A method, system and device based on electronic guided sorting

Abstract

The present invention is applicable to the technical field of cargo sorting, and provides a method, system and device based on electronic guided sorting. The present invention determines the target sorting cargo; determines the actual label surface; when the basic identification is unsuccessful, screens multiple suspicious cargo information; selects the adjacent scanning camera, receives the collaborative feedback image, and performs relative angle identification; performs clamping rotation adjustment and label position identification, matches the target cargo information; and performs guided sorting control. It can identify and determine the actual label surface, perform primary and secondary basic identification and judgment, and when the basic identification is unsuccessful, receive the collaborative feedback image, perform clamping rotation adjustment and label position identification, match the target cargo information, and then perform guided sorting control, which can ensure stable and reliable cargo identification even when the label code is damaged, and ensure automatic and accurate cargo sorting without human intervention, reduce logistics costs, and improve service quality and customer satisfaction.

Description

Technical Field

[0001] The present invention belongs to the technical field of cargo sorting, and in particular relates to a method, system and device based on electronically guided sorting. Background Art

[0002] Cargo sorting is the process of classifying, organizing, selecting and distributing goods according to certain standards or rules. Sorting is widely used in logistics, warehousing, production and other fields. It is of great significance to improve logistics efficiency, reduce costs and ensure accurate delivery of goods.

[0003] In the prior art, the electronic guidance sorting mechanism for goods mainly relies on scanning the label code attached to the surface of the goods to obtain the goods information, and then automatically guides the goods into the designated sorting path according to the preset sorting strategy to realize the automatic sorting of the goods. However, during the transportation of goods, due to the influence of various factors (including loading and unloading wear, stacking wear, and weather influence), the label code of the goods may be damaged, which in turn affects the subsequent identification and sorting process, requiring manual intervention, increasing logistics costs, and may cause sorting errors, affecting service quality and customer satisfaction. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide a method, system and device based on electronic guided sorting, aiming to solve the technical problems existing in the prior art mentioned in the background technology.

[0005] The embodiment of the present invention is implemented as follows:

[0006] A method based on electronic guided sorting, the method specifically comprises the following steps:

[0007] Determine the target sorting goods, select the target code scanning camera, perform initial shooting control, obtain the initial shooting image, and perform appearance recognition to determine a pair of clamping surfaces and four suspicious label surfaces;

[0008] According to the pair of clamping surfaces, clamping rotation control is performed, and the target code scanning camera is used to synchronously shoot four suspicious label surfaces to identify and determine the actual label surface;

[0009] Perform primary and secondary basic identification and judgment of code scanning and order number identification on the actual label surface, and screen multiple suspicious goods information based on the preset goods backup data when basic identification fails;

[0010] Select a neighboring barcode scanning camera, generate and send a collaborative shooting instruction to the neighboring barcode scanning camera, receive a collaborative feedback image, and perform relative angle recognition to determine the target relative angle;

[0011] According to the relative angle of the target, the clamping rotation is adjusted, the parallel plane image is acquired by the target code scanning camera, and the label position is identified, and the target cargo information is matched from the multiple suspicious cargo information;

[0012] Guided sorting control is performed according to the target cargo information.

[0013] As a further limitation of the technical solution of the embodiment of the present invention, the steps of determining the target sorting goods, selecting the target code scanning camera, performing initial shooting control, acquiring the initial shooting image, and performing appearance recognition to determine a pair of clamping surfaces and four suspicious label surfaces specifically include the following steps:

[0014] Determine the target sorting goods and select the target scanning camera;

[0015] Performing initial shooting control on the target code scanning camera to obtain an initial shot image;

[0016] According to the initial captured image, three-side recognition is performed on the target sorted goods, three target intersecting surfaces are determined, and three intersecting surface images are extracted;

[0017] Relative area recognition is performed on the three intersecting surface images, and the relative areas of the three target intersecting surfaces are recorded;

[0018] The relative areas of the three target intersecting faces are compared, and a face symmetry analysis is performed to select a pair of clamping faces and four suspicious label faces.

[0019] As a further limitation of the technical solution of the embodiment of the present invention, the clamping rotation control is performed according to a pair of the clamping surfaces, and the four suspicious label surfaces are synchronously photographed by the target code scanning camera to identify and determine the actual label surface, which specifically includes the following steps:

[0020] According to a preset clamping rotation speed, a pair of clamping surfaces of the target sorting goods are clamped and rotated in a controlled manner;

[0021] According to a preset synchronous shooting frequency, the target code scanning camera is used to synchronously shoot four suspicious label surfaces to obtain multiple synchronous shooting images;

[0022] Based on preset basic label features, feature recognition analysis is performed on the plurality of synchronously shot images to select a synchronous label image;

[0023] According to the synchronized label image, the actual label surface is determined from the four suspicious label surfaces.

[0024] As a further limitation of the technical solution of the embodiment of the present invention, the primary and secondary basic identification and judgment of the actual label surface by scanning code identification and order number identification, and when the basic identification is unsuccessful, screening multiple suspicious goods information based on the preset goods backup data specifically includes the following steps:

[0025] Scanning and identifying the actual label surface to determine whether the scanning and identification is successful;

[0026] When the code scanning recognition is unsuccessful, the order number recognition is performed on the actual label surface to determine whether the order number recognition is successful;

[0027] When the order number recognition fails, extract the defect order number information;

[0028] Based on the preset cargo backup data, the defective order number information is matched with the order number to screen multiple suspicious cargo information.

