Tire sorting method and device

Abstract

The embodiments of this specification provide a tire sorting method and device, wherein the tire sorting method includes: acquiring a sample tire image, marking the sample tire image, and determining a marked image; training based on the marked image and an initial deep learning model to obtain a target deep learning model; acquiring a target tire image, inputting the target tire image into the target deep learning model, and determining a feature position; and sorting tires based on the feature position. By acquiring a sample tire image, marking the sample tire image, and determining a marked image; training based on the marked image and an initial deep learning model to obtain a target deep learning model; acquiring a target tire image, inputting the target tire image into the target deep learning model, and determining a feature position; and sorting tires based on the feature position, automatic tire sorting is achieved, thereby improving sorting efficiency.

Description

Technical Field

[0001] The embodiments of this specification relate to the field of logistics sorting technology, and in particular to a tire sorting method. Background Art

[0002] Tires produced by the tire factory must be stored after passing the inspection. Qualified tires must be conveyed from the inspection workshop to different warehouses according to different models and specifications through the conveyor line. There are key classification information on the tires, such as logo, ply, specification, pattern number, vacuum / non-vacuum;

[0003] Among the application scenarios of OCR technology, tire character recognition is one of the important scenarios. The character identification carried on the tire surface usually reflects some performance and characteristics of the rubber tire on the vulcanization molding assembly line. At present, tire sorting is mostly done manually, but in large-scale production, there are many types and the working environment is complex, so it is difficult to meet the needs by manual labor alone.

[0004] Therefore, a better solution is urgently needed. Summary of the invention

[0005] In view of this, the embodiments of this specification provide a tire sorting method. One or more embodiments of this specification also relate to a tire sorting device, a computing device, a computer-readable storage medium and a computer program to solve the technical defects existing in the prior art.

[0006] According to a first aspect of an embodiment of this specification, a tire sorting method is provided, comprising:

[0007] Acquire a tire sample image, mark the tire sample image, and determine a marked image;

[0008] Perform training based on the labeled images and the initial deep learning model to obtain a target deep learning model;

[0009] Collect the target tire image, input the target tire image into the target deep learning model, and determine the feature location;

[0010] Tires are sorted based on feature locations.

[0011] In a possible implementation, obtaining a tire sample image, marking the tire sample image, and determining a marked image include:

[0012] determining a sample quantity and a sample size, and acquiring tire sample images based on the sample quantity and the sample size;

[0013] Determine a target size, determine a target size sample by marking the tire sample image based on the target size, and mark the target size sample to determine a size marked sample;

[0014] Marking the character area in the tire sample image to determine the character area marking sample;

[0015] A mark image is determined based on the size mark sample and the character area mark sample.

[0016] In one possible implementation, the sample size includes a first size, a second size, and a third size;

[0017] The first size is larger than the second size, and the second size is larger than the third size;

[0018] The target size is equal to the first size.

[0019] In a possible implementation, training is performed based on the labeled image and the initial deep learning model to obtain a target deep learning model, including:

[0020] Perform training based on the region labeled samples and the initial deep learning model to determine the region recognition model;

[0021] The target deep learning model is obtained by training based on the character region labeling samples and the region recognition model.

[0022] In a possible implementation, acquiring a target tire image includes:

[0023] When the conveyor belt detects the tire passing by, an initial tire image is acquired through the area array camera;

[0024] The initial tire image is rotated to a set angle to obtain the target tire image.

[0025] In a possible implementation, sorting tires based on feature positions further includes:

[0026] Scaling the target tire image based on the feature position and the sample size to determine a scaled image;

[0027] Tires are sorted based on zoomed images.

[0028] In a possible implementation, the zoomed image is used to sort tires, including:

[0029] Input the scaled image and character library into the target deep learning model to determine the category of the tire;

[0030] Tires are sorted based on their categories.

[0031] According to a second aspect of an embodiment of this specification, a tire sorting device is provided, comprising:

[0032] An image determination module is configured to obtain a tire sample image, mark the tire sample image, and determine a marked image;

[0033] A model training module is configured to perform training based on the labeled image and the initial deep learning model to obtain a target deep learning model;

[0034] An image acquisition module is configured to acquire a target tire image, input the target tire image into a target deep learning model, and determine a feature location;

[0035] The tire sorting module is configured to sort the tires based on the characteristic positions.

