, and identifying corresponding barcode data in each to-be-picked area image;

[0036] It should be noted that in warehousing logistics, after obtaining the sorting list, each item to be picked in the list will be identified, the area where each item to be picked is located will be determined, and a light signal will be sent to the LED light in the area to instruct the warehouse pickers to pick the goods accurately; after the indicator light is on, the pickers have not yet entered the site, and the image of the storage area can be obtained at this time. The storage area has multiple shelves, each shelf is layered into multiple compartments, and each compartment of the shelf is affixed with a barcode, and different goods are placed in each compartment according to category; the barcode can be a barcode or a QR code, and the barcode can be read through the image to obtain the goods information of the compartment, as well as the compartment number, etc.;

[0037] After receiving the light-on signal, the storage area is photographed. Each camera can capture images of multiple compartments. Multiple cameras can overlap to ensure that each compartment can be photographed. The lighting in the storage area is uniform. The average brightness of the image pixels is uniform when the lights are not on. After the LED lights are on, the image will have a higher grayscale value at the light source due to the brightness. The LED lights are set at fixed positions between each compartment, and each LED light corresponds to a compartment. Therefore, after the LED lights are identified, the area to be picked can be identified at the corresponding position and divided. The image is segmented according to the identified and divided area to be picked, and the image of the non-picking area without lights is eliminated. Only the image of the area to be picked is analyzed. The number of images of the area to be picked will be the number of LED lights that are on.

[0038] S200, receiving a human body passing signal, acquiring a second image of the storage area, and identifying the picked area corresponding to the lighted area; performing image segmentation on the image to obtain an image of the picked area, identifying barcode data in the image of the picked area, and identifying the corresponding image of the area to be picked according to the barcode data;

[0039] It should be noted that an infrared probe can be set up in the storage area to detect the passage of human bodies. For human body detection in different storage areas captured by the camera, for example, when human body signals are detected twice in the area, it can be determined that the picker has entered and then left the current area, and a human body passing signal is sent to the lighting control processing terminal; after receiving the human body passing signal, it can be regarded that the picker in the photographed storage area has completed picking according to the lighting indication of the LED. At this time, the storage area should be in a picked-up posture. After the person leaves the current area, a second image of the storage area is captured again. The second image of the storage area is shot at the same angle and shelf compartment as the first image of the storage area. When the goods stored in the compartment have been picked; based on the same recognition and division method as the aforementioned step S100, multiple picked area images are obtained, and the image also has a barcode of each compartment. According to the compartment number or cargo information read in the barcode, the picked area image and the to-be-picked area image of the same compartment are matched.

[0040] S300, performing image similarity comparison between the image of the picked area and the corresponding image of the to-be-picked area. If the similarity is less than a preset threshold, a light-off signal is sent according to the indicator light corresponding to the barcode data in the image.

[0041] It should be noted that the image similarity comparison can use the image grayscale histogram for similarity comparison and calculate the distance between the two images. The hash algorithm can also be used to calculate the hash representation of the image and then use the Hamming distance to calculate the similarity of the two images. If the distance is greater than the preset threshold, it means that the similarity is small. If the corresponding similarity is less than the preset threshold, it means that there is a large change in the goods in the compartment. The picker has completed picking the goods and can turn off the light. The barcode data in the image corresponds to the shelf compartment number, and a light-off command signal is sent to the corresponding LED indicator to complete the light turning off. If the similarity is greater than the preset threshold, it means that the goods in the corresponding compartment have not been picked up, and there may be missed picking or wrong picking. The indicator light still needs to be on, or change color and flash, to further prompt the sorting personnel to pick up.

[0042] In this embodiment, by acquiring images of the storage area before and after the sorting personnel pick up the goods, the two images are segmented according to the positions of the lights on, and image comparison is performed to determine whether the items to be picked are correctly picked up by the sorting personnel, thereby avoiding the lights going out due to missed or wrong picks during the picking process of the indicator light, increasing the accuracy of the indicator light indication, reducing sorting problems caused by lighting errors, and improving the efficiency of material sorting.

[0043] The above is a detailed description of the first embodiment of a logistics lighting control method based on image recognition provided by the present application. The following is a detailed description of the second embodiment of a logistics lighting control method based on image recognition provided by the present application.

[0044] In this embodiment, a logistics lighting control method based on image recognition is further provided.