[0029] As a further limitation of the technical solution of the embodiment of the present invention, the selecting of the adjacent code scanning camera, generating and sending a collaborative shooting instruction to the adjacent code scanning camera, receiving the collaborative feedback image, and performing relative angle recognition to determine the target relative angle specifically includes the following steps:

[0030] Selecting a neighboring barcode scanning camera corresponding to the target barcode scanning camera;

[0031] Generate and send a collaborative shooting instruction to the adjacent code scanning camera;

[0032] Receiving the collaborative feedback image from the adjacent code scanning camera;

[0033] Identify the collaborative feedback image to determine the camera edge plane of the target code scanning camera and the cargo edge plane of the target sorted cargo;

[0034] Relative angle recognition is performed based on the camera edge plane and the cargo edge plane to determine the target relative angle.

[0035] As a further limitation of the technical solution of the embodiment of the present invention, the clamping rotation adjustment is performed according to the relative angle of the target, the parallel plane image is acquired by the target code scanning camera, and the label position is identified, and the target cargo information is matched from the multiple suspicious cargo information specifically including the following steps:

[0036] According to the target relative angle, clamping and rotating the target sorting goods;

[0037] After the clamping rotation adjustment is completed, the target sorting goods are photographed in parallel through the target code scanning camera to obtain parallel plane images;

[0038] Performing label position recognition on the parallel plane image to obtain label position data;

[0039] According to the tag location data, target cargo information is matched from multiple pieces of suspicious cargo information.

[0040] As a further limitation of the technical solution of the embodiment of the present invention, the guiding sorting control according to the target cargo information specifically includes the following steps:

[0041] Analyze the target cargo information and determine the cargo sorting direction;

[0042] Generate sorting control instructions according to the cargo sorting direction;

[0043] According to the sorting control instruction, the target sorting goods are guided and controlled.

[0044] A system based on electronic guided sorting, the system comprises an appearance recognition processing module, a synchronous shooting recognition module, a primary and secondary basis recognition module, a relative angle recognition module, a label position recognition module and a guided sorting control module, wherein:

[0045] The appearance recognition processing module is used to determine the target sorting goods, select the target code scanning camera, perform initial shooting control, obtain the initial shooting image, and perform appearance recognition to determine a pair of clamping surfaces and four suspicious label surfaces;

[0046] A synchronous shooting and identification module is used to perform clamping and rotation control according to a pair of the clamping surfaces, and synchronously shoot four suspicious label surfaces through the target code scanning camera to identify and determine the actual label surface;

[0047] The primary and secondary basic identification module is used to perform primary and secondary basic identification and judgment on the actual label surface by scanning code identification and order number identification, and when the basic identification fails, it screens multiple suspicious goods information based on the preset goods backup data;

[0048] A relative angle recognition module is used to select a neighboring barcode scanning camera, generate and send a collaborative shooting instruction to the neighboring barcode scanning camera, receive a collaborative feedback image, and perform relative angle recognition to determine the target relative angle;

[0049] A label position recognition module is used to perform clamping rotation adjustment according to the relative angle of the target, obtain a parallel plane image through the target code scanning camera, and perform label position recognition to match the target cargo information from the multiple suspicious cargo information;

[0050] The guidance sorting control module is used to perform guidance sorting control according to the target cargo information.

[0051] As a further limitation of the technical solution of the embodiment of the present invention, the appearance recognition processing module specifically includes:

[0052] A target selection unit is used to determine the target sorting goods and select the target scanning camera;

[0053] An initial shooting control unit, used to perform initial shooting control on the target code scanning camera to obtain an initial shooting image;

[0054] A three-side recognition unit, used to perform three-side recognition on the target sorting goods according to the initial captured image, determine three target intersecting surfaces, and extract three intersecting surface images;

[0055] A relative area recognition unit is used to perform relative area recognition on the three intersecting surface images and record the relative areas of the three target intersecting surfaces;

[0056] The face symmetry analysis selection unit is used to compare the relative areas of the three target intersecting faces, perform face symmetry analysis, and select a pair of clamping faces and four suspicious label faces.

[0057] A device for electronically guided sorting, wherein a computer program is stored on the device. When the computer program is executed by a processor, the processor executes the steps of the method for electronically guided sorting as described above.

[0058] Compared with the prior art, the present invention has the following beneficial effects:

[0059] The embodiment of the present invention determines the target sorting goods; determines the actual label surface; when the basic identification is unsuccessful, screens multiple suspicious goods information; selects the adjacent scanning camera, receives the collaborative feedback image, and performs relative angle identification; performs clamping rotation adjustment and label position identification, matches the target goods information; and performs guided sorting control. It can identify and determine the actual label surface, perform primary and secondary basic identification and judgment, and when the basic identification is unsuccessful, receive the collaborative feedback image, perform clamping rotation adjustment and label position identification, match the target goods information, and then perform guided sorting control, which can ensure stable and reliable goods identification even when the label code is damaged, and ensure automatic and accurate goods sorting without human intervention, reduce logistics costs, and improve service quality and customer satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 A flow chart of a method for electronically guided sorting provided by an embodiment of the present invention is shown;

[0061] Figure 2 A flowchart of initial shooting and appearance recognition in the method provided by an embodiment of the present invention is shown;

[0062] Figure 3 A flow chart showing the identification and determination of the actual label surface in the method provided by an embodiment of the present invention;

[0063] Figure 4 A flowchart showing primary and secondary basis identification and judgment in the method provided by an embodiment of the present invention is shown;

