Logistics tracking system and method

Abstract

The invention provides a logistics tracking system and method, and the method comprises the steps: carrying out the edge detection and filtering of a bar code collection image through a logistics tracking edge device, and obtaining a bar code enhanced image; performing bar code reference separation on the bar code acquisition image to obtain a plurality of bar code reset reference sub-images; determining a reference confidence coefficient weight corresponding to the bar code reset reference sub-graph according to a reference contrast ratio and a reference orientation factor corresponding to the bar code reset reference sub-graph; performing reset fusion on the reset rotation features corresponding to the reset reference sub-graphs of the barcodes to obtain reference reset angles of the barcodes; and finally, resetting and detecting the bar code enhanced image according to the reference reset angle, and sending a detection result to the cloud. According to the application, the logistics tracking bar code can be accurately reset when the reference object to which the logistics tracking bar code is attached generates distortion, and the identification rate of the logistics tracking bar code is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of logistics tracking, and more particularly, to a logistics tracking system and method, such as a terminal device, a chip, a computer storage medium, etc. BACKGROUND

[0002] In a logistics tracking system, a barcode is an important information tracking carrier and a core link connecting physical goods and a digital management system, which solves the core problems of asynchronization between goods and information and low efficiency and error-prone manual recording in logistics, greatly improving the efficiency and accuracy of logistics processing. However, with the continuous complication of application scenarios, the logistics tracking barcode detection technology in the logistics tracking system is facing unprecedented challenges.

[0003] Generally, the barcode detection technology for logistics tracking is often to identify the logistics tracking barcode area, and then rotate and reset the barcode according to the rectangularity or deflection angle of the barcode and identify it. This way does not take into account the distortion influence of the reference object attached to the barcode on the barcode. When the object attached to the barcode has defects or large distortion, there is a great difficulty in detecting the barcode due to the lack of background, which easily makes the logistics tracking barcode detection time too long or unable to be detected, greatly restricting the expansion application of the logistics tracking barcode. SUMMARY

[0004] The present application provides a logistics tracking system and method to solve the technical problem of great difficulty in resetting the logistics tracking barcode when the reference object attached to the logistics tracking barcode is distorted.

[0005] In a first aspect, the present application provides a reset detection method for a logistics tracking barcode, applied to a logistics tracking system, wherein the logistics tracking system adopts a cloud-edge collaborative architecture including a logistics tracking edge device and a cloud end.

[0006] Specifically, the method comprises: starting logistics tracking barcode reset detection by the logistics tracking edge device, and acquiring a barcode collection image; performing edge detection and filtering on the barcode collection image to obtain a barcode enhanced image; performing barcode reference separation on the barcode collection image to obtain a plurality of barcode reset reference subgraphs; for any one barcode reset reference subgraph, determining the reference contrast and reference orientation factor corresponding to the barcode reset reference subgraph, and then determining the reference confidence weight corresponding to the barcode reset reference subgraph according to the reference contrast and reference orientation factor corresponding to the barcode reset reference subgraph; determine a reset rotation feature corresponding to each barcode reset reference subgraph, reset fuse the reset rotation features corresponding to each barcode reset reference subgraph according to the reference confidence weight corresponding to each barcode reset reference subgraph, and obtain a reference reset angle of the barcode; reset the barcode enhanced image according to the reference reset angle and perform detection, and send the detection result to the cloud.

[0007] In combination with the first aspect, in some implementations of the first aspect, the edge detection and filtering of the barcode acquisition image to obtain the barcode enhanced image specifically includes: performing gray scale binarization processing on the barcode acquisition image to obtain a barcode black and white image; performing contour extraction on the barcode black and white image to obtain barcode contour features, and performing region segmentation and filtering on the barcode acquisition image according to the barcode contour features to obtain the barcode enhanced image.

[0008] In combination with the first aspect, in some implementations of the first aspect, the barcode reference separation of the barcode acquisition image to obtain a plurality of barcode reset reference subgraphs specifically includes: performing reference background recognition on the barcode acquisition image to obtain a plurality of reference background edge points; grouping according to the positional relationship of the plurality of reference background edge points to obtain a plurality of reference background edge groups; for any one reference background edge group, performing background segmentation according to all reference background edge points in the reference background edge group to obtain one barcode reset reference subgraph, and then obtaining a plurality of barcode reset reference subgraphs in the same way.