[0045] In the aforementioned step S100, before receiving the light-on signal, the method further includes:

[0046] Obtain the orders to be sorted, merge the orders to be sorted, and obtain the quantity of each item to be picked; identify the corresponding compartment number according to the information of the items to be picked, and send a lighting command signal to the LED indicator;

[0047] It should be noted that the logistics distribution center produces orders to be sorted according to the customer's order requirements or distribution plan, but some categories of orders have few and miscellaneous items. If sorting is performed according to the order, it is necessary to go back and forth to the warehouse many times, which consumes a lot of logistics time on the road. Therefore, the secondary sorting method of "first merge and then divide" is adopted. First, multiple sorting orders that meet the merging requirements are merged, and multiple similar items are taken at one time to improve the sorting efficiency. After the items are merged and picked out from the storage area, they are classified according to the order, and the operation process is centralized. After the orders are merged, the corresponding storage compartment number can be determined according to the information of each item to be picked, and the corresponding LED indicator light can be found according to the number, and a lighting command signal is sent to light up the corresponding compartment to instruct the sorting personnel to find the goods.

[0048] Furthermore, in the aforementioned step S300, if the similarity is less than a preset threshold, sending a light-off signal according to the indicator light corresponding to the barcode data in the image specifically includes:

[0049] Based on the preset machine vision model, the quantity of goods in the image of the to-be-picked area and the corresponding image of the picked area is identified, and the quantity of picked goods is calculated; the quantity of picked goods is compared with the quantity of to-be-picked items in the corresponding compartment to determine whether they are picked correctly, and if not, a prompt is issued to the sorting personnel;

[0050] It should be noted that, at present, multiple identical items will be picked up in the compartment during the second sorting. The sorting personnel will sort according to the mobile order records at hand, which may lead to missed picking or wrong picking. Setting up grating detection is not only costly but also complicated in routing, affecting the safety of the storage area. The machine vision model can be trained in advance according to the items stored in the storage area, and the quantity can be identified in the corresponding to-be-picked area image and the picked area image to obtain the quantity of goods in the to-be-picked area and the quantity of goods in the picked area. The difference between the two quantities is the quantity of picked goods. The quantity of goods in the compartment picked by the sorting personnel is analyzed and compared with the quantity of to-be-picked goods in the corresponding merged order. If they are consistent, it means that the sorting personnel has picked the goods correctly and the LED indicator light can be turned off. However, if they are inconsistent, re-sorting is required. A flashing signal can be sent to the LED indicator light for warning, or an error prompt can be sent to the mobile terminal of the sorting personnel to let the sorting personnel find the flashing LED indicator light for re-sorting.

[0051] Furthermore, in the aforementioned step S100, the to-be-picked area corresponding to the lighted area is identified, and the image is segmented to obtain multiple to-be-picked area images, specifically:

[0052] Grayscale processing is performed on the first image of the storage area to identify pixel areas whose grayscale values ​​are greater than the grayscale threshold, and the coordinates of the center point of the indicator light are calculated in the pixel area; a segmentation frame is set based on the coordinates of the center point of the indicator light according to the to-be-picked area division model set according to the shelf structure, and the image is segmented according to the segmentation frame to obtain multiple to-be-picked area images;

[0053] It should be noted that the ambient lighting in the storage area is uniform, and the LED indicator light will be very obvious when it is on, and the brightness is much higher than the environment; after the grayscale processing of the first image of the storage area, the grayscale value of the area with high brightness is high, and the grayscale value of the area with low brightness is low. The grayscale threshold can be set based on the experience value to identify the pixels greater than the grayscale threshold. The LED indicator light corresponds to an area, so multiple pixels with grayscale values ​​greater than the grayscale threshold will be identified, and the LED indicator light is distributed discretely, corresponding to multiple pixel point areas; the LED indicator light is generally circular or rectangular, and the corresponding pixel point area with grayscale values ​​greater than the grayscale threshold is also the same shape, so the coordinates of the center point of the indicator light can be found according to the regional centroid of the pixel point area, and the coordinates of the center point reflect the position of the LED indicator light;

[0054] Each compartment on the shelf will be equipped with an LED indicator light, and the LED indicator light is generally set on the partition of the corresponding compartment. It can be set on any side of the compartment as needed, but in order to facilitate the sorting personnel to identify the compartment corresponding to the lit LED indicator light, the LED indicator light setting method should be consistent. For example, in a certain storage area, the LED indicator light is set on the lower partition of each compartment, and the size of the segmentation frame is preset based on the size of the compartment. After the center point coordinates of the LED indicator light are identified, because the LED indicator light is below the compartment, a segmentation frame is set at a fixed position above the center point. Each indicator light center point coordinate corresponds to a segmentation frame, and the relative position between the center point coordinates and the segmentation frame is fixed. Then, the image can be segmented according to each positioned segmentation frame to obtain multiple images of the area to be picked, and each segmentation frame contains the placement image of the goods in each compartment.