[0064] Figure 5 A flow chart of determining a target relative angle in a method provided by an embodiment of the present invention is shown;

[0065] Figure 6 A flowchart of tag position identification and analysis in the method provided by an embodiment of the present invention is shown;

[0066] Figure 7 A flowchart of guiding sorting control in the method provided by an embodiment of the present invention is shown;

[0067] Figure 8 An application architecture diagram of a system based on electronically guided sorting provided by an embodiment of the present invention is shown;

[0068] Fig. 9 The structure block diagram of the appearance recognition processing module in the system provided by the embodiment of the present invention is shown. DETAILED DESCRIPTION

[0069] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0070] It is understandable that in the prior art, the electronic guidance sorting mechanism for goods mainly relies on scanning the label code attached to the surface of the goods to obtain the goods information, and then automatically guides the goods into the designated sorting path according to the preset sorting strategy to realize the automatic sorting of the goods. However, during the transportation of goods, due to the influence of various factors (including loading and unloading wear, stacking wear, and weather influence), the label code of the goods may be damaged, which in turn affects the subsequent identification and sorting process, requiring manual intervention, increasing logistics costs, and may cause sorting errors, affecting service quality and customer satisfaction.

[0071] To solve the above problems, the embodiments of the present invention disclose a method, system and device based on electronic guided sorting, which determines the target sorting goods, selects the target code scanning camera, performs initial shooting control, obtains the initial shooting image, and performs appearance recognition to determine a pair of clamping surfaces and four suspicious label surfaces; according to the pair of clamping surfaces, clamping rotation control is performed, and the four suspicious label surfaces are synchronously photographed by the target code scanning camera to identify and determine the actual label surface; the actual label surface is subjected to primary and secondary basic recognition and judgment of code scanning recognition and order number recognition, and when the basic recognition is unsuccessful, multiple suspicious goods information is screened based on preset goods backup data; an adjacent code scanning camera is selected, a collaborative shooting instruction is generated and sent to the adjacent code scanning camera, a collaborative feedback image is received, and relative angle recognition is performed to determine the target relative angle; according to the target relative angle, clamping rotation adjustment is performed, a parallel plane image is obtained by shooting with the target code scanning camera, and label position recognition is performed to match the target goods information from multiple suspicious goods information; guided sorting control is performed according to the target goods information. It can identify and determine the actual label surface, perform primary and secondary basic identification and judgment, and when basic identification is unsuccessful, receive collaborative feedback images, perform clamping rotation adjustment and label position identification, match target cargo information, and then guide sorting control. It can ensure stable and reliable cargo identification even when the label code is damaged, ensure automatic and accurate cargo sorting without human intervention, reduce logistics costs, and improve service quality and customer satisfaction.

[0072] Specifically, Figure 1 A flow chart of a method for electronically guided sorting provided by an embodiment of the present invention is shown.

[0073] In a preferred embodiment provided by the present invention, a method based on electronic guided sorting comprises the following steps:

[0074] Step S101, determine the target sorting goods, select the target code scanning camera, perform initial shooting control, obtain the initial shooting image, and perform appearance recognition to determine a pair of clamping surfaces and four suspicious label surfaces.

[0075] In an embodiment of the present invention, target sorting goods that have not been sorted on the conveyor belt are determined, and a target scanning camera close to the target sorting goods is selected from multiple online scanning cameras, and then the target scanning camera is initially controlled to obtain an initial shooting image, and the initial shooting image is preprocessed and feature recognized to determine three target intersection surfaces on the outer surface of the target sorting goods, and three intersection surface images corresponding to the three target intersection surfaces are extracted from the initial shooting image, and then the three intersection surface images are identified according to the preset basic image area of ​​the initial shooting image. The occupation ratio of the three intersection surface images to the initial shooting image is determined, and then the relative areas of the three target intersection surfaces corresponding to the three intersection surface images are calculated, and by comparing the relative areas of the three target intersection surfaces, the target intersection surface with the smallest area is marked as a clamping surface, and the other two target intersection surfaces are marked as suspicious label surfaces, and then according to the surface symmetry relationship, a pair of clamping surfaces and four suspicious label surfaces of the target sorting goods can be determined.

[0076] It can be understood that the target sorting goods have six outer surfaces, and the six outer surfaces are symmetrically arranged by three different target intersecting surfaces. By identifying the three target intersecting surfaces of the target sorting goods and then performing a rough relative area calculation on the three target intersecting surfaces, the areas of the three target intersecting surfaces can be relatively compared. The label code of the goods is generally pasted on the outer surface with a large area. Therefore, through the relative area comparison and the surface symmetry relationship, a pair of clamping surfaces and four suspicious label surfaces of the target sorting goods can be determined, providing basic conditions for subsequent clamping and label identification.

[0077] Specifically, Figure 2 A flow chart of initial shooting and appearance recognition in the method provided by an embodiment of the present invention is shown.

[0078] Among them, in the preferred embodiment provided by the present invention, the steps of determining the target sorting goods, selecting the target code scanning camera, performing initial shooting control, acquiring the initial shooting image, and performing appearance recognition to determine a pair of clamping surfaces and four suspicious label surfaces specifically include the following steps:

[0079] Step S1011, determine the target sorting goods and select the target scanning camera.

[0080] Step S1012: performing initial shooting control on the target code scanning camera to obtain an initial shot image.

[0081] Step S1013: perform three-side recognition on the target sorted goods according to the initial captured image, determine three target intersecting surfaces, and extract three intersecting surface images.

[0082] Step S1014: perform relative area recognition on the three intersecting surface images, and record the relative areas of the three target intersecting surfaces.