[0009] In combination with the first aspect, in some implementations of the first aspect, determining the reference contrast corresponding to the barcode reset reference subgraph specifically includes: obtaining a barcode enhanced image; obtaining edge feature points of the barcode reset reference subgraph and edge feature points of the barcode enhanced image; determining a reference repeated area of the barcode reset reference subgraph according to the edge feature points of the barcode reset reference subgraph and the edge feature points of the barcode enhanced image; determining the reference contrast corresponding to the barcode reset reference subgraph according to the reference repeated area.

[0010] In combination with the first aspect, in some implementations of the first aspect, determining the reference orientation factor corresponding to the barcode reset reference subgraph specifically includes: obtaining a barcode enhanced image; obtaining the centroid coordinates of the barcode reset reference subgraph, and obtaining the centroid coordinates of the barcode enhanced image; According to the centroid coordinates of the barcode reset reference subgraph and the centroid coordinates of the barcode enhanced image, the reference orientation factor corresponding to the barcode reset reference subgraph is determined.

[0011] In combination with the first aspect, in some implementations of the first aspect, determining the reset rotation feature corresponding to each barcode reset reference subgraph specifically includes: For any barcode reset reference subgraph, the edge feature point of the barcode reset reference subgraph is determined, and the reset rotation feature of the barcode reset reference subgraph is determined according to the edge feature point of the barcode reset reference subgraph. Further, the reset rotation feature corresponding to each barcode reset reference subgraph is determined by using the same steps.

[0012] In combination with the first aspect, in some implementations of the first aspect, a high-definition camera is used to collect a region image of a region where the barcode is located, to obtain the barcode collection image.

[0013] Secondly, the present application provides a logistics tracking system, which adopts a cloud-edge collaborative architecture including a logistics tracking edge device and a cloud end, wherein the logistics tracking edge device includes a logistics tracking barcode reset detection unit, and the logistics tracking barcode reset detection unit includes: The barcode collection module is configured to start the logistics tracking barcode reset detection and obtain a barcode collection image. The processing module is configured to perform edge detection and filtering on the barcode collection image to obtain a barcode enhanced image. The processing module is further configured to perform barcode reference separation on the barcode collection image to obtain a plurality of barcode reset reference subgraphs. The processing module is further configured to determine, for any barcode reset reference subgraph, the reference contrast and the reference orientation factor corresponding to the barcode reset reference subgraph, and further determine the reference confidence weight corresponding to the barcode reset reference subgraph according to the reference contrast and the reference orientation factor corresponding to the barcode reset reference subgraph. The processing module is further configured to determine the reset rotation feature corresponding to each barcode reset reference subgraph, to perform reset fusion on the reset rotation feature corresponding to each barcode reset reference subgraph according to the reference confidence weight corresponding to each barcode reset reference subgraph, and to obtain a reference reset angle of the barcode. The reset detection module is configured to reset and detect the barcode enhanced image according to the reference reset angle, and to send the detection result to the cloud end.

[0014] In a third aspect, the present application provides a computer terminal device, comprising a memory and a processor, the memory stores a code, and the processor is configured to acquire the code and execute the reset detection method of the logistics tracking barcode.

[0015] In a fourth aspect, the present application provides a computer readable storage medium, which stores at least one computer program, the computer program is loaded and executed by a processor to implement the operations performed by the reset detection method of the logistics tracking barcode.

