A wheel mixed bag detection method and device, model and training method and device

Abstract

This application proposes a wheel mix-up detection method and device, model, and training method and device. The model integrates YOLOv10‑S with a Triplet / Siamese network. The Triplet / Siamese network uses the first 47 layers of ResNet50 as feature extraction layers and incorporates channel and spatial attention mechanisms. The channel attention mechanism performs global max pooling and average pooling on the feature map, which is then input into a shared perceptron; the spatial attention mechanism processes the feature map output by the channel attention mechanism. This model combines the advantages of both networks and improves detection performance through the attention mechanism. After training, the model can accurately identify wheel images, effectively solving the problem of wheel mix-up detection and providing an efficient solution for wheel quality inspection.

Description

Technical Field

[0001] The present application relates to the field of wheel detection, and in particular to a wheel mixed bag detection method and device, a model, and a training method and device. Background Art

[0002] Due to various reasons (such as human error, equipment failure, etc.), wheel mix-ups may occur, that is, wheels of different models or specifications are mistakenly mixed in the same package. This situation not only affects the efficiency of the production line, but may also cause serious quality problems and even endanger driving safety.

[0003] Traditional wheel mix-up detection methods rely primarily on manual inspection, which is not only time-consuming and labor-intensive but also susceptible to human error, resulting in low accuracy and reliability of detection results. With the rapid development of computer vision technology, automated detection methods based on image recognition have become an effective solution to this problem.

[0004] Among existing image recognition technologies, the YOLO (You Only Look Once) model series has garnered widespread attention for its efficiency and accuracy. As a variant of the YOLO family, YOLOv10-S offers faster detection speed and higher accuracy, making it ideal for real-time detection tasks. However, directly applying the YOLOv10-S network to mixed wheel detection can face challenges. Occlusion, varying lighting conditions, and varying angles can lead to poor detection results. Summary of the Invention

[0005] The purpose of this application is to overcome the defects in the above-mentioned prior art and provide a wheel mix-up detection method and device, model and training method and device.

[0006] This application provides a wheel mixed packet detection model, including: YOLOv10-S network and Triplet / Siamesenetwork network;

[0007] The Triplet / Siamese network is connected to the YOLOv10-S network. The Triplet / Siamese network uses the first 47 layers of the ResNet50 network as feature extraction layers, and introduces a channel attention mechanism module and a spatial attention mechanism module.

[0008] The channel attention mechanism module performs global maximum pooling and global average pooling on the feature maps extracted by the feature extraction layer, and inputs them into the shared perceptron; the spatial attention mechanism module processes the feature maps output by the channel attention mechanism module respectively.

[0009] This application also provides a wheel mix-up detection model training method, which is used to train the above-mentioned wheel mix-up detection model, comprising:

[0010] Get a training set of images, including two category labels: complete wheels and occluded wheels;

[0011] Input the image training set into the YOLOv10-S network to obtain bounding boxes and category labels;

[0012] According to the bounding box screenshot of the complete wheel category label, positive sample and negative sample labels are marked to generate a triplet sample, wherein the triplet sample includes an anchor sample, a positive sample, and a negative sample;

[0013] The feature extraction layer extracts the feature map of the triplet sample, including the feature Figure 1 ,feature Figure 2 and features Figure 3 Based on the characteristics Figure 1 ,feature Figure 2 and features Figure 3 Perform global maximum pooling and global average pooling respectively, input into the channel attention mechanism module, and obtain features Figure 1-1 ,feature Figure 2-1 and features Figure 3-1 ; The features are respectively Figure 1-1 ,feature Figure 2-1 and features Figure 3-1 Input into the spatial attention mechanism module to obtain improved features Figure 1 , Improved Features Figure 2 and improved features Figure 3 ;

[0014] The improved features Figure 1 , Improved Features Figure 2 and improved features Figure 3 They are input into the tiled layer and the fully connected layer respectively, and then the loss function is calculated.