[0083] Step S1015: compare the relative areas of the three target intersecting surfaces, perform surface symmetry analysis, and select a pair of clamping surfaces and four suspicious label surfaces.

[0084] Furthermore, the method based on electronically guided sorting further comprises the following steps:

[0085] Step S102: according to the pair of clamping surfaces, clamping rotation control is performed, and four suspicious label surfaces are synchronously photographed by the target code scanning camera to identify and determine the actual label surface.

[0086] In an embodiment of the present invention, a pair of clamping surfaces of the target sorting goods are clamped and rotationally controlled according to a preset clamping rotation speed, driving the target sorting goods to rotate around the clamping points of the pair of clamping surfaces, and then according to a preset synchronous shooting frequency matching the clamping rotation speed, four suspicious label surfaces are synchronously photographed through a target code scanning camera to obtain multiple synchronously photographed images, and feature recognition and analysis are performed on the multiple synchronously photographed images based on preset basic label features, and a synchronous label image with a label code is selected, and then the corresponding actual label surface is determined from the four suspicious label surfaces according to the synchronous label image.

[0087] It can be understood that each suspicious label surface has at least one synchronously captured image.

[0088] It can be understood that the basic label features include the color, texture, size, etc. of the label code.

[0089] Specifically, Figure 3 A flow chart of identifying and determining the actual label surface in the method provided by an embodiment of the present invention is shown.

[0090] Among them, in the preferred embodiment provided by the present invention, the clamping rotation control is performed according to a pair of the clamping surfaces, and the four suspicious label surfaces are synchronously photographed by the target scanning camera, and the identification and determination of the actual label surface specifically includes the following steps:

[0091] Step S1021: clamping and rotating a pair of clamping surfaces of the target sorting goods according to a preset clamping rotation speed.

[0092] Step S1022: synchronously shoot four suspicious label surfaces through the target code scanning camera according to a preset synchronous shooting frequency to obtain a plurality of synchronously shot images.

[0093] Step S1023: Based on preset basic label features, feature recognition analysis is performed on the multiple synchronously shot images to select a synchronous label image.

[0094] Step S1024: Determine the actual label surface from the four suspicious label surfaces according to the synchronized label image.

[0095] Furthermore, the method based on electronically guided sorting further comprises the following steps:

[0096] Step S103: Perform primary and secondary basic identification and judgment of code scanning and order number identification on the actual label surface, and when the basic identification is unsuccessful, screen multiple suspicious goods information based on the preset goods backup data.

[0097] In an embodiment of the present invention, a code scanning and recognition is performed on the synchronous label image corresponding to the actual label surface to determine whether the code scanning and recognition is successful. If the code scanning and recognition is unsuccessful, the order number is recognized on the synchronous label image corresponding to the actual label surface to determine whether the order number recognition is successful. If the order number recognition is unsuccessful, the defective order number information is extracted, and then based on the preset cargo backup data, the defective order number information is partially matched with the order number, and suspicious cargo information with multiple successful partial matches is screened.

[0098] It can be understood that if the complete order number information can be identified and obtained, the order number recognition is successful; if the identified and obtained order number information is defective, the order number recognition is unsuccessful.

[0099] It is understandable that the cargo backup data records information such as the recipient address, sender address, order number, label location, etc. of each cargo in the batch of cargo to be sorted.

[0100] It can be understood that the basic identification of primary and secondary is to first scan the code for recognition, and if the scanning code recognition is unsuccessful, then perform the basic identification process of order number recognition with clear priorities.

[0101] Specifically, Figure 4 A flow chart of primary and secondary basis identification and judgment in the method provided by an embodiment of the present invention is shown.

[0102] Among them, in the preferred embodiment provided by the present invention, the primary and secondary basic identification and judgment of scanning code recognition and order number recognition on the actual label surface, and when the basic identification is unsuccessful, screening multiple suspicious goods information based on the preset goods backup data specifically includes the following steps:

[0103] Step S1031: Scan the actual label surface to determine whether the scan is successful.

[0104] Step S1032: When the code scanning and recognition is unsuccessful, the order number is recognized on the actual label surface to determine whether the order number recognition is successful.

[0105] Step S1033: When the order number recognition is unsuccessful, extract the defect order number information.

[0106] Step S1034: Based on the preset cargo backup data, the defective order number information is matched and multiple suspicious cargo information is screened.

[0107] Furthermore, the method based on electronically guided sorting further comprises the following steps:

[0108] Step S104: select a neighboring code scanning camera, generate and send a collaborative shooting instruction to the neighboring code scanning camera, receive a collaborative feedback image, perform relative angle recognition, and determine the target relative angle.

[0109] In an embodiment of the present invention, a neighboring code scanning camera that is located at an adjacent workstation to a target code scanning camera is selected, and working status data of the neighboring code scanning camera is obtained. By analyzing the working status data, a collaborative gap period when the neighboring code scanning camera is in an idle state is selected, and then a collaborative shooting instruction is generated during the collaborative gap period, and the collaborative shooting instruction is sent to the neighboring code scanning camera, so that the neighboring code scanning camera is adjusted to the direction of the target code scanning camera to perform collaborative shooting and feedback transmission, and then the collaborative feedback image of the neighboring code scanning camera is received, and the camera edge plane of the target code scanning camera and the cargo edge plane of the target sorted goods are determined by preprocessing and edge feature recognition of the collaborative feedback image, and then the relative angles of the camera edge plane and the cargo edge plane are recognized to determine the target relative angle.