[0016] The technical scheme provided by the embodiments of the present application has the following beneficial effects: In the logistics tracking system and method provided by the present application, first, the logistics tracking edge device starts the logistics tracking barcode reset detection and acquires the barcode collection image; the barcode collection image is subjected to edge detection and filtering to obtain a barcode enhanced image; the barcode collection image is subjected to barcode reference separation to obtain a plurality of barcode reset reference subgraphs, each of which contains a barcode and a separate layer of reference background, providing different reference angles and contrasts; for any one barcode reset reference subgraph, the reference contrast and the reference orientation factor corresponding to the barcode reset reference subgraph are determined, and then the reference confidence weight corresponding to the barcode reset reference subgraph is determined according to the reference contrast and the reference orientation factor corresponding to the barcode reset reference subgraph, the reference contrast and the orientation factor of the reference in each subgraph are quantified to affect the barcode position and angle, so as to accurately determine the actual rotation state of the barcode; the reset rotation features corresponding to each barcode reset reference subgraph are determined, the reset rotation features corresponding to each barcode reset reference subgraph are fused according to the reference confidence weight corresponding to each barcode reset reference subgraph, and the reference reset angle of the barcode is obtained, so as to reduce the error possibly caused by a single reference, and when the reference attached to the barcode is distorted, the actual angle of the barcode can still be accurately determined; finally, the barcode enhanced image is reset and detected according to the reference reset angle, and the detection result is sent to the cloud. In summary, by determining the reference confidence weight of the plurality of references attached to the logistics tracking barcode and resetting and detecting the barcode enhanced image according to the image features of the references, the logistics tracking barcode can be accurately reset when the references attached to the logistics tracking barcode are distorted, and the recognition rate of the logistics tracking barcode is improved. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 is an exemplary flowchart of a reset detection method of a logistics tracking barcode according to some embodiments of the present application; Figure 2is a structural schematic diagram of a logistics tracking barcode reset detection unit shown according to some embodiments of the present application; Figure 3 is a structural schematic diagram of a computer terminal device for implementing a logistics tracking barcode reset detection method shown according to some embodiments of the present application. DETAILED DESCRIPTION

[0018] The present application starts logistics tracking barcode reset detection through a logistics tracking edge device, acquires a barcode acquisition image, performs edge detection and filtering on the barcode acquisition image to obtain a barcode enhanced image, performs barcode reference separation on the barcode acquisition image to obtain a plurality of barcode reset reference subgraphs, determines the reference contrast and reference orientation factor corresponding to each barcode reset reference subgraph, and then determines the reference confidence weight corresponding to each barcode reset reference subgraph according to the reference contrast and reference orientation factor corresponding to each barcode reset reference subgraph, determines the reset rotation features corresponding to each barcode reset reference subgraph, performs reset fusion on the reset rotation features corresponding to each barcode reset reference subgraph according to the reference confidence weight corresponding to each barcode reset reference subgraph, and obtains a reference reset angle of the barcode. Finally, the barcode enhanced image is reset and detected according to the reference reset angle. The present application determines the reference confidence weight of the reference object to which the barcode is attached, and resets and detects the barcode enhanced image according to the image features of the reference object, which can accurately reset the logistics tracking barcode when the reference object to which the logistics tracking barcode is attached is distorted, and improves the recognition rate of the logistics tracking barcode.

[0019] In order to better understand the above technical solutions, the above technical solutions will be described in detail below in combination with the drawings in the specification and specific embodiments. Reference Figure 1 The figure is an exemplary flowchart of a logistics tracking barcode reset detection method 100 shown according to some embodiments of the present application, which mainly includes the following steps: In step S101, the logistics tracking edge device starts logistics tracking barcode reset detection and acquires a barcode acquisition image.

[0020] Optionally, the logistics tracking edge device in the present application may, for example, be a code scanning device or other edge device. In some embodiments, the barcode acquisition image is a region image of the region where the barcode is located. In specific implementation, a high-definition camera may be used to acquire the region image of the region where the barcode is located to obtain the barcode acquisition image. Other devices or equipment capable of image acquisition may also be used, which is not limited here.

[0021] In step S102, edge detection and filtering are performed on the barcode acquisition image to obtain a barcode enhanced image.

[0022] It should be noted that the barcode enhanced image is a feature image containing only the barcode after segmentation and filtering of the barcode acquisition image. Preferably, in some embodiments, edge detection and filtering are performed on the barcode acquisition image to obtain a barcode enhanced image, which can be implemented in the following manner, namely: The barcode acquisition image is subjected to grayscale binarization processing to obtain a barcode black-and-white image. The barcode black-and-white image is subjected to contour extraction to obtain barcode contour features, and the barcode acquisition image is subjected to region segmentation and filtering according to the barcode contour features to obtain a barcode enhanced image.