[0036] According to a third aspect of an embodiment of this specification, a computing device is provided, including:

[0037] Memory and processor;

[0038] The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the above tire sorting method are implemented.

[0039] According to a fourth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores computer-executable instructions, and when the instructions are executed by a processor, the steps of the above tire sorting method are implemented.

[0040] According to a fifth aspect of the embodiments of this specification, a computer program is provided, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above tire sorting method.

[0041] The embodiments of this specification provide a tire sorting method and device, wherein the tire sorting method includes: acquiring a sample tire image, marking the sample tire image, and determining a marked image; training based on the marked image and an initial deep learning model to obtain a target deep learning model; acquiring a target tire image, inputting the target tire image into the target deep learning model, and determining a feature position; and sorting tires based on the feature position. By acquiring a sample tire image, marking the sample tire image, and determining a marked image; training based on the marked image and an initial deep learning model to obtain a target deep learning model; acquiring a target tire image, inputting the target tire image into the target deep learning model, and determining a feature position; and sorting tires based on the feature position, automatic tire sorting is achieved, thereby improving sorting efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a scene schematic diagram of a tire sorting method provided by an embodiment of this specification;

[0043] Figure 2 is a flow chart of a tire sorting method provided by one embodiment of this specification;

[0044] Figure 3 It is a hardware structure diagram of a tire sorting method provided by an embodiment of this specification;

[0045] Figure 4 It is a structural schematic diagram of a tire sorting device provided by an embodiment of this specification;

[0046] Figure 5 It is a structural block diagram of a computing device provided by an embodiment of this specification. DETAILED DESCRIPTION

[0047] Many specific details are described in the following description to facilitate a full understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of this specification, so this specification is not limited to the specific implementation disclosed below.

[0048] The terms used in one or more embodiments of this specification are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of this specification. The singular forms of "a" and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0049] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0050] In this specification, a tire sorting method is provided. This specification also relates to a tire sorting device, a computing device, and a computer-readable storage medium, which are described in detail one by one in the following embodiments.

[0051] See also Figure 1 , Figure 1 A schematic diagram of a tire sorting method provided according to an embodiment of the present specification is shown.

[0052] exist Figure 1 In the application scenario of , the computing device 101 can obtain a sample tire image, mark the sample tire image, and determine a marked image 102. Then, the computing device 101 can perform training based on the marked image 102 and the initial deep learning model to obtain a target deep learning model 103. After that, the computing device 101 can collect a target tire image, input the target tire image into the target deep learning model 103, and determine a feature position 104. Finally, the computing device 101 can sort the tires based on the feature position 104, as shown by reference numeral 105.

[0053] It should be noted that the computing device 101 can be hardware or software. When the computing device 101 is hardware, it can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or it can be implemented as a single server or a single terminal device. When the computing device 101 is embodied as software, it can be installed in the hardware devices listed above. It can be implemented as multiple software or software modules for providing distributed services, for example, or it can be implemented as a single software or software module. No specific limitation is made here.

[0054] See also Figure 2 , Figure 2 A flow chart of a tire sorting method provided according to an embodiment of the present specification is shown, which specifically includes the following steps.

[0055] Step 201: Acquire a tire sample image, mark the tire sample image, and determine a marked image.

[0056] In a possible implementation, a tire sample image is obtained, the tire sample image is marked, and a marked image is determined, including: determining a sample quantity and a sample size, and obtaining a tire sample image based on the sample quantity and the sample size; determining a target size, marking the tire sample image based on the target size to determine a target size sample, and marking the target size sample to determine a size marked sample; marking a character area in the tire sample image to determine a character area marked sample; and determining a marked image based on the size marked sample and the character area marked sample.

[0057] The sample size includes a first size, a second size and a third size; the first size is larger than the second size, and the second size is larger than the third size; and the target size is equal to the first size.

[0058] In practical applications, see Figure 3 , the hardware may include the following devices.

[0059] Area array camera: The area array camera is used to capture the surface image of the tire and transmit the image to the industrial computer.

