Pre-sorting judgment method and system based on visual inspection

Abstract

The invention is suitable for the technical field of visual inspection, and provides a pre-sorting judgment method and system based on visual inspection. According to the invention, basic transmission control is carried out by receiving sorting planning information; performing basic shooting on the target material package to obtain basic shooting data; based on a visual detection technology, carrying out information identification on the basic shooting data, and judging whether the information identification is successful or not; when the information identification succeeds, sorting processing is directly carried out on the target material package; and when information identification fails, binocular shooting and appearance identification are carried out on the target material package, and sorting processing is carried out on the target material package. According to the technical scheme, basic shooting and information identification can be carried out, direct sorting processing is carried out when information identification succeeds, binocular shooting and appearance identification are carried out when information identification fails, and then sorting processing is carried out, so that sorting judgment processing can be carried out under the conditions of label defect, label shielding and the like, and the actual use effect is effectively improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of visual inspection, and in particular relates to a pre-sorting determination method and system based on visual inspection. Background Art

[0002] Visual inspection is a process that uses machine vision technology and algorithms to analyze, process and understand image or video content. It mainly relies on computers and related image processing software to simulate the visual function of the human eye and realize the recognition and detection of object shape, size, color, position, texture and other features.

[0003] In the prior art, pre-sorting judgment based on visual detection can only identify the label information affixed to the material packaging, and then perform sorting judgment processing. However, in actual application, sorting judgment processing cannot be performed for situations such as label defect or label obstruction, which affects actual use. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide a pre-sorting determination method and system based on visual detection, 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 pre-sorting determination method based on visual detection, the method specifically comprising the following steps:

[0007] Receive sorting planning information and perform basic transmission control;

[0008] Conduct real-time infrared monitoring to determine the target material packages entering the preset target sorting space, and perform basic photography on the target material packages to obtain basic photography data;

[0009] Based on visual detection technology, information recognition is performed on the basic shooting data to determine whether the information recognition is successful;

[0010] When the information recognition is successful, the target material packaging is directly sorted;

[0011] When information recognition fails, binocular photography and appearance recognition are performed on the target material packaging, and the target material packaging is sorted.

[0012] As a further limitation of the technical solution of the embodiment of the present invention, the receiving of sorting planning information and performing basic transmission control specifically includes the following steps:

[0013] Receive sorting planning information;

[0014] Identify the sorting planning information to determine the target sorting equipment and the planned sorting parameters;

[0015] According to the planned sorting parameters, perform basic drive control on the target sorting equipment.

[0016] As a further limitation of the technical solution of the embodiment of the present invention, the steps of performing real-time infrared monitoring to determine the target material package entering the preset target sorting space, and performing basic shooting on the target material package to obtain basic shooting data specifically include the following steps:

[0017] Perform real-time infrared monitoring to obtain infrared monitoring data;

[0018] Perform real-time analysis on the infrared monitoring data to determine the target material package entering the preset target sorting space;

[0019] Generate a basic shooting instruction;

[0020] According to the basic shooting instruction, perform basic shooting on the target material package to obtain basic shooting data.

[0021] As a further limitation of the technical solution of the embodiment of the present invention, the steps of performing information recognition on the basic shooting data based on visual detection technology to determine whether information recognition is successful specifically include the following steps:

[0022] Based on visual detection technology, perform visual detection control;

[0023] Perform region recognition on the basic shooting data to determine the material information region;

[0024] Perform information recognition on the material information region to obtain the region information content;

[0025] Based on the preset material backup information, perform matching recognition on the region information content to determine whether information recognition is successful.

[0026] As a further limitation of the technical solution of the embodiment of the present invention, the steps of directly performing sorting processing on the target material package when information recognition is successful specifically include the following steps:

[0027] When information recognition is successful, determine the pre-sorting direction of the target material package;

[0028] According to the pre-sorting direction, generate a pre-sorting processing instruction;

[0029] According to the pre-sorting processing instruction, directly perform sorting processing on the target material package.