[0015] The present application also provides a wheel mix-up detection method, which performs wheel mix-up detection based on the wheel mix-up detection model trained by the wheel mix-up detection model training method, including:

[0016] Input the acquired wheel image into the YOLOv10-S network to obtain the bounding box, confidence, and category of the complete wheel category target;

[0017] Selecting the complete wheel category target whose confidence is above a preset confidence threshold, identifying the complete wheel category target closest to the center point of the wheel image as the anchor target, and setting the other complete wheel category targets as comparison targets;

[0018] The anchor target and the comparison target are scaled, and a plurality of the comparison targets and the anchor target are formed into a matching queue and input into the Triplet / Siamese network to obtain a detection result.

[0019] Optionally, the plurality of comparison targets and the anchor target are combined into a matching queue and input into the Triplet / Siamese network to obtain a detection result, further comprising:

[0020] If the predicted values ​​in the detection results are all less than the prediction threshold, the wheels in the wheel image are identical and no processing is performed;

[0021] If there is a predicted value greater than the prediction threshold in the detection results, the comparison target is marked on the global map and the sound and light alarm is triggered.

[0022] Optionally, in the detection network, the channel attention weight value is directly referenced.

[0023] Optionally, the preset confidence threshold is set to 0.8.

[0024] Optionally, the prediction threshold is set to 0.1.

[0025] The present application also provides a wheel mix-up detection model training device, comprising:

[0026] Get the module and obtain the image training set, including two category labels: complete wheels and occluded wheels;

[0027] The training module inputs the image training set into the YOLOv10-S network to obtain a bounding box and a category label; generates a triplet sample based on the bounding box and the category label, wherein the triplet sample includes an anchor sample, a positive sample, and a negative sample; extracts a feature map of the triplet sample through a feature extraction layer, including feature Figure 1 ,feature Figure 2 and features Figure 3 Based on the characteristics Figure 1 ,feature Figure 2 and features Figure 3 Perform global maximum pooling and global average pooling respectively, input into the channel attention mechanism module, and obtain features Figure 1-1 ,feature Figure 2-1 and features Figure 3-1 ; The features are respectively Figure 1-1 ,feature Figure 2-1 and features Figure 3-1 Input into the spatial attention mechanism module to obtain improved features Figure 1 , Improved Features Figure 2 and improved features Figure 3 ; The improved features Figure 1 , Improved Features Figure 2 and improved features Figure 3 They are input into the tiled layer and the fully connected layer respectively, and then the loss function is calculated.

[0028] The present application also provides a wheel mix-up detection device, comprising:

[0029] The input module inputs the acquired wheel image into the YOLOv10-S network to obtain the bounding box, confidence, and category of the complete wheel category target;

[0030] an identification module, selecting a complete wheel category target whose confidence level is above a preset confidence level threshold, identifying a complete wheel category target closest to the center point of the wheel image as an anchor target, and setting other complete wheel category targets as comparison targets;

[0031] The detection module scales the anchor target and the comparison target, forms a matching queue with multiple comparison targets and anchor targets, and inputs the matching queue into the Triplet / Siamese network to obtain a detection result.

[0032] Optionally, the detection module forms a matching queue with the plurality of comparison targets and the anchor target and inputs the queue into the Triplet / Siamese network to obtain a detection result, further comprising:

[0033] If the predicted values ​​in the detection results are all less than the prediction threshold, the wheels in the wheel image are identical and no processing is performed;

[0034] If there is a predicted value greater than the prediction threshold in the detection results, the comparison target is marked on the global map and the sound and light alarm is triggered.

[0035] Optionally, in the detection network, the channel attention weight value is directly referenced.

[0036] Optionally, the preset confidence threshold is set to 0.8.

[0037] Optionally, the prediction threshold is set to 0.1.