[0023] In a specific implementation, the step of performing grayscale binarization processing on the barcode acquisition image can first convert a color image into a grayscale image, i.e., the color information of the original image is simplified into a single-channel grayscale value, which is implemented by weighted average of the values of the three RGB channels in some embodiments of the present application. Subsequently, the grayscale value of each pixel in the image is compared with a threshold value, and the pixels with a value greater than the threshold value are assigned a white color (255), and the pixels with a value less than the threshold value are assigned a black color (0), thereby obtaining a binary image. Then, the findContours contour detection algorithm can be used to extract contours from the barcode black-and-white image to obtain a plurality of barcode contour features. Then, the found contours are screened to select the barcode contour feature most similar to the shape of the barcode. Then, a bounding box is drawn according to the selected barcode contour feature, which is used as the position of the barcode region. Finally, the original image is cropped according to the drawn bounding box to obtain a barcode enhanced image.

[0024] Optionally, in some embodiments, the barcode enhanced image can be filtered using a commonly used Gaussian filtering method for image filtering. Gaussian filtering is a commonly used image smoothing method that can effectively remove noise in the image and make the image smoother, thereby enhancing the clarity of the barcode. In a specific implementation, other methods capable of image filtering such as bilateral filtering can also be used, which are not limited in the present application.

[0025] In step S103, barcode reference separation is performed on the barcode acquisition image to obtain a plurality of barcode reset reference subgraphs.

[0026] It should be noted that the barcode reset reference subgraph is the surface image of the plurality of reference objects to which the barcode is attached, for example, the mail bag on which the barcode is located is the first reference object, and the desk on which the mail bag is located is the second reference object. Since the reference object on which the barcode is located is usually a rectangular object with a smooth surface, the barcode reference separation can be performed according to the rectangularity of the edge profile of the background reference object in the present application, to obtain a plurality of barcode reset reference subgraphs. In some embodiments, the barcode reference separation is performed on the barcode acquisition image to obtain a plurality of barcode reset reference subgraphs, which specifically includes: The reference background recognition is performed on the barcode acquisition image to obtain a plurality of reference background edge points. The plurality of reference background edge points are grouped according to the positional relationship to obtain a plurality of reference background edge groups. For any one reference background edge group, the background segmentation is performed according to all the reference background edge points in the reference background edge group to obtain a barcode reset reference subgraph, and then the same method is used to obtain a plurality of barcode reset reference subgraphs.

[0027] Optionally, in some embodiments, the Canny edge detection algorithm can be used to perform the reference background recognition on the barcode acquisition image to obtain a plurality of reference background edge points.

[0028] Optionally, in some embodiments, the plurality of reference background edge points are grouped according to the positional relationship to obtain a plurality of reference background edge groups, which specifically includes: The contour detection is performed on the plurality of reference background edge points to obtain a plurality of background contours. Specifically, the findContours function of OpenCV can be used for contour detection. The reference background edge points in each background contour are grouped according to the positional relationship of the background contours to obtain a plurality of reference background edge groups.

[0029] In a specific implementation, a straight line fitting can be first performed on each contour, a Hough Transform or a Least Squares method can be used to fit the contour into a straight line segment, and then a parameterized description can be performed on each straight line segment, for example, a slope and an intercept (or a rho and a theta in a polar coordinate representation) are used to describe each straight line, and the straight lines are grouped according to the parameters (such as a slope, an intercept, an angle, and the like) of the straight lines. The grouping can generally be performed according to the following criteria: 1. The straight lines with the same or similar slopes can be regarded as parallel and belong to the same group; 2. The straight lines with a distance within a certain range can be grouped into the same group, representing opposite edges of the same rectangle; and 3. The intersection points between different straight lines are detected, and the existence or nonexistence of the intersection points can further confirm which straight lines constitute the edges of the rectangle. For each group of parallel straight lines, a straight line pair that constitutes a rectangle is first analyzed, and then by checking the intersection between each two straight lines and the distance relationship between the straight lines, the existing rectangle boundaries can be found. Finally, all the reference background edge points included in the rectangle boundaries are taken as a reference background edge group.