[0110] It can be understood that edge feature recognition is the process of matching and identifying the edge shape, color, texture and other features of the target scanning camera and the target sorting goods.

[0111] It can be understood that relative angle recognition is a process of identifying the deviation angle between the camera edge plane and the cargo edge plane that deviates from parallelism.

[0112] Specifically, Figure 5 A flow chart of determining the relative angle of a target in the method provided by an embodiment of the present invention is shown.

[0113] Among them, in the preferred embodiment provided by the present invention, the selecting of the adjacent code scanning camera, generating and sending a collaborative shooting instruction to the adjacent code scanning camera, receiving the collaborative feedback image, and performing relative angle recognition, and determining the target relative angle specifically include the following steps:

[0114] Step S1041: Select a neighboring code scanning camera corresponding to the target code scanning camera.

[0115] Step S1042: Generate and send a collaborative shooting instruction to the adjacent code scanning camera.

[0116] Step S1043: receiving the collaborative feedback image of the adjacent code scanning camera.

[0117] Step S1044: Identify the collaborative feedback image to determine the camera edge plane of the target code scanning camera and the cargo edge plane of the target sorted cargo.

[0118] Step S1045: Relative angle recognition is performed based on the camera edge plane and the cargo edge plane to determine a target relative angle.

[0119] Furthermore, the method based on electronically guided sorting further comprises the following steps:

[0120] Step S105: according to the relative angle of the target, the clamping rotation is adjusted, the parallel plane image is acquired by the target code scanning camera, and the label position is recognized, and the target cargo information is matched from the multiple suspicious cargo information.

[0121] In an embodiment of the present invention, the target sorted goods are clamped and rotated according to the target relative angle, so that the camera edge plane of the target code scanning camera and the goods edge plane of the target sorted goods are parallel. After that, the actual label surface of the target sorted goods is photographed in parallel by the target code scanning camera to obtain a parallel plane image, and then the spatial position of the label code on the actual label surface is identified according to the preset basic label features to obtain label position data, and multiple suspicious label positions are extracted from multiple suspicious goods information, the label position data is matched with the multiple suspicious label positions, and the successfully matched suspicious goods information is marked as the target goods information, so that the target goods information of the target sorted goods can be identified and obtained.

[0122] It can be understood that parallel shooting can ensure that the actual label surface of the target sorted goods is shot completely in a positive direction without relative tilt and offset, thereby ensuring the accuracy of subsequent label position recognition.

[0123] It can be understood that the identification of the spatial position of the label code on the actual label surface is the identification of the minimum distance and relative angle of the four code edges of the label code relative to the four surface edges of the actual label surface, wherein the four code edges are the lines corresponding to the four rectangular edges of the rectangular label code; the four surface edges are the lines corresponding to the four rectangular edges of the rectangular actual label surface of the target sorted goods.

[0124] Specifically, Figure 6 A flow chart of tag position identification and analysis in the method provided by an embodiment of the present invention is shown.

[0125] Among them, in the preferred embodiment provided by the present invention, the clamping rotation adjustment is performed according to the relative angle of the target, the parallel plane image is obtained by shooting with the target code scanning camera, and the label position is identified, and the target cargo information is matched from the multiple suspicious cargo information, specifically including the following steps:

[0126] Step S1051: clamp and rotate the target sorting goods according to the target relative angle.

[0127] Step S1052: After the clamping rotation adjustment is completed, the target sorting goods are photographed in parallel through the target code scanning camera to obtain parallel plane images.

[0128] Step S1053: perform label position recognition on the parallel plane image to obtain label position data.

[0129] Step S1054: Match target cargo information from multiple pieces of suspicious cargo information according to the tag location data.

[0130] Furthermore, the method based on electronically guided sorting further comprises the following steps:

[0131] Step S106: performing guided sorting control according to the target cargo information.

[0132] In an embodiment of the present invention, by analyzing the target cargo information, the corresponding cargo sorting direction is determined according to the preset sorting guidance strategy, and then the sorting control instructions are generated according to the cargo sorting direction. Then, according to the sorting control instructions, the target sorting cargo is guided and sorted accordingly to realize automatic and accurate cargo sorting.

[0133] Specifically, Figure 7 A flow chart of guided sorting control in the method provided by an embodiment of the present invention is shown.

[0134] Among them, in the preferred embodiment provided by the present invention, the guiding sorting control according to the target cargo information specifically includes the following steps:

[0135] Step S1061: Analyze the target cargo information to determine the cargo sorting direction.

[0136] Step S1062: Generate a sorting control instruction according to the cargo sorting direction.

[0137] Step S1063: According to the sorting control instruction, guide sorting control is performed on the target sorting goods.

[0138] Furthermore, Figure 8The application architecture diagram of the system based on electronically guided sorting provided by an embodiment of the present invention is shown.

[0139] Among them, in another preferred embodiment provided by the present invention, a system based on electronic guided sorting includes:

[0140] The appearance recognition processing module 101 is used to determine the target sorting goods, select the target code scanning camera, perform initial shooting control, obtain the initial shooting image, and perform appearance recognition to determine a pair of clamping surfaces and four suspicious label surfaces.