[0038] The beneficial effects of this application are:

[0039] The present application provides a wheel mixed packet detection model, including: a YOLOv10-S network and a Triplet / Siamese network; the Triplet / Siamese network is connected to the YOLOv10-S network, and the Triplet / Siamese network uses the first 47 layers of the ResNet50 network as the feature extraction layer, and introduces a channel attention mechanism module and a spatial attention mechanism module; the channel attention mechanism module performs global maximum pooling and global average pooling on the feature map extracted by the feature extraction layer, and inputs them into a shared perceptron; the spatial attention mechanism module processes the feature map output by the channel attention mechanism module separately. The present application combines the advantages of the YOLOv10-S network and the Triplet / Siamese network, and introduces a channel attention mechanism and a spatial attention mechanism to improve detection performance. By training this model, accurate recognition of wheel images can be achieved, thereby effectively solving the problem of wheel mixed packet detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is a schematic diagram of the wheel mix-up detection model in this application;

[0041] Figure 2 This is the training flow chart of the wheel mixed bag detection model in this application;

[0042] Figure 3 This is a diagram of the Triplet / Siamese network training process in this application;

[0043] Figure 4 This is a schematic diagram of the wheel mixed bag detection process in this application;

[0044] Figure 5 This is a schematic diagram of the Triplet / Siamese network process for wheel mixed packet detection in this application;

[0045] Figure 6 This is a schematic diagram of the wheel mix-up detection model training device in this application;

[0046] Figure 7 It is a schematic diagram of the wheel mixed bag detection model detection device in this application. DETAILED DESCRIPTION

[0047] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, the embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0048] Please refer to Figure 1 As shown, the present application relates to a wheel mixed packet detection model, including: a YOLOv10-S network and a Triplet / Siamese network, each performing a step to realize wheel mixed packet detection.

[0049] The YOLOv10-S network recognizes wheels from the global image captured by the camera.

[0050] The Triplet / Siamese network includes a Triplet network that inputs triplet samples during training and a Siamese network that inputs two groups of samples during the detection phase. The Triplet network and the Siamese network are the same neural network.

[0051] The wheels are placed on a pallet and moved. Considering that the loading process is dynamic, the present application selects wheels that are not blocked and cuts the selected multiple target wheels to form a new picture.

[0052] The Triplet / Siamese network anchors the target crop image closest to the center of the global image, and uses the Triplet / Siamese network (twin neural network) to calculate the similarity of multiple wheel images one by one, and those that exceed the set threshold are judged as.

[0053] The Triplet / Siamese network is connected to the YOLOv10-S network, and the Triplet / Siamese network includes the first 47 layers of the ResNet50 network as feature extraction layers, and also includes a channel attention mechanism module and a spatial attention mechanism module;

[0054] The channel attention mechanism module performs global maximum pooling and global average pooling on the feature maps extracted by the feature extraction layer, and inputs them into the shared perceptron; the spatial attention mechanism module processes the feature maps output by the channel attention mechanism module respectively.

[0055] Please refer to Figure 2 、 Figure 3As shown, the present application also relates to a wheel mixed package detection model training method, comprising:

[0056] S101. Obtain an image training set, including two category labels: complete wheels and occluded wheels;

[0057] Train the YOLOv10-S network to recognize complete wheel category objects.

[0058] Because the loading video is transmitted to the model in real time, in order to distinguish the complete wheel category targets that have been loaded from the complete wheel category targets that are being loaded by the loaders and are blocked, this application uses pictures with two category labels, complete wheels and blocked wheels, for training, so that complete wheel category target pictures can be obtained in subsequent predictions.

[0059] S102: Input the image training set into the YOLOv10-S network to obtain bounding boxes and category labels;

[0060] After the YOLOv10-S network inputs the pictures of the two category labels of the complete wheel and the occluded wheel, it outputs a model weight file (.pt format) for subsequent reasoning of the real-time video stream.

[0061] The YOLOv10-S network output includes a bounding box and a category label, which is passed to the subsequent Triplet / Siamese network for feature extraction.

[0062] S103, generating a triplet sample according to the bounding box and the category label, wherein the triplet sample includes an anchor sample, a positive sample, and a negative sample;

[0063] Based on the complete / occluded wheel ROI (Region of Interest) image patches detected by YOLOv10-S, a triplet of samples (Anchor-Positive-Negative) is generated. The sample includes: Anchor, which is the baseline image of the complete wheel; Positive, which is a complete wheel of the same type (but with different viewing angles / lighting); and Negative, which is an occluded wheel or a complete wheel of another type.