[0030] In step S104, for any one barcode reset reference subgraph, a reference contrast and a reference orientation factor corresponding to the one barcode reset reference subgraph are determined, and then a reference confidence weight corresponding to the one barcode reset reference subgraph is determined according to the reference contrast and the reference orientation factor corresponding to the one barcode reset reference subgraph.

[0031] It should be noted that the reference contrast is the coverage of the barcode on the reference corresponding to the one barcode reset reference subgraph. In some embodiments, determining the reference contrast corresponding to the one barcode reset reference subgraph specifically includes: An enhanced barcode image is acquired. Edge feature points of the one barcode reset reference subgraph are acquired, and edge feature points of the enhanced barcode image are acquired. A reference repetitive region of the one barcode reset reference subgraph is determined according to the edge feature points of the one barcode reset reference subgraph and the edge feature points of the enhanced barcode image. The reference contrast corresponding to the one barcode reset reference subgraph is determined according to the reference repetitive region.

[0032] In a specific implementation, a proportion value of an area of the reference repetitive region in the one barcode reset reference subgraph can be taken as the reference contrast.

[0033] It should be noted that the reference orientation factor is a central orientation deviation degree between the barcode and the reference corresponding to the one barcode reset reference subgraph. Optionally, in some embodiments, determining the reference orientation factor corresponding to the one barcode reset reference subgraph specifically includes: obtaining a barcode enhanced image; obtaining a centroid coordinate of the barcode reset reference subgraph, and obtaining a centroid coordinate of the barcode enhanced image; determining a reference orientation factor corresponding to the barcode reset reference subgraph according to the centroid coordinate of the barcode reset reference subgraph and the centroid coordinate of the barcode enhanced image.

[0034] Optionally, in some embodiments, the centroid coordinate of each barcode reset reference subgraph and the centroid coordinate of the barcode enhanced image can be respectively differentiated and normalized, and the normalized result of each barcode reset reference subgraph is taken as the reference orientation factor.

[0035] It should be noted that the reference confidence weight is used to reflect the reference confidence degree of the barcode reference corresponding to the barcode reset reference subgraph. Optionally, in some embodiments, the reference confidence weight corresponding to the barcode reset reference subgraph is the product of the reference contrast and the reference orientation factor corresponding to the barcode reset reference subgraph.

[0036] In step S105, the reset rotation feature corresponding to each barcode reset reference subgraph is determined, and the reset rotation features corresponding to each barcode reset reference subgraph are fused according to the reference confidence weight corresponding to each barcode reset reference subgraph to obtain a reference reset angle of the barcode.

[0037] In some embodiments, the reset rotation feature corresponding to each barcode reset reference subgraph can be determined in the following manner, that is: For any barcode reset reference subgraph, the edge feature point of the barcode reset reference subgraph is determined, and the reset rotation feature of the barcode reset reference subgraph is determined according to the edge feature point of the barcode reset reference subgraph. The reset rotation features corresponding to each barcode reset reference subgraph are determined by the same steps.

[0038] Optionally, in some embodiments, the reset rotation feature of the barcode reset reference subgraph can be determined in the following manner according to the edge feature point of the barcode reset reference subgraph: The reference contour is extracted according to the edge feature point of the barcode reset reference subgraph, and the edge line slope of the reference contour is obtained by linear fitting. The barcode enhanced image is obtained, the contour of the barcode enhanced image is extracted, and the barcode edge slope is obtained by linear fitting. The barcode edge slope and the edge line slope of the reference contour are differentiated to obtain the reset rotation feature of the barcode reset reference subgraph.

[0039] Optionally, in some embodiments, the slope difference between the barcode edge slope and the edge line slope of the reference contour can be subjected to an arctangent transformation, and the function return value obtained is taken as the reset rotation feature of the barcode reset reference subgraph.

[0040] It should be noted that the reference reset angle is a barcode reference angle obtained according to the contours of a plurality of background references of the barcode, and resetting and repairing the barcode enhanced image according to the reference reset angle can improve the reading speed of the barcode in a complex background environment. Optionally, in some embodiments, the reset rotation features corresponding to each barcode reset reference subgraph can be weighted and fused according to the reference confidence weight corresponding to each barcode reset reference subgraph to obtain the reference reset angle.