[0030] As a further limitation of the technical solution of the embodiment of the present invention, when the information recognition fails, binocular shooting and shape recognition are performed on the target material package, and the sorting process of the target material package specifically includes the following steps:

[0031] When the information recognition fails, binocular shooting is performed on the target material package to obtain binocular shooting data;

[0032] Shape recognition is performed on the binocular shooting data to obtain package shape data;

[0033] Based on the preset material backup information, matching recognition is performed on the package shape data to determine the pre-sorting direction of the target material package;

[0034] According to the pre-sorting direction, a pre-sorting processing instruction is generated;

[0035] According to the pre-sorting processing instruction, the sorting process of the target material package is performed.

[0036] A pre-sorting determination system based on visual detection, the system includes a basic transmission control module, an infrared monitoring and shooting module, an information recognition and judgment module, a direct sorting processing module, and a binocular shooting and recognition module, wherein:

[0037] The basic transmission control module is used to receive sorting planning information and perform basic transmission control;

[0038] The infrared monitoring and shooting module is used to perform real-time infrared monitoring, determine the target material package entering the preset target sorting space, and perform basic shooting on the target material package to obtain basic shooting data;

[0039] The information recognition and judgment module is used to perform information recognition on the basic shooting data based on visual detection technology to judge whether the information recognition is successful;

[0040] The direct sorting processing module is used to directly perform the sorting process on the target material package when the information recognition is successful;

[0041] The binocular shooting and recognition module is used to perform binocular shooting and shape recognition on the target material package when the information recognition fails, and perform the sorting process on the target material package.

[0042] As a further limitation of the technical solution of the embodiment of the present invention, the infrared monitoring and shooting module specifically includes:

[0043] The infrared monitoring unit is used to perform real-time infrared monitoring to obtain infrared monitoring data;

[0044] A real-time analysis unit for performing real-time analysis on the infrared monitoring data to determine the target material package entering a preset target sorting space;

[0045] A basic shooting instruction generation unit for generating basic shooting instructions;

[0046] A basic shooting unit for performing basic shooting on the target material package according to the basic shooting instructions to obtain basic shooting data.

[0047] As a further limitation of the technical solution of the embodiment of the present invention, the information recognition and judgment module specifically includes:

[0048] A visual detection control unit for performing visual detection control based on visual detection technology;

[0049] An area recognition unit for performing area recognition on the basic shooting data to determine the material information area;

[0050] An information recognition unit for performing information recognition on the material information area to obtain the area information content;

[0051] A content matching and recognition unit for performing matching recognition on the area information content based on preset material backup information to determine whether information recognition is successful.

[0052] As a further limitation of the technical solution of the embodiment of the present invention, the binocular shooting and recognition module specifically includes:

[0053] A binocular shooting unit for performing binocular shooting on the target material package when information recognition fails to obtain binocular shooting data;

[0054] An appearance recognition unit for performing appearance recognition on the binocular shooting data to obtain packaging appearance data;

[0055] An appearance matching and recognition unit for performing matching recognition on the packaging appearance data based on preset material backup information to determine the pre-sorting direction of the target material package;

[0056] A pre-sorting processing instruction generation unit for generating a pre-sorting processing instruction according to the pre-sorting direction;

[0057] A sorting processing unit for performing sorting processing on the target material package according to the pre-sorting processing instruction.

[0058] Compared with the prior art, the beneficial effects of the present invention are:

[0059] In an embodiment of the present invention, by receiving sorting planning information, basic transmission control is performed; basic shooting is carried out on the target material packaging to obtain basic shooting data; based on visual detection technology, information recognition is performed on the basic shooting data to determine whether information recognition is successful; when information recognition is successful, direct sorting processing is performed on the target material packaging; when information recognition fails, binocular shooting and shape recognition are performed on the target material packaging, and sorting processing is performed on the target material packaging. It is possible to perform basic shooting and information recognition. When information recognition is successful, direct sorting processing is carried out, and when information recognition fails, binocular shooting and shape recognition are performed, and then sorting processing is carried out, so that sorting determination processing can be carried out even in cases such as damaged signs and blocked signs, effectively improving the actual use effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 FIG. shows a flowchart of a pre-sorting determination method based on visual detection provided by an embodiment of the present invention;

[0061] Figure 2 FIG. shows a flowchart of performing basic transmission control in the method provided by an embodiment of the present invention;