[0060] Square long throw light: The square long throw light is composed of four single long throw lights of the same length. The secondary light source is used to illuminate the tire surface to form a clear image. The secondary light source is used to evenly illuminate the tire surface through a reflective effect through counter-reflection, which is not easy to form overexposure or insufficient brightness, thereby ensuring the imaging effect of the image collected by the area array camera.

[0061] Laser sensor 1: measures the tire diameter in conjunction with the encoder. When the laser sensor 1 is triggered for the first time when the tire is transported from the conveyor belt, the encoder data is reset once, and then the encoder data is immediately recorded until the laser sensor 1 signal stops triggering, and then the tire diameter is calculated. The laser sensor is installed on the main conveyor belt, at a certain distance from the camera, which is greater than 1.5 times the maximum tire diameter.

[0062] Laser sensor 2: triggers tire diameter data transmission; when the tire passes the first laser sensor, the tire continues to move forward and triggers the second laser sensor 2 to trigger the data transmission signal, ensuring that the vertical center of the tire coincides with the vertical center of the camera, and then collects the image.

[0063] Auxiliary center device: used to assist in conveying the center line of the tire, and try to coincide with the horizontal center of the camera to ensure the effect of image acquisition.

[0064] Encoder: used to calculate the distance the drive belt moves and record tire data at the same time.

[0065] Industrial computer: used for image processing, image labeling, image deep learning and other related data processing.

[0066] Specifically, first collect tire images as samples, collect the tire models that need to be identified, and collect three different diameter models within the field of view of the area array camera, the smallest, largest, and medium, and collect no less than 20 pictures of each type. Use the image marking tool to mark any image with the largest diameter; mark the character information that needs to be identified into different areas, so that the characters are divided into different areas; after marking and training are completed, automatic recognition can be performed.

[0067] The embodiments of this specification collect images of tires of different sizes so that tires of different sizes can be subsequently identified, and different areas in the tire are collected to achieve accurate identification of the tire position.

[0068] Step 202: Perform training based on the labeled image and the initial deep learning model to obtain a target deep learning model.

[0069] In one possible implementation, training is performed based on labeled images and an initial deep learning model to obtain a target deep learning model, including: training based on region labeled samples and an initial deep learning model to determine a region recognition model; training based on character region labeled samples and a region recognition model to obtain a target deep learning model.

[0070] In practical applications, deep learning is performed on the common feature points of tires for the collected batch images so that the target deep learning model has the function of target positioning and detection. At the same time, deep learning is performed on different areas to enable different types of tires to be identified.

[0071] Step 203: Capture a target tire image, input the target tire image into a target deep learning model, and determine feature locations.

[0072] In a possible implementation, capturing a target tire image includes: acquiring an initial tire image through an area array camera when a conveyor belt detects that a tire has passed; and rotating the initial tire image to a set angle to obtain a target tire image.

[0073] In practical applications, after the tire image is collected on the assembly line, the pre-processed image is automatically rotated to a fixed angle in the software, that is, the target is located and the target features are found.

[0074] Step 204: sorting the tires based on the characteristic positions.

[0075] In a possible implementation, sorting the tires based on the feature positions further includes: scaling the target tire image based on the feature positions and the sample size to determine the scaled image; and sorting the tires based on the scaled image.

[0076] Specifically, the zoomed image is used to sort the tires, including: inputting the zoomed image and the character library into the target deep learning model to determine the category of the tires; and sorting the tires based on the category of the tires.

[0077] In actual applications, in order to adapt to tires of different diameters, the software can scale the marked position proportionally based on the proportional scaling function to locate the area that needs to be detected. When detecting a fixed position, the character library inside the software can realize the recognition of ordinary text, images and special characters, and display the recognized content at the required position, and send the content to the processing device to realize tire sorting to different conveyor belts.