[0041] In step S106, the barcode enhanced image is reset and detected according to the reference reset angle, and the detection result is sent to the cloud.

[0042] Optionally, in some embodiments, the barcode enhanced image can be rotated according to the reference reset angle to realize resetting and repairing of the barcode enhanced image, thereby improving the reading speed of the barcode in a complex background environment.

[0043] Optionally, in some embodiments, barcode detection can be realized by comparing the reset barcode enhanced image with the images in the barcode recognition library.

[0044] In addition, another aspect of the present application, in some embodiments, the present application provides a logistics tracking system, the logistics tracking system adopts a cloud-edge collaborative architecture, the cloud-edge collaborative architecture includes a logistics tracking edge device and a cloud, wherein the logistics tracking edge device includes a logistics tracking barcode reset detection unit, for example Figure 2 The figure is a structural schematic diagram of a logistics tracking barcode reset detection unit according to some embodiments of the present application. The logistics tracking barcode reset detection unit 200 includes a barcode acquisition module 201, a processing module 202, and a reset detection module 203, which are described as follows: The barcode acquisition module 201 is mainly used to start the logistics tracking barcode reset detection and acquire a barcode acquisition image in some specific embodiments of the present application. The processing module 202 is used to perform edge detection and filtering on the barcode acquisition image to obtain a barcode enhanced image in some specific embodiments of the present application. It should be noted that the processing module 202 in the present application is also used for barcode reference separation on the barcode collection image to obtain a plurality of barcode reset reference subgraphs; In addition, the processing module 202 in the present application is also used for determining the reference contrast and the reference orientation factor corresponding to any one of the barcode reset reference subgraphs, and then determining the reference confidence weight corresponding to the barcode reset reference subgraph according to the reference contrast and the reference orientation factor corresponding to the barcode reset reference subgraph; In addition, the processing module 202 is also used for determining the reset rotation feature corresponding to each barcode reset reference subgraph, respectively, and performing reset fusion on the reset rotation feature corresponding to each barcode reset reference subgraph, respectively, according to the reference confidence weight corresponding to each barcode reset reference subgraph, respectively, to obtain the reference reset angle of the barcode. The reset detection module 203 is mainly used for resetting and detecting the barcode enhanced image according to the reference reset angle and sending the detection result to the cloud in some specific embodiments of the present application.

[0045] The above describes the examples of the reset detection method of the logistics tracking barcode provided by the embodiments of the present application in detail. It can be understood that the corresponding device contains the hardware structure and / or software module corresponding to the execution of each function in order to realize the above functions.

[0046] Those skilled in the art should easily realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in the present application can be realized in the form of hardware or combination of hardware and computer software. Whether a certain function in the application is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution, so that the professional technicians can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0047] In addition, the present application also provides a computer terminal device, which comprises a memory and a processor, the memory stores a code, and the processor is configured to acquire the code and execute the above-mentioned reset detection method of the logistics tracking barcode.

[0048] In some embodiments, referring to Figure 3 The figure is a structural schematic diagram of a computer terminal device for implementing the reset detection method of the logistics tracking barcode according to some embodiments of the present application. The reset detection method of the logistics tracking barcode in the above-mentioned embodiments can be realized by the computer terminal device shown in the figure. Figure 3The computer terminal device shown is implemented by a computer terminal device 300 including at least one communication bus 301, a communication interface 302, a processor 303, and a memory 304.

[0049] The processor 303 can be a general central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more processors for controlling execution of the reset detection method of the logistics tracking barcode in the present application.

[0050] The communication bus 301 can include a path for transmitting information between the above components.

[0051] The memory 304 can be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disk storage, a magnetic disk storage or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto. The memory 304 can exist independently and be connected to the processor 303 through the communication bus 301. The memory 304 can also be integrated with the processor 303.

[0052] The memory 304 is used to store program code for executing the scheme of the present application and is controlled by the processor 303 for execution. The processor 303 is used to execute the program code stored in the memory 304. The program code can include one or more software modules. The determination of the confidence weight in the above embodiments can be implemented by one or more software modules in the program code of the processor 303 and the memory 304.