[0064] Normalize and resize to a fixed resolution.

[0065] S104, extracting the feature map of the triple sample through the feature extraction layer, including feature Figure 1 ,feature Figure 2 and features Figure 3 Based on the characteristics Figure 1 ,feature Figure 2 and features Figure 3Perform global maximum pooling and global average pooling respectively, input into the channel attention mechanism module, and obtain features Figure 1-1 ,feature Figure 2-1 and features Figure 3-1 ; The features are respectively Figure 1-1 ,feature Figure 2-1 and features Figure 3-1 Input into the spatial attention mechanism module to obtain improved features Figure 1 , Improved Features Figure 2 and improved features Figure 3 ; The improved features Figure 1 , Improved Features Figure 2 and improved features Figure 3 They are input into the tiled layer and the fully connected layer respectively, and then the loss function is calculated.

[0066] Specifically, a group of three pictures is used as a triplet sample: anchor sample anchor, positive sample posit, and negative sample negative for training.

[0067] The reason for choosing the Triplet / Siamese network is that the loss function is used to make the distance between the same categories as small as possible and the distance between different categories as large as possible, which works better for samples with small differences.

[0068] In this application, the loss function used is the triplet loss function Triplet / Triplet / Siamese loss.

[0069] Triplet / Triplet / Siamese loss distinguishes details in samples and better models them. The goal of the above model is to distinguish wheel images of different wheel types. Most of the differences between wheel types are fine-grained features.

[0070] L=max(d(a,p)-d(a,n)+margin,0)

[0071] Here, "margin" is a preset threshold, a is the anchor sample anchor, d(a,p) and d(a,n) are the distances between positive samples and positive samples, and between positive samples and negative samples in the embedding space, respectively. In this application, Euclidean distance is used.

[0072]

[0073] The Triplet / Siamese network first extracts features from the input image.

[0074] In this application, the first 47 layers of the ResNet50 convolutional neural network are selected for feature map extraction.

[0075] During the training phase, the CBAM convolutional attention module was introduced to extract the feature layers of the image in order to enable the feature detection of the Triplet / Siamese network to focus on the differences in the characteristic structure of the wheel in key areas.

[0076] The CBAM (Convolutional Block Attention Module) module is composed of two small modules in series, one is the channel attention module and the other is the spatial attention module.

[0077] In this application, the Channel Attention Module focuses on which channels (i.e., feature categories) in the feature map are more important to the final result, thereby giving these channels higher weights. The expression is as follows:

[0078]

[0079] The Spatial Attention Module focuses on which spatial locations in the feature map contain more critical information, thereby giving these locations higher weights. The expression is as follows:

[0080]

[0081] Since all three images in the training phase are wheels, theoretically the features that need to be focused on are the same. Therefore, in the channel attention module, the feature maps of the three images are summed by global maximum pooling and global average pooling, and then input into the shared multi-layer perceptron (Share MLP).

[0082] The spatial features cannot be uniformly extracted due to the position, orientation and natural light of the wheels when the picture was taken, so they are input into the spatial attention module for processing.

[0083] Please refer to Figure 4 、 Figure 5 As shown, the present application also provides a wheel mixed package detection method, comprising:

[0084] S201, input the obtained wheel image into the YOLOv10-S network to obtain the bounding box, confidence and category of the complete wheel category target;

[0085] First, input the camera image into the YOLOv10-S network to obtain the bounding box coordinates, confidence level, and category of the complete wheel category target.

[0086] Preferably, considering the actual situation of wheel placement target overlap, the IOU threshold of the YOLO model is most appropriately set to 0.2.

[0087] S202, selecting the complete wheel category target whose confidence level is above a preset threshold, identifying the complete wheel category target closest to the center point of the wheel image as the anchor target, and setting the complete wheel category targets of other vehicles as comparison targets;

[0088] Select objects with a confidence score of 0.8 or higher for the complete wheel category and identify the object closest to the center point as the anchor object. For example, the predicted bounding box (x1, y1, x2, y2) is the coordinates of the top left and bottom right corners, and (w, h) is the width and height of the global image. Iterate through each object's bounding box and calculate d = |w / 2 - (x1 + x1) / 2| + |h / 2 - (y1 + y1) / 2)|. Select the object with the smallest d value. Crop the image based on its bounding box coordinates as the anchor object image. Crop the other predicted objects based on their bounding boxes as well, forming n comparison target images.