[0141] In the embodiment of the present invention, the appearance recognition processing module 101 determines the target sorting goods that have not been sorted on the conveyor belt, and selects a target scanning camera close to the target sorting goods from multiple online scanning cameras, and then performs initial shooting control on the target scanning camera to obtain an initial shooting image, pre-processes and features the initial shooting image, determines three target intersection surfaces on the outer surface of the target sorting goods, and extracts three intersection surface images corresponding to the three target intersection surfaces from the initial shooting image, and then performs relative area recognition on the three intersection surface images according to the preset basic image area of ​​the initial shooting image, determines the occupation ratio of the three intersection surface images to the initial shooting image, and then calculates the relative areas of the three target intersection surfaces corresponding to the three intersection surface images, and by comparing the relative areas of the three target intersection surfaces, marks the target intersection surface with the smallest area as a clamping surface, and marks the other two target intersection surfaces as suspicious label surfaces, and then according to the surface symmetry relationship, a pair of clamping surfaces and four suspicious label surfaces of the target sorting goods can be determined.

[0142] Specifically, Fig. 9 It shows a structural block diagram of the appearance recognition processing module 101 in the system provided by the embodiment of the present invention.

[0143] In a preferred embodiment of the present invention, the appearance recognition processing module 101 specifically includes:

[0144] The target selection unit 1011 is used to determine the target sorting goods and select the target scanning camera.

[0145] The initial shooting control unit 1012 is used to perform initial shooting control on the target code scanning camera to obtain an initial shooting image.

[0146] The three-surface recognition unit 1013 is used to perform three-surface recognition on the target sorting goods according to the initial captured image, determine three target intersecting surfaces, and extract three intersecting surface images.

[0147] The relative area recognition unit 1014 is used to perform relative area recognition on the three intersecting surface images and record the relative areas of the three target intersecting surfaces.

[0148] The face symmetry analysis selection unit 1015 is used to compare the relative areas of the three target intersecting faces, perform face symmetry analysis, and select a pair of clamping faces and four suspicious label faces.

[0149] Furthermore, the electronically guided sorting system further comprises:

[0150] The synchronous shooting and identification module 102 is used to perform clamping rotation control according to a pair of the clamping surfaces, and synchronously shoot four suspicious label surfaces through the target code scanning camera to identify and determine the actual label surface.

[0151] In an embodiment of the present invention, the synchronous shooting identification module 102 clamps and rotates a pair of clamping surfaces of the target sorting goods according to a preset clamping rotation speed, drives the target sorting goods to rotate around the clamping points of the pair of clamping surfaces, and then synchronously shoots four suspicious label surfaces through the target scanning camera according to a preset synchronous shooting frequency matching the clamping rotation speed, obtains multiple synchronous shooting images, performs feature recognition analysis on the multiple synchronous shooting images based on preset basic label features, selects a synchronous label image with a label code, and then determines the corresponding actual label surface from the four suspicious label surfaces according to the synchronous label image.

[0152] The primary and secondary basic identification module 103 is used to perform primary and secondary basic identification and judgment of code scanning and order number identification on the actual label surface, and when the basic identification is unsuccessful, screen multiple suspicious goods information based on preset goods backup data.

[0153] In an embodiment of the present invention, the primary and secondary basic identification module 103 scans and identifies the synchronized label image corresponding to the actual label surface to determine whether the scan and identification is successful. If the scan and identification is unsuccessful, the synchronized label image corresponding to the actual label surface is subjected to order number identification to determine whether the order number identification is successful. If the order number identification is unsuccessful, the defective order number information is extracted, and then based on the preset cargo backup data, the defective order number information is partially matched, and suspicious cargo information with multiple partial matches is screened.

[0154] The relative angle recognition module 104 is used to select a neighboring code scanning camera, generate and send a collaborative shooting instruction to the neighboring code scanning camera, receive a collaborative feedback image, and perform relative angle recognition to determine the target relative angle.

[0155] In an embodiment of the present invention, the relative angle recognition module 104 selects a neighboring code scanning camera that is located at an adjacent workstation to the target code scanning camera, and obtains working status data of the neighboring code scanning camera. By analyzing the working status data, the collaborative gap period when the neighboring code scanning camera is in an idle state is selected, and then during the collaborative gap period, a collaborative shooting instruction is generated, and the collaborative shooting instruction is sent to the neighboring code scanning camera, so that the neighboring code scanning camera is adjusted to the direction of the target code scanning camera to perform collaborative shooting and feedback transmission, and then the collaborative feedback image of the neighboring code scanning camera is received, and the camera edge plane of the target code scanning camera and the cargo edge plane of the target sorted goods are determined by preprocessing and edge feature recognition of the collaborative feedback image, and then the camera edge plane and the cargo edge plane are recognized at relative angles to determine the target relative angle.

[0156] The label position recognition module 105 is used to perform clamping rotation adjustment according to the relative angle of the target, obtain a parallel plane image through the target code scanning camera, and perform label position recognition to match the target cargo information from the multiple suspicious cargo information.

[0157] In the embodiment of the present invention, the label position identification module 105 clamps and rotates the target sorted goods according to the target relative angle, so that the camera edge plane of the target code scanning camera and the goods edge plane of the target sorted goods are parallel. Then, the actual label surface of the target sorted goods is photographed in parallel through the target code scanning camera to obtain a parallel plane image, and then the spatial position of the label code on the actual label surface is identified according to the preset basic label features to obtain label position data, and multiple suspicious label positions are extracted from multiple suspicious goods information, the label position data is matched with the multiple suspicious label positions, and the successfully matched suspicious goods information is marked as the target goods information, so that the target goods information of the target sorted goods can be identified and obtained.

[0158] The guidance sorting control module 106 is used to perform guidance sorting control according to the target cargo information.