[0062] Figure 3 FIG. shows a flowchart of obtaining basic shooting data in the method provided by an embodiment of the present invention;

[0063] Figure 4 FIG. shows a flowchart of determining successful information recognition in the method provided by an embodiment of the present invention;

[0064] Figure 5 FIG. shows a flowchart of directly performing sorting processing in the method provided by an embodiment of the present invention;

[0065] Figure 6 FIG. shows a flowchart of binocular shooting and shape recognition in the method provided by an embodiment of the present invention;

[0066] Figure 7 FIG. shows an application architecture diagram of a pre-sorting determination system based on visual detection provided by an embodiment of the present invention;

[0067] Figure 8 FIG. shows a structural block diagram of an infrared monitoring shooting module in the system provided by an embodiment of the present invention;

[0068] Figure 9 FIG. shows a structural block diagram of an information recognition judgment module in the system provided by an embodiment of the present invention;

[0069] Figure 10 FIG. shows a structural block diagram of a binocular shooting and recognition module in the system provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0070] 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.

[0071] It is understandable that in the prior art, pre-sorting judgment based on visual detection can only identify the label information affixed to the material packaging, and then perform sorting judgment processing. However, in actual application, for abnormal situations such as label missing, label obstruction, etc., sorting judgment processing cannot be performed, thus affecting actual use.

[0072] In order to solve the above problems, the embodiment of the present invention discloses a pre-sorting judgment method and system based on visual detection, which receives sorting planning information to perform basic transmission control; performs real-time infrared monitoring to determine the target material packaging that enters the preset target sorting space, and performs basic photography of the target material packaging to obtain basic photography data; based on visual detection technology, performs information recognition on the basic photography data to determine whether the information recognition is successful; when the information recognition is successful, directly sort the target material packaging; when the information recognition fails, binocular photography and appearance recognition are performed on the target material packaging, and the target material packaging is sorted. It is capable of performing basic photography and information recognition, and when the information recognition is successful, direct sorting is performed, and when the information recognition fails, binocular photography and appearance recognition are performed, and then sorting is performed, so that sorting judgment can be performed even in the case of missing or blocked signs, effectively improving the actual use effect.

[0073] Specifically, Figure 1 The flowchart of the pre-sorting determination method based on visual detection provided by an embodiment of the present invention is shown.

[0074] In a preferred embodiment of the present invention, a pre-sorting determination method based on visual detection comprises the following steps:

[0075] Step S101, receiving sorting planning information and performing basic transmission control.

[0076] In an embodiment of the present invention, when it is necessary to sort and process packaged materials, sorting planning information can be uploaded, and the sorting planning information can be received and then identified to determine the target sorting equipment for sorting and the corresponding planned sorting parameters, and then basic transmission control can be performed on the target sorting equipment according to the planned sorting parameters.

[0077] It can be understood that the planning of sorting parameters includes running speed, sorting category, sorting direction, etc.

[0078] Specifically, Figure 2The flowchart of the basic drive control in the method provided by the embodiment of the present invention is shown.

[0079] Wherein, in another preferred embodiment provided by the present invention, the receiving the sorting planning information and performing the basic drive control specifically includes the following steps:

[0080] Step S1011: Receive the sorting planning information;

[0081] Step S1012: Identify the sorting planning information to determine the target sorting equipment and the planned sorting parameters;

[0082] Step S1013: Perform basic drive control on the target sorting equipment according to the planned sorting parameters.

[0083] Furthermore, the pre-sorting determination method based on visual detection further includes the following steps:

[0084] Step S102: Perform real-time infrared monitoring to determine the target material package entering the preset target sorting space, and perform basic shooting on the target material package to obtain basic shooting data.

[0085] In the embodiment of the present invention, real-time infrared monitoring is performed on the target sorting equipment to obtain infrared monitoring data, and then the infrared monitoring data is analyzed in real time to determine the target material package entering the preset target sorting space, generate a basic shooting instruction, and further respond to the basic shooting instruction to shoot the upper end surface of the target material package entering the target sorting space to obtain basic shooting data.