[0053] The communication interface 302 uses any transceiver-like device for communicating with other devices or communication networks, such as an Ethernet, a radio access network (RAN), a wireless local area network (WLAN), etc.

[0054] Optionally, the computer terminal device 300 can further include a power supply 305 for providing power to various devices or circuits in the real-time computer terminal device.

[0055] In a specific implementation, as an embodiment, the computer terminal device can include a plurality of processors, each of which can be a single-CPU processor or a multi-CPU processor. The processor herein can refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0056] The computer terminal device described above can be a general-purpose computer terminal device or a special-purpose computer terminal device. In a specific implementation, the computer terminal device can be a desktop computer, a laptop computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. The embodiments of the present application do not limit the type of computer terminal device.

[0057] In addition, the present application also provides a computer-readable storage medium storing at least one computer program, which is loaded and executed by a processor to implement the operations performed by the above-mentioned reset detection method for a logistics tracking barcode.

[0058] In summary, in the logistics tracking system and method disclosed by the embodiments of the present application, the reset detection of the logistics tracking barcode is first started, and a barcode acquisition image is obtained. The barcode acquisition image is subjected to edge detection and filtering to obtain a barcode enhancement image. The barcode acquisition image is subjected to barcode reference separation to obtain a plurality of barcode reset reference sub-images. For any one barcode reset reference sub-image, the reference contrast and the reference orientation factor corresponding to the barcode reset reference sub-image are determined, and then the reference confidence weight corresponding to the barcode reset reference sub-image is determined according to the reference contrast and the reference orientation factor corresponding to the barcode reset reference sub-image. The reset rotation features corresponding to each barcode reset reference sub-image are determined, and the reset rotation features corresponding to each barcode reset reference sub-image are fused according to the reference confidence weight corresponding to each barcode reset reference sub-image to obtain a reference reset angle of the barcode. Finally, the barcode enhancement image is reset and detected according to the reference reset angle. By determining the reference confidence weight of the reference object to which the barcode is attached and resetting and detecting the barcode enhancement image according to the image features of the reference object, the present application can accurately reset the logistics tracking barcode when the reference object to which the logistics tracking barcode is attached is distorted, thereby improving the recognition rate of the logistics tracking barcode.

[0059] The above is only the embodiment of the present application, and the common technical solutions or characteristics in the scheme are not described in detail. It should be pointed out that for those skilled in the art, without departing from the technical solutions of the present application, a number of modifications and improvements can be made, which should also be considered as the protection scope of the present application, and these will not affect the effect and practicality of the patent implementation.

[0060] The protection scope of the present application shall be subject to the content of its claims, and the specific embodiments and the like recorded in the specification can be used to explain the content of the claims. Obviously, those skilled in the art can make various modifications and changes to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and changes of the present application belong to the scope of the claims of the present application and its equivalent technology, the present application also intends to include these modifications and changes.

Claims

1. A method for resetting and detecting logistics tracking barcodes, applied to a logistics tracking system, wherein the logistics tracking system adopts a cloud-edge collaborative architecture, the cloud-edge collaborative architecture including logistics tracking edge devices and a cloud, characterized in that, The method comprises: The logistics tracking edge device starts the logistics tracking barcode reset detection, and acquires a barcode collection image; Edge detection and filtering are performed on the barcode collection image to obtain a barcode enhanced image; Barcode reference separation is performed on the barcode collection image to obtain a plurality of barcode reset reference subgraphs; For any one barcode reset reference subgraph, the reference contrast and the reference orientation factor corresponding to the barcode reset reference subgraph are determined, and then the reference confidence weight corresponding to the barcode reset reference subgraph is determined according to the reference contrast and the reference orientation factor corresponding to the barcode reset reference subgraph; The reset rotation features corresponding to each barcode reset reference subgraph are determined, and the reset rotation features corresponding to each barcode reset reference subgraph are fused according to the reference confidence weight corresponding to each barcode reset reference subgraph to obtain a reference reset angle of the barcode; The barcode enhanced image is reset and detected according to the reference reset angle, and the detection result is sent to the cloud.