[0089] S203 , scaling the anchor target and the comparison target, forming a matching queue with a plurality of the comparison targets and the anchor target, and inputting the queue into the Triplet / Siamese network to obtain a detection result.

[0090] All target images are scaled to a size of 512×512.

[0091] The n comparison target images and the anchor target images are respectively formed into matching pairs and input into the improved Triplet / Siamese network (the model parameters are taken from the results of the corresponding modules of the training model) for prediction.

[0092] In this application, the prediction model graph is different from the training model. Only two pictures are input for comparison. Moreover, due to the single characteristic of the recognition target and the relatively fixed features of the wheel, the channel attention weight value is directly referenced for calculation.

[0093] Finally, the Euclidean distance between the transformed one-dimensional vectors of the two images is calculated.

[0094]

[0095] The prediction result is a value between 0 and 1. The closer the value is to 0, the more similar the two images are. Finally, based on the actual test results, the results with a prediction value less than 0.1 are judged to be the same wheel type.

[0096] The prediction results of the anchor target image and the comparison target image are obtained. If the prediction values ​​are all less than 0.1, it means that the wheels on the pallet are all of the same type and no processing is done. If the prediction value is greater than 0.1, the comparison target image is marked with a red border on the global image and displayed on the large-screen display, and a switch value is given to the sound and light alarm to make the sound and light alarm sound.

[0097] Please refer to Figure 6 As shown, the present application also provides a wheel mixed package detection model training device, comprising:

[0098] Acquisition module 301 obtains a training set of images, including two category labels: complete wheels and occluded wheels;

[0099] Training module 302 inputs the image training set into the YOLOv10-S network to obtain a bounding box and a category label; generates a triplet sample based on the bounding box and the category label, the triplet sample includes an anchor sample, a positive sample and a negative sample; extracts a feature map of the triplet sample through a feature extraction layer, including feature Figure 1 ,feature Figure 2 and features Figure 3 Based on the characteristics Figure 1 ,feature Figure 2 and features Figure 3 Perform global maximum pooling and global average pooling respectively, input into the channel attention mechanism module, and obtain features Figure 1-1 ,feature Figure 2-1 and features Figure 3-1 ; The features are respectively Figure 1-1 ,feature Figure 2-1 and features Figure 3-1 Input into the spatial attention mechanism module to obtain improved features Figure 1 , Improved Features Figure 2 and improved features Figure 3 ; The improved features Figure 1 , Improved Features Figure 2 and improved features Figure 3 They are input into the tiled layer and the fully connected layer respectively, and then the loss function is calculated.

[0100] Please refer to Figure 7 As shown, the present application also provides a wheel mixed bag detection device, comprising:

[0101] Input module 401 inputs the acquired wheel image into the YOLOv10-S network to obtain the bounding box, confidence level, and category of the complete wheel category object;

[0102] The identification module 402 selects the complete wheel category target whose confidence level is above a preset threshold, identifies the complete wheel category target closest to the center point of the wheel image as the anchor target, and sets the other complete wheel category targets as comparison targets;

[0103] The detection module 403 scales the anchor target and the comparison target, forms a matching queue with multiple comparison targets and the anchor target, and inputs the matching queue into the Triplet / Siamese network to obtain a detection result.

[0104] Furthermore, the detection module forms a matching queue with the plurality of comparison targets and the anchor target and inputs the queue into the Triplet / Siamese network to obtain a detection result, further comprising:

[0105] If the predicted values ​​in the test results are all less than 0.1, the wheels in the wheel images are identical and no processing is performed;

[0106] If there is a predicted value greater than 0.1 in the detection result, the comparison target is marked on the global map and the sound and light alarm is activated.

[0107] Furthermore, in the detection network, the channel attention weight value is directly referenced.

Claims

1. A wheel mixed bag detection model training