[0086] Specifically, Figure 3 The flowchart of obtaining the basic shooting data in the method provided by the embodiment of the present invention is shown.

[0087] Wherein, in another preferred embodiment provided by the present invention, the performing real-time infrared monitoring, determining the target material package entering the preset target sorting space, and performing basic shooting on the target material package to obtain basic shooting data specifically includes the following steps:

[0088] Step S1021: Perform real-time infrared monitoring to obtain infrared monitoring data;

[0089] Step S1022: Analyze the infrared monitoring data in real time to determine the target material package entering the preset target sorting space;

[0090] Step S1023: Generate a basic shooting instruction;

[0091] Step S1024: Perform basic shooting on the target material package according to the basic shooting instruction to obtain basic shooting data.

[0092] Furthermore, the pre-sorting determination method based on visual detection further includes the following steps:

[0093] Step S103: Based on visual detection technology, perform information recognition on the basic shooting data to determine whether information recognition is successful.

[0094] In the embodiment of the present invention, based on visual detection technology, visual detection control is performed, and then region recognition is performed on the basic shooting data to determine the material information region on the upper end face of the target material package. Then, information recognition is performed on the material information region to obtain the regional information content. Based on the preset material backup information, matching recognition is performed on the regional information content to determine whether information recognition is successful.

[0095] It can be understood that in the material backup information, there are internal numbers of different types of materials. In the regional information content, there may be the internal number of the corresponding material in the target material package. Therefore, multiple internal numbers in the material backup information can be used to match the possible internal numbers in the regional information content. If the match is successful, the information recognition is successful; if the match fails, the information recognition fails.

[0096] It can be understood that there may be no material information region on the upper end face of the target material package. At this time, the regional information content is blank, so the match fails and the information recognition fails.

[0097] Specifically, Figure 4 Fig. shows the flowchart for judging successful information recognition in the method provided by the embodiment of the present invention.

[0098] Among them, in another preferred embodiment provided by the present invention, the step of performing information recognition on the basic shooting data based on visual detection technology to determine whether information recognition is successful specifically includes the following steps:

[0099] Step S1031: Based on visual detection technology, perform visual detection control;

[0100] Step S1032: Perform region recognition on the basic shooting data to determine the material information region;

[0101] Step S1033: Perform information recognition on the material information region to obtain the regional information content;

[0102] Step S1034: Based on the preset material backup information, perform matching recognition on the regional information content to determine whether information recognition is successful.

[0103] Furthermore, the pre-sorting determination method based on visual detection further includes the following steps:

[0104] Step S104: When the information recognition is successful, directly perform sorting processing on the target material package.

[0105] In an embodiment of the present invention, when the information recognition is successful, according to the planned sorting parameters, determine the pre-sorting direction of the target material package, and then generate a corresponding pre-sorting processing instruction according to the pre-sorting direction. Furthermore, according to the pre-sorting processing instruction, directly perform sorting processing on the target material package, and push the target material package in the pre-sorting direction to achieve sorting.

[0106] Specifically, Figure 5 FIG. shows a flowchart of directly performing sorting processing in the method provided by the embodiment of the present invention.

[0107] Among them, in another preferred embodiment provided by the present invention, the step of directly performing sorting processing on the target material package when the information recognition is successful specifically includes the following steps:

[0108] Step S1041: When the information recognition is successful, determine the pre-sorting direction of the target material package;

[0109] Step S1042: Generate a pre-sorting processing instruction according to the pre-sorting direction;

[0110] Step S1043: Directly perform sorting processing on the target material package according to the pre-sorting processing instruction.

[0111] Furthermore, the pre-sorting determination method based on visual detection further includes the following steps:

[0112] Step S105: When the information recognition fails, perform binocular shooting and shape recognition on the target material package, and perform sorting processing on the target material package.

[0113] In an embodiment of the present invention, when the information recognition fails, perform binocular shooting on the target material package to obtain binocular shooting data of the target material package, then perform shape recognition on the binocular shooting data to obtain package shape data, and based on the preset material backup information, perform matching recognition on the package shape data to determine the category of the material in the target material package, determine the corresponding pre-sorting direction, and then generate a corresponding pre-sorting processing instruction according to the pre-sorting direction. Furthermore, according to the pre-sorting processing instruction, perform sorting processing on the target material package, and push the target material package in the pre-sorting direction to achieve sorting.