[0055] The above is a detailed description of a logistics lighting control method based on image recognition according to the first aspect of the present application. The following is a detailed description of an embodiment of a logistics lighting control system based on image recognition according to the second aspect of the present application.

[0056] See also Figure 2 , Figure 2 This is a structural diagram of a logistics lighting control system based on image recognition. This embodiment provides a logistics lighting control system based on image recognition, including:

[0057] The to-be-picked image processing module 10 is used to receive the light-on signal, obtain the first image of the storage area, and identify the to-be-picked area corresponding to the light-on area; perform image segmentation on the image to obtain multiple to-be-picked area images, and identify the corresponding barcode data in each to-be-picked area image;

[0058] The picked image processing module 20 is used to receive a human body passing signal, obtain a second image of the storage area, and identify the picked area corresponding to the lighted area; perform image segmentation on the image to obtain a picked area image, identify the barcode data in the picked area image, and identify the corresponding to-be-picked area image according to the barcode data;

[0059] The lighting control module 30 is used to compare the image of the picked area with the corresponding image of the to-be-picked area for image similarity. If the similarity is less than a preset threshold, a light-off signal is sent according to the indicator light corresponding to the barcode data in the image.

[0060] Furthermore, the to-be-picked image processing module 10, before receiving the light-on signal, further includes:

[0061] Obtain the orders to be sorted, merge the orders to be sorted, and obtain the quantity of each item to be picked; identify the corresponding compartment number according to the information of the items to be picked, and send a lighting command signal to the LED indicator.

[0062] Furthermore, in the lighting control module 30, if the similarity is less than a preset threshold, a light-off signal is sent according to the indicator light corresponding to the barcode data in the image, which specifically includes:

[0063] Based on the preset machine vision model, the quantity of goods in the image of the to-be-picked area and the corresponding image of the picked area are identified, and the number of picked goods is calculated; the number of picked goods is compared with the number of items to be picked in the corresponding compartment to determine whether they are picked correctly. If not, a prompt will be issued to the sorting personnel.

[0064] Furthermore, in the to-be-picked image processing module 10, the to-be-picked area corresponding to the lighted area is identified, and the image is segmented to obtain multiple to-be-picked area images, specifically:

[0065] The first image of the storage area is gray-processed, the pixel area with gray-scale values ​​greater than the gray-scale threshold is identified, and the coordinates of the center point of the indicator light are calculated in the pixel area; a to-be-picked area division model is set according to the shelf structure, a segmentation frame is set based on the coordinates of the center point of the indicator light, and the image is segmented according to the segmentation frame to obtain multiple to-be-picked area images.

[0066] The third aspect of the present application also provides a logistics lighting control method device based on image recognition, including a processor and a memory: the memory is used to store program code and transfer the program code to the processor; the processor is used to execute the above-mentioned logistics lighting control method based on image recognition according to the instructions in the program code.

[0067] A fourth aspect of the present application provides a computer-readable storage medium, characterized in that the computer-readable storage medium is used to store program code, and the program code is used to execute the above-mentioned logistics lighting control method based on image recognition.

[0068] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and equipment can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0069] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0070] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0071] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0072] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0073] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A logistics lighting control method based on image recognition, characterized in that include: Receive the light-on signal, obtain the first image of the storage area, and identify the area to be picked corresponding to the light-on area; Performing image segmentation on the image to obtain a plurality of to-be-picked area images, and identifying corresponding barcode data in each to-be-picked area image, wherein the barcode is affixed to each compartment of the shelf; Receive the human body passing signal, obtain the second image of the storage area, and identify the picked area corresponding to the lighted area; perform image segmentation on the image to obtain the picked area image, identify the barcode data in the picked area image, and identify the corresponding to-be-picked area image based on the barcode data; The image of the picked area is compared with the corresponding image of the to-be-picked area for image similarity. If the similarity is less than a preset threshold, a light-off signal is sent according to the indicator light corresponding to the barcode data in the image.