[0159] In the embodiment of the present invention, the guided sorting control module 106 analyzes the target cargo information, determines the corresponding cargo sorting direction according to the preset sorting guidance strategy, and then generates sorting control instructions according to the cargo sorting direction, and then performs corresponding guided sorting control on the target sorted cargo according to the sorting control instructions, thereby realizing automatic and accurate cargo sorting.

[0160] Furthermore, in another preferred embodiment of the present invention, a device based on electronically guided sorting is provided, wherein a computer program is stored on the device based on electronically guided sorting, and when the computer program is executed by a processor, the processor performs the following steps:

[0161] Determine the target sorting goods, select the target code scanning camera, perform initial shooting control, obtain the initial shooting image, and perform appearance recognition to determine a pair of clamping surfaces and four suspicious label surfaces;

[0162] According to the pair of clamping surfaces, clamping rotation control is performed, and the target code scanning camera is used to synchronously shoot four suspicious label surfaces to identify and determine the actual label surface;

[0163] Perform primary and secondary basic identification and judgment of code scanning and order number identification on the actual label surface, and screen multiple suspicious goods information based on the preset goods backup data when basic identification fails;

[0164] Select a neighboring barcode scanning camera, generate and send a collaborative shooting instruction to the neighboring barcode scanning camera, receive a collaborative feedback image, and perform relative angle recognition to determine the target relative angle;

[0165] According to the relative angle of the target, the clamping rotation is adjusted, the parallel plane image is acquired by the target code scanning camera, and the label position is identified, and the target cargo information is matched from the multiple suspicious cargo information;

[0166] Guided sorting control is performed according to the target cargo information.

[0167] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0168] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0169] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A method based on electronically guided sorting, characterized in that: The method specifically comprises the following steps: Determine the target sorting goods, select the target code scanning camera, perform initial shooting control, obtain the initial shooting image, and perform appearance recognition to determine a pair of clamping surfaces and four suspicious label surfaces; According to the pair of clamping surfaces, clamping rotation control is performed, and four suspicious label surfaces are synchronously photographed by the target code scanning camera to identify and determine the actual label surface; Perform primary and secondary basic identification and judgment of code scanning and order number identification on the actual label surface, and screen multiple suspicious goods information based on the preset goods backup data when basic identification fails; Select a neighboring barcode scanning camera, generate and send a collaborative shooting instruction to the neighboring barcode scanning camera, receive a collaborative feedback image, and perform relative angle recognition to determine the target relative angle; Select a neighboring code scanning camera that is located at an adjacent workstation to the target code scanning camera, and obtain working status data of the neighboring code scanning camera. By analyzing the working status data, select a collaborative gap period when the neighboring code scanning camera is in an idle state, and then generate a collaborative shooting instruction during the collaborative gap period, and send the collaborative shooting instruction to the neighboring code scanning camera, so that the neighboring code scanning camera is adjusted to the direction of the target code scanning camera, and collaborative shooting and feedback transmission are performed, and then the collaborative feedback image of the neighboring code scanning camera is received, and the camera edge plane of the target code scanning camera and the cargo edge plane of the target sorted goods are determined by preprocessing and edge feature recognition of the collaborative feedback image, and then the relative angle of the camera edge plane and the cargo edge plane is recognized to determine the target relative angle; According to the relative angle of the target, the clamping rotation is adjusted, the parallel plane image is acquired by the target code scanning camera, and the label position is identified, and the target cargo information is matched from the multiple suspicious cargo information; According to the target relative angle, the target sorting goods are clamped and rotated to adjust so that the camera edge plane of the target code scanning camera and the goods edge plane of the target sorting goods are parallel. Then, the actual label surface of the target sorting goods is photographed in parallel by the target code scanning camera to obtain a parallel plane image, and then the spatial position of the label code on the actual label surface is identified according to the preset basic label features to obtain label position data, and multiple suspicious label positions are extracted from multiple suspicious goods information, the label position data are matched with the multiple suspicious label positions, and the suspicious goods information that is successfully matched is marked as the target goods information, so that the target goods information of the target sorting goods can be identified; the spatial position of the label code on the actual label surface is identified, which is the minimum distance and relative angle of the four code edges of the label code relative to the four surface edges of the actual label surface, wherein the four code edges are the lines corresponding to the four rectangular edges of the rectangular label code; the four surface edges are the lines corresponding to the four rectangular edges of the rectangular actual label surface of the target sorting goods; Guided sorting control is performed according to the target cargo information.

2. The method based on electronically guided sorting according to claim 1, characterized in that: The steps of determining the target sorting goods, selecting the target barcode scanning camera, performing initial shooting control, acquiring the initial shooting image, and performing appearance recognition to determine a pair of clamping surfaces and four suspicious label surfaces specifically include the following steps: Determine the target sorting goods and select the target scanning camera; Performing initial shooting control on the target code scanning camera to obtain an initial shot image; According to the initial captured image, three-side recognition is performed on the target sorted goods, three target intersecting surfaces are determined, and three intersecting surface images are extracted; Relative area recognition is performed on the three intersecting surface images, and the relative areas of the three target intersecting surfaces are recorded; The relative areas of the three target intersecting faces are compared, and a face symmetry analysis is performed to select a pair of clamping faces and four suspicious label faces.