[0114] It can be understood that in the material backup information, there are shape dimension data such as length, width, and height of different types of materials in a packaged state.

[0115] Specifically, Figure 6The flowchart of binocular shooting and shape recognition in the method provided by the embodiment of the present invention is shown.

[0116] Wherein, in another preferred embodiment provided by the present invention, when the information recognition fails, binocular shooting and shape recognition are performed on the target material package, and the specific steps of sorting the target material package are as follows:

[0117] Step S1051: When the information recognition fails, perform binocular shooting on the target material package to obtain binocular shooting data;

[0118] Step S1052: Perform shape recognition on the binocular shooting data to obtain package shape data;

[0119] Step S1053: Based on the preset material backup information, perform matching recognition on the package shape data to determine the pre-sorting direction of the target material package;

[0120] Step S1054: Generate a pre-sorting processing instruction according to the pre-sorting direction;

[0121] Step S1055: Sort the target material package according to the pre-sorting processing instruction.

[0122] Furthermore, Figure 7 The application architecture diagram of the pre-sorting determination system based on visual detection provided by the embodiment of the present invention is shown.

[0123] Specifically, in another preferred embodiment provided by the present invention, a pre-sorting determination system based on visual detection includes:

[0124] The basic transmission control module 101 is used to receive sorting planning information and perform basic transmission control.

[0125] In the embodiment of the present invention, when it is necessary to sort the packaged material, the sorting planning information can be uploaded. The basic transmission control module 101 receives the sorting planning information, then identifies the sorting planning information, determines the target sorting device for sorting and the corresponding planned sorting parameters, and then performs basic transmission control on the target sorting device according to the planned sorting parameters.

[0126] The infrared monitoring and shooting module 102 is used to perform real-time infrared monitoring, determine the target material package entering the preset target sorting space, and perform basic shooting on the target material package to obtain basic shooting data.

[0127] In an embodiment of the present invention, the infrared monitoring and shooting module 102 performs real-time infrared monitoring on the target sorting device to obtain infrared monitoring data, and then analyzes the infrared monitoring data in real time to determine the target material package entering the preset target sorting space, generates a basic shooting instruction, and further responds to the basic shooting instruction to shoot the upper end surface of the target material package entering the target sorting space to obtain basic shooting data.

[0128] Specifically, Figure 8 FIG. shows the structural block diagram of the infrared monitoring and shooting module 102 in the system provided by the embodiment of the present invention.

[0129] Among them, in another preferred embodiment provided by the present invention, the infrared monitoring and shooting module 102 specifically includes:

[0130] The infrared monitoring unit 1021 is used to perform real-time infrared monitoring and obtain infrared monitoring data;

[0131] The real-time analysis unit 1022 is used to analyze the infrared monitoring data in real time to determine the target material package entering the preset target sorting space;

[0132] The basic shooting instruction generation unit 1023 is used to generate a basic shooting instruction;

[0133] The basic shooting unit 1024 is used to perform basic shooting on the target material package according to the basic shooting instruction to obtain basic shooting data.

[0134] Furthermore, the pre-sorting determination system based on visual detection further includes:

[0135] The information recognition and judgment module 103 is used to perform information recognition on the basic shooting data based on visual detection technology to judge whether information recognition is successful.

[0136] In an embodiment of the present invention, the information recognition and judgment module 103 performs visual detection control based on visual detection technology, then performs region recognition on the basic shooting data to determine the material information region on the upper end surface of the target material package, and then performs information recognition on the material information region to obtain the regional information content, and matches and recognizes the regional information content based on the preset material backup information to judge whether information recognition is successful.

[0137] Specifically, Figure 9 FIG. shows the structural block diagram of the information recognition and judgment module 103 in the system provided by the embodiment of the present invention.