2. The method of claim 1, wherein, The edge detection and filtering on the barcode collection image to obtain the barcode enhanced image specifically comprise: The barcode collection image is subjected to grayscale binarization processing to obtain a barcode black and white image; The barcode black and white image is subjected to contour extraction to obtain barcode contour features, and the barcode collection image is subjected to region segmentation and filtering according to the barcode contour features to obtain the barcode enhanced image.

3. The method of claim 1, wherein, The barcode reference separation on the barcode collection image to obtain a plurality of barcode reset reference subgraphs specifically comprises: The barcode collection image is subjected to reference background recognition to obtain a plurality of reference background edge points; The plurality of reference background edge points are grouped according to their positional relationship to obtain a plurality of reference background edge groups; For any one reference background edge group, background segmentation is performed according to all the reference background edge points in the reference background edge group to obtain one barcode reset reference subgraph, and then a plurality of barcode reset reference subgraphs are obtained in the same way.

4. The method of claim 1, wherein, The reference contrast corresponding to the barcode reset reference subgraph specifically comprises: The barcode enhanced image is acquired; The edge feature points of the barcode reset reference subgraph and the edge feature points of the barcode enhanced image are acquired; According to the edge feature points of the barcode reset reference subgraph and the edge feature points of the barcode enhanced image, the reference repeated area of the barcode reset reference subgraph is determined; According to the reference repeated area, the reference contrast corresponding to the barcode reset reference subgraph is determined.

5. The method of claim 1, wherein, The reference orientation factor corresponding to the barcode reset reference subgraph specifically comprises: The barcode enhanced image is acquired; The centroid coordinates of the barcode reset reference subgraph and the centroid coordinates of the barcode enhanced image are acquired; According to the centroid coordinates of the barcode reset reference subgraph and the centroid coordinates of the barcode enhanced image, the reference orientation factor corresponding to the barcode reset reference subgraph is determined.

6. The method of claim 1, wherein, The reset rotation features corresponding to each barcode reset reference subgraph specifically comprise: For any one barcode reset reference subgraph, the edge feature point of the barcode reset reference subgraph is determined, and the reset rotation feature of the barcode reset reference subgraph is determined according to the edge feature point of the barcode reset reference subgraph. Further, the corresponding reset rotation features of each barcode reset reference subgraph are determined by using the same steps.

7. The method of claim 1, wherein, The high-definition camera is used to collect the area image of the area where the barcode is located, and the barcode collection image is obtained.

8. A logistics tracking system employing a cloud-edge collaborative architecture comprising a logistics tracking edge device and a cloud, wherein the logistics tracking edge device comprises a logistics tracking barcode reset detection unit, characterized in that, The logistics tracking barcode reset detection unit comprises: The barcode collection module is used to start the logistics tracking barcode reset detection, and the barcode collection image is obtained. The processing module is used to perform edge detection and filtering on the barcode collection image to obtain a barcode enhanced image. The processing module is also used to perform barcode reference separation on the barcode collection image to obtain a plurality of barcode reset reference subgraphs. The processing module is also used to determine the reference contrast and reference orientation factor corresponding to each barcode reset reference subgraph, and further determine the reference confidence weight corresponding to each barcode reset reference subgraph according to the reference contrast and reference orientation factor corresponding to each barcode reset reference subgraph. The processing module is also used to determine the reset rotation feature corresponding to each barcode reset reference subgraph, and perform reset fusion on the reset rotation feature corresponding to each barcode reset reference subgraph according to the reference confidence weight corresponding to each barcode reset reference subgraph to obtain the reference reset angle of the barcode. The reset detection module is used to reset and detect the barcode enhanced image according to the reference reset angle, and send the detection result to the cloud.

9. A computer terminal device, characterized by The computer terminal device comprises a memory and a processor, the memory stores a code, the processor is configured to obtain the code, and perform the reset detection method of the logistics tracking barcode as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium storing at least one computer program, characterized in that, The computer program is loaded and executed by the processor to realize the operations performed by the reset detection method of the logistics tracking barcode as claimed in any one of claims 1 to 7.

Images