3. The method based on electronically guided sorting according to claim 1, characterized in that: The clamping rotation control is performed according to a pair of the clamping surfaces, and the four suspicious label surfaces are synchronously photographed by the target code scanning camera to identify and determine the actual label surface, which specifically includes the following steps: According to a preset clamping rotation speed, a pair of clamping surfaces of the target sorting goods are clamped and rotated in a controlled manner; According to a preset synchronous shooting frequency, the target code scanning camera is used to synchronously shoot four suspicious label surfaces to obtain multiple synchronous shooting images; Based on preset basic label features, feature recognition analysis is performed on the plurality of synchronously shot images to select a synchronous label image; According to the synchronized label image, the actual label surface is determined from the four suspicious label surfaces.

4. The method based on electronically guided sorting according to claim 1, characterized in that: The primary and secondary basic identification and judgment of scanning code recognition and order number recognition on the actual label surface, and when the basic identification is unsuccessful, screening multiple suspicious goods information based on the preset goods backup data specifically includes the following steps: Scanning and identifying the actual label surface to determine whether the scanning and identification is successful; When the code scanning recognition is unsuccessful, the order number recognition is performed on the actual label surface to determine whether the order number recognition is successful; When the order number recognition fails, extract the defect order number information; Based on the preset cargo backup data, the defective order number information is matched with the order number to screen multiple suspicious cargo information.

5. The method based on electronically guided sorting according to claim 1, characterized in that: The guiding sorting control according to the target cargo information specifically includes the following steps: Analyze the target cargo information and determine the cargo sorting direction; Generate sorting control instructions according to the cargo sorting direction; According to the sorting control instruction, guided sorting control is performed on the target sorting goods.

6. A system based on electronically guided sorting, characterized in that: The system includes an appearance recognition processing module, a synchronous shooting recognition module, a primary and secondary basis recognition module, a relative angle recognition module, a label position recognition module and a guidance sorting control module, wherein: The appearance recognition processing module is used to determine the target sorting goods, select the target code scanning camera, perform initial shooting control, obtain the initial shooting image, and perform appearance recognition to determine a pair of clamping surfaces and four suspicious label surfaces; A synchronous shooting and identification module is used to perform clamping and rotation control according to a pair of the clamping surfaces, and synchronously shoot four suspicious label surfaces through the target code scanning camera to identify and determine the actual label surface; The primary and secondary basic identification module is used to perform primary and secondary basic identification and judgment on the actual label surface by scanning code identification and order number identification, and when the basic identification fails, it screens multiple suspicious goods information based on the preset goods backup data; A relative angle recognition module is used to select a neighboring barcode scanning camera, generate and send a collaborative shooting instruction to the neighboring barcode scanning camera, receive a collaborative feedback image, and perform relative angle recognition to determine the target relative angle; The relative angle recognition module selects a neighboring code scanning camera that is located at an adjacent workstation to the target code scanning camera, and obtains the working status data of the neighboring code scanning camera. By analyzing the working status data, the collaborative gap period when the neighboring code scanning camera is in an idle state is selected, and then a collaborative shooting instruction is generated during the collaborative gap period, and the collaborative shooting instruction is sent to the neighboring code scanning camera, so that the neighboring code scanning camera is adjusted to the direction of the target code scanning camera, and collaborative shooting and feedback transmission are performed, and then the collaborative feedback image of the neighboring code scanning camera is received, and the camera edge plane of the target code scanning camera and the cargo edge plane of the target sorted goods are determined by preprocessing and edge feature recognition of the collaborative feedback image, and then the camera edge plane and the cargo edge plane are recognized at a relative angle to determine the target relative angle; A label position recognition module is used to perform clamping rotation adjustment according to the relative angle of the target, obtain a parallel plane image through the target code scanning camera, and perform label position recognition to match the target cargo information from the multiple suspicious cargo information; The label position recognition module clamps and rotates the target sorting goods according to the target relative angle, so that the camera edge plane of the target code scanning camera and the goods edge plane of the target sorting goods are parallel to each other. Then, the actual label surface of the target sorting goods is photographed in parallel through the target code scanning camera to obtain a parallel plane image, and then the spatial position of the label code on the actual label surface is recognized according to the preset basic label features to obtain label position data, and multiple suspicious label positions are extracted from multiple suspicious goods information, and the label position data are matched with the multiple suspicious label positions, and the suspicious goods information that is successfully matched is marked as the target goods information, so that the target goods information of the target sorting goods can be identified; the spatial position of the label code on the actual label surface is recognized, which is the recognition of the minimum distance and relative angle of the four code edges of the label code relative to the four surface edges of the actual label surface, wherein the four code edges are the lines corresponding to the four rectangular edges of the rectangular label code; the four surface edges are the lines corresponding to the four rectangular edges of the rectangular actual label surface of the target sorting goods; The guidance sorting control module is used to perform guidance sorting control according to the target cargo information.

7. The system based on electronically guided sorting according to claim 6, characterized in that: The appearance recognition processing module specifically includes: A target selection unit is used to determine the target sorting goods and select the target scanning camera; An initial shooting control unit, used to perform initial shooting control on the target code scanning camera to obtain an initial shooting image; A three-side recognition unit, used to perform three-side recognition on the target sorting goods according to the initial captured image, determine three target intersecting surfaces, and extract three intersecting surface images; A relative area recognition unit is used to perform relative area recognition on the three intersecting surface images and record the relative areas of the three target intersecting surfaces; The face symmetry analysis selection unit is used to compare the relative areas of the three target intersecting faces, perform face symmetry analysis, and select a pair of clamping faces and four suspicious label faces.

8. A device based on electronically guided sorting, characterized in that: A computer program is stored on the device for electronically guided sorting. When the computer program is executed by a processor, the processor executes the steps of the method for electronically guided sorting according to any one of claims 1 to 5.

Images