[0138] Among them, in another preferred embodiment provided by the present invention, the information recognition and judgment module 103 specifically includes:

[0139] The visual detection control unit 1031 is used to perform visual detection control based on visual detection technology;

[0140] The area recognition unit 1032 is used to perform area recognition on the basic shooting data to determine the material information area;

[0141] The information recognition unit 1033 is used to perform information recognition on the material information area to obtain the area information content;

[0142] The content matching and recognition unit 1034 is used to perform matching recognition on the area information content based on the preset material backup information to determine whether the information recognition is successful.

[0143] Furthermore, the pre-sorting determination system based on visual detection further includes:

[0144] The direct sorting processing module 104 is used to directly perform sorting processing on the target material package when the information recognition is successful.

[0145] In an embodiment of the present invention, when the information recognition is successful, the direct sorting processing module 104 determines the pre-sorting direction of the target material package according to the planned sorting parameters, then generates a corresponding pre-sorting processing instruction according to the pre-sorting direction, and further directly performs sorting processing on the target material package according to the pre-sorting processing instruction, and pushes the target material package in the pre-sorting direction to achieve sorting.

[0146] The binocular shooting and recognition module 105 is used to perform binocular shooting and shape recognition on the target material package when the information recognition fails, and perform sorting processing on the target material package.

[0147] In an embodiment of the present invention, when the information recognition fails, the binocular shooting and recognition module 105 performs binocular shooting on the target material package to obtain the binocular shooting data of the target material package, then performs shape recognition on the binocular shooting data to obtain the package shape data, performs matching recognition on the package shape data based on the preset material backup information, determines the category of the material in the target material package, determines the corresponding pre-sorting direction, then generates a corresponding pre-sorting processing instruction according to the pre-sorting direction, and further performs sorting processing on the target material package according to the pre-sorting processing instruction, and pushes the target material package in the pre-sorting direction to achieve sorting.

[0148] Specifically, Figure 10 Fig. shows the structural block diagram of the binocular shooting and recognition module 105 in the system provided by the embodiment of the present invention.

[0149] Among them, in another preferred embodiment provided by the present invention, the binocular shooting and recognition module 105 specifically includes:

[0150] The binocular shooting unit 1051 is configured to perform binocular shooting on the target material package when information recognition fails, and obtain binocular shooting data;

[0151] The shape recognition unit 1052 is configured to perform shape recognition on the binocular shooting data to obtain package shape data;

[0152] The shape matching and recognition unit 1053 is configured to perform matching and recognition on the package shape data based on the preset material backup information to determine the pre-sorting direction of the target material package;

[0153] The pre-sorting processing instruction generation unit 1054 is configured to generate a pre-sorting processing instruction according to the pre-sorting direction;

[0154] The sorting processing unit 1055 is configured to perform sorting processing on the target material package according to the pre-sorting processing instruction.

[0155] It should be understood that although the steps in the flowcharts of the embodiments of the present invention are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps has no strict order limitation, and these steps can be executed in other orders. Moreover, at least a part of the steps in each embodiment may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or sub-steps or stages of other steps.

[0156] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. 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 methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of 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 (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0157] The above-described embodiments merely represent several implementation manners of the present invention. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention should be subject to the appended claims.

Claims

1. A pre-sorting determination method based on visual detection, characterized in that, The method specifically includes the following steps: Receive sorting planning information and perform basic drive control; Perform real-time infrared monitoring, determine the target material package entering the preset target sorting space, and perform basic shooting on the target material package to obtain basic shooting data; Based on visual detection technology, perform information recognition on the basic shooting data to determine whether information recognition is successful; When information recognition is successful, directly perform sorting processing on the target material package; When information recognition fails, perform binocular shooting and shape recognition on the target material package, and perform sorting processing on the target material package.

2. The pre-sorting determination method based on visual detection according to claim 1, wherein The receiving of sorting planning information and performing basic drive control specifically includes the following steps: Receive sorting planning information; Identify the sorting planning information to determine the target sorting equipment and planned sorting parameters; According to the planned sorting parameters, perform basic drive control on the target sorting equipment.

3. The pre-sorting determination method based on visual detection according to claim 1, characterized in that, The performing of real-time infrared monitoring, determining the target material package entering the preset target sorting space, and performing basic shooting on the target material package to obtain basic shooting data specifically includes the following steps: Perform real-time infrared monitoring to obtain infrared monitoring data; Perform real-time analysis on the infrared monitoring data to determine the target material package entering the preset target sorting space; Generate a basic shooting instruction; According to the basic shooting instruction, perform basic shooting on the target material package to obtain basic shooting data.