2. According to the method of controlling logistics lighting based on image recognition according to claim 1, it is characterized in that: Before receiving the light-on signal, the method further comprises: Obtain the orders to be sorted, merge the orders to be sorted, and obtain the quantity of each item to be picked; identify the corresponding compartment number according to the information of the items to be picked, and send a lighting command signal to the LED indicator.

3. According to claim 2, a logistics lighting control method based on image recognition is characterized in that: If the similarity is less than a preset threshold, a light-off signal is sent according to the indicator light corresponding to the barcode data in the image, which specifically includes: Based on the preset machine vision model, the quantity of goods in the image of the to-be-picked area and the corresponding image of the picked area are identified, and the number of picked goods is calculated; the number of picked goods is compared with the number of items to be picked in the corresponding compartment to determine whether they are picked correctly. If not, a prompt will be issued to the sorting personnel.

4. According to the method of controlling logistics lighting based on image recognition according to claim 1, it is characterized in that: The identification of the to-be-picked area corresponding to the lighted area, and the image segmentation to obtain multiple to-be-picked area images are specifically as follows: The first image of the storage area is gray-processed, the pixel area with gray-scale values ​​greater than the gray-scale threshold is identified, and the coordinates of the center point of the indicator light are calculated in the pixel area; a to-be-picked area division model is set according to the shelf structure, a segmentation frame is set based on the coordinates of the center point of the indicator light, and the image is segmented according to the segmentation frame to obtain multiple to-be-picked area images.

5. A logistics lighting control system based on image recognition, characterized in that: include: The to-be-picked image processing module is used to receive the light-on signal, obtain the first image of the storage area, and identify the to-be-picked area corresponding to the light-on area; Performing image segmentation on the image to obtain a plurality of to-be-picked area images, and identifying corresponding barcode data in each to-be-picked area image, wherein the barcode is affixed to each compartment of the shelf; The picked image processing module is used to receive the human body passing signal, obtain the second image of the storage area, and identify the picked area corresponding to the lighted area; perform image segmentation on the image to obtain the picked area image, identify the barcode data in the picked area image, and identify the corresponding to-be-picked area image according to the barcode data; The lighting control module is used to compare the image of the picked area with the corresponding image of the to-be-picked area for image similarity. If the similarity is less than a preset threshold, a light-off signal is sent according to the indicator light corresponding to the barcode data in the image.

6. The logistics lighting control system based on image recognition according to claim 5 is characterized in that: The to-be-picked image processing module, before receiving the light-on signal, also includes: Obtain the orders to be sorted, merge the orders to be sorted, and obtain the quantity of each item to be picked; identify the corresponding compartment number according to the information of the items to be picked, and send a lighting command signal to the LED indicator.

7. The logistics lighting control system based on image recognition according to claim 6 is characterized in that: In the lighting control module, if the similarity is less than a preset threshold, a light-off signal is sent according to the indicator light corresponding to the barcode data in the image, which specifically includes: Based on the preset machine vision model, the quantity of goods in the image of the to-be-picked area and the corresponding image of the picked area are identified, and the number of picked goods is calculated; the number of picked goods is compared with the number of items to be picked in the corresponding compartment to determine whether they are picked correctly. If not, a prompt will be issued to the sorting personnel.

8. The logistics lighting control system based on image recognition according to claim 5 is characterized in that: In the to-be-picked image processing module, the to-be-picked area corresponding to the lighted area is identified, and the image is segmented to obtain multiple to-be-picked area images, specifically: The first image of the storage area is gray-processed, the pixel area with gray-scale values ​​greater than the gray-scale threshold is identified, and the coordinates of the center point of the indicator light are calculated in the pixel area; a to-be-picked area division model is set according to the shelf structure, a segmentation frame is set based on the coordinates of the center point of the indicator light, and the image is segmented according to the segmentation frame to obtain multiple to-be-picked area images.

9. A logistics lighting control device based on image recognition, characterized in that: The device comprises a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is used to execute a logistics lighting control method based on image recognition as described in any one of claims 1 to 4 according to the instructions in the program code.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store program code, and the program code is used to execute the logistics lighting control method based on image recognition as described in any one of claims 1-4.

Images