[0078] The embodiments of this specification provide a tire sorting method and device, wherein the tire sorting method includes: acquiring a sample tire image, marking the sample tire image, and determining a marked image; training based on the marked image and an initial deep learning model to obtain a target deep learning model; acquiring a target tire image, inputting the target tire image into the target deep learning model, and determining a feature position; and sorting tires based on the feature position. By acquiring a sample tire image, marking the sample tire image, and determining a marked image; training based on the marked image and an initial deep learning model to obtain a target deep learning model; acquiring a target tire image, inputting the target tire image into the target deep learning model, and determining a feature position; and sorting tires based on the feature position, automatic tire sorting is achieved, thereby improving sorting efficiency.

[0079] Corresponding to the above method embodiment, this specification also provides a tire sorting device embodiment, Figure 4 FIG. 1 is a schematic diagram showing the structure of a tire sorting device provided by an embodiment of the present specification. Figure 4 As shown, the device comprises:

[0080] The image determination module 401 is configured to obtain a tire sample image, mark the tire sample image, and determine a marked image;

[0081] A model training module 402 is configured to perform training based on the labeled image and the initial deep learning model to obtain a target deep learning model;

[0082] An image acquisition module 403 is configured to acquire a target tire image, input the target tire image into a target deep learning model, and determine a feature position;

[0083] The tire sorting module 404 is configured to sort the tires based on the characteristic locations.

[0084] In a possible implementation, the image determination module 401 is further configured to:

[0085] determining a sample quantity and a sample size, and acquiring tire sample images based on the sample quantity and the sample size;

[0086] Determine a target size, determine a target size sample by marking the tire sample image based on the target size, and mark the target size sample to determine a size marked sample;

[0087] Marking the character area in the tire sample image to determine the character area marking sample;

[0088] A mark image is determined based on the size mark sample and the character area mark sample.

[0089] In a possible implementation, the image determination module 401 is further configured to:

[0090] The sample size includes a first size, a second size, and a third size;

[0091] The first size is larger than the second size, and the second size is larger than the third size;

[0092] The target size is equal to the first size.

[0093] In a possible implementation, the model training module 402 is further configured to:

[0094] Perform training based on the region labeled samples and the initial deep learning model to determine the region recognition model;

[0095] The target deep learning model is obtained by training based on the character region labeling samples and the region recognition model.

[0096] In a possible implementation, the image acquisition module 403 is further configured to:

[0097] When the conveyor belt detects the tire passing by, an initial tire image is acquired through the area array camera;

[0098] The initial tire image is rotated to a set angle to obtain the target tire image.

[0099] In a possible implementation, the tire sorting module 404 is further configured to:

[0100] Scaling the target tire image based on the feature position and the sample size to determine a scaled image;

[0101] Tires are sorted based on zoomed images.

[0102] In a possible implementation, the tire sorting module 404 is further configured to:

[0103] Input the scaled image and character library into the target deep learning model to determine the category of the tire;

[0104] Tires are sorted based on their categories.

[0105] The embodiments of this specification provide a tire sorting method and device, wherein the tire sorting device comprises: acquiring a sample tire image, marking the sample tire image, and determining a marked image; training based on the marked image and an initial deep learning model to obtain a target deep learning model; acquiring a target tire image, inputting the target tire image into the target deep learning model, and determining a feature position; and sorting tires based on the feature position. By acquiring a sample tire image, marking the sample tire image, and determining a marked image; training based on the marked image and an initial deep learning model to obtain a target deep learning model; acquiring a target tire image, inputting the target tire image into the target deep learning model, and determining a feature position; and sorting tires based on the feature position, automatic tire sorting is achieved, thereby improving sorting efficiency.

[0106] The above is a schematic scheme of a tire sorting device of this embodiment. It should be noted that the technical scheme of the tire sorting device and the technical scheme of the above tire sorting method belong to the same concept, and the details not described in detail in the technical scheme of the tire sorting device can be referred to the description of the technical scheme of the above tire sorting method.

[0107] Figure 5 The structure block diagram of a computing device 500 provided according to an embodiment of the present specification is shown. The components of the computing device 500 include but are not limited to a memory 510 and a processor 520. The processor 520 is connected to the memory 510 via a bus 530, and the database 550 is used to store data.

[0108] The computing device 500 also includes an access device 540 that enables the computing device 500 to communicate via one or more networks 560. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 540 may include one or more of any type of network interface (e.g., a network interface card (NIC)) that is wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a world-wide interoperability for microwave access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, and a near field communication (NFC).