4. The pre-sorting determination method based on visual detection according to claim 1, characterized in that The performing of information recognition on the basic shooting data based on visual detection technology to determine whether information recognition is successful specifically includes the following steps: Based on visual detection technology, perform visual detection control; Perform region recognition on the basic shooting data to determine the material information region; Perform information recognition on the material information region to obtain the region information content; Based on the preset material backup information, perform matching recognition on the region information content to determine whether information recognition is successful.

5. The pre-sorting determination method based on visual detection according to claim 1, wherein The directly performing of sorting processing on the target material package when information recognition is successful specifically includes the following steps: When information recognition is successful, determine the pre-sorting direction of the target material package; Generate a pre-sorting processing instruction according to the pre-sorting direction; According to the pre-sorting processing instruction, directly perform sorting processing on the target material package.

6. The pre-sorting determination method based on visual detection according to claim 1, characterized in that The performing of binocular shooting and shape recognition on the target material package and performing sorting processing on the target material package when information recognition fails specifically includes the following steps: When information recognition fails, perform binocular shooting on the target material package to obtain binocular shooting data; Perform shape recognition on the binocular shooting data to obtain the package shape data; Based on the preset material backup information, perform matching recognition on the package shape data to determine the pre-sorting direction of the target material package; Generate a pre-sorting processing instruction according to the pre-sorting direction; According to the pre-sorting processing instruction, perform sorting processing on the target material package.

7. A pre-sorting determination system based on visual detection, characterized in that, The system includes a basic drive control module, an infrared monitoring and shooting module, an information recognition and judgment module, a direct sorting processing module, and a binocular shooting and recognition module, where: The basic transmission control module is used to receive sorting planning information and perform basic transmission control; The infrared monitoring and shooting module is used to perform real-time infrared monitoring, determine the target material package entering the preset target sorting space, and perform basic shooting on the target material package to obtain basic shooting data; The information recognition and judgment module is used to perform information recognition on the basic shooting data based on vision detection technology and judge whether information recognition is successful; The direct sorting processing module is used to directly perform sorting processing on the target material package when information recognition is successful; The binocular shooting and recognition module is used to perform binocular shooting and shape recognition on the target material package when information recognition fails, and perform sorting processing on the target material package.

8. The pre-sorting determination system based on visual detection according to claim 7, characterized in that The infrared monitoring and shooting module specifically includes: The infrared monitoring unit is used to perform real-time infrared monitoring and obtain infrared monitoring data; The real-time analysis unit is used to perform real-time analysis on the infrared monitoring data to determine the target material package entering the preset target sorting space; The basic shooting instruction generation unit is used to generate basic shooting instructions; The basic shooting unit is used to perform basic shooting on the target material package according to the basic shooting instructions to obtain basic shooting data.

9. The pre-sorting determination system based on visual detection according to claim 7, wherein The information recognition and judgment module specifically includes: The vision detection control unit is used to perform vision detection control based on vision detection technology; The region recognition unit is used to perform region recognition on the basic shooting data to determine the material information region; The information recognition unit is used to perform information recognition on the material information region to obtain the region information content; The content matching and recognition unit is used to perform matching recognition on the region information content based on the preset material backup information to judge whether information recognition is successful.

10. The pre-sorting determination system based on visual detection according to claim 7, characterized in that, The binocular shooting and recognition module specifically includes: The binocular shooting unit is used to perform binocular shooting on the target material package when information recognition fails to obtain binocular shooting data; The shape recognition unit is used to perform shape recognition on the binocular shooting data to obtain the package shape data; The shape matching and recognition unit is used to perform matching recognition on the package shape data based on the preset material backup information to determine the pre-sorting direction of the target material package; The pre-sorting processing instruction generation unit is used to generate pre-sorting processing instructions according to the pre-sorting direction; The sorting processing unit is used to perform sorting processing on the target material package according to the pre-sorting processing instructions.

Images