[0109] In one embodiment of the present specification, the above components of the computing device 500 and Figure 5 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Figure 5 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0110] The computing device 500 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or a personal computer (PC). The computing device 500 may also be a mobile or stationary server.

[0111] The processor 520 is used to execute the following computer executable instructions, which implement the steps of the above tire sorting method when executed by the processor. The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the above tire sorting method belong to the same concept, and the details of the technical scheme of the computing device that are not described in detail can all be referred to the description of the technical scheme of the above tire sorting method.

[0112] An embodiment of the present specification further provides a computer-readable storage medium storing computer-executable instructions, which can implement the steps of the above tire sorting method when executed by a processor.

[0113] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the above tire sorting method belong to the same concept, and the details not described in detail in the technical scheme of the storage medium can be referred to the description of the technical scheme of the above tire sorting method.

[0114] An embodiment of the present specification further provides a computer program, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above tire sorting method.

[0115] The above is a schematic scheme of a computer program of this embodiment. It should be noted that the technical scheme of the computer program and the technical scheme of the above tire sorting method belong to the same concept, and the details not described in detail in the technical scheme of the computer program can be referred to the description of the technical scheme of the above tire sorting method.

[0116] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0117] The computer instructions include computer program codes, which may be in source code form, object code form, executable files or some intermediate forms, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0118] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.

[0119] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0120] The preferred embodiments of this specification disclosed above are only used to help explain this specification. The optional embodiments do not describe all the details in detail, nor do they limit the invention to only the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that technicians in the relevant technical field can well understand and use this specification. This specification is only limited by the claims and their full scope and equivalents.

Claims

1. A tire sorting method, characterized in that: include: Acquire a tire sample image, mark the tire sample image, and determine a marked image; Performing training based on the labeled image and the initial deep learning model to obtain a target deep learning model; Collecting a target tire image, inputting the target tire image into the target deep learning model, and determining a feature position; sorting the tires based on the characteristic positions; The step of acquiring a tire sample image, marking the tire sample image, and determining a marked image includes: Determine a sample quantity and a sample size, and acquire a tire sample image based on the sample quantity and the sample size; Determine a target size, determine a target size sample by marking the tire sample image based on the target size, and mark the target size sample to determine a size mark sample; Marking the character area in the tire sample image to determine a character area marking sample; determining a mark image based on the size mark sample and the character area mark sample; The training based on the labeled image and the initial deep learning model to obtain a target deep learning model includes: Performing training based on the size-labeled samples and the initial deep learning model to determine a region recognition model; Training is performed based on the character region labeling samples and the region recognition model to obtain a target deep learning model.

2. The method according to claim 1, characterized in that The sample size includes a first size, a second size, and a third size; The first size is larger than the second size, and the second size is larger than the third size; The target size is equal to the first size.

3. The method according to claim 1, characterized in that The collecting of the target tire image comprises: When the conveyor belt detects the tire passing by, an initial tire image is acquired through the area array camera; The initial tire image is rotated to a set angle to obtain a target tire image.

4. The method according to claim 1, characterized in that: The step of sorting the tires based on the characteristic positions further comprises: Scaling the target tire image based on the feature position and the sample size to determine a scaled image; Tires are sorted based on the zoomed image.

5. The method according to claim 4, characterized in that The step of sorting tires by using the zoomed image comprises: Inputting the zoomed image and the character library into the target deep learning model to determine the category of the tire; The tires are sorted based on the categories of the tires.

6. A tire sorting device, used to implement the steps of the tire sorting method according to any one of claims 1 to 5, characterized in that: include: An image determination module is configured to obtain a tire sample image, mark the tire sample image, and determine a marked image; A model training module is configured to perform training based on the labeled image and the initial deep learning model to obtain a target deep learning model; An image acquisition module is configured to acquire a target tire image, input the target tire image into the target deep learning model, and determine a feature position; The tire sorting module is configured to sort the tires based on the characteristic positions.

7. A computing device, characterized in that include: Memory and processor; The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the tire sorting method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement the steps of the tire sorting method according to any one of claims 1 to 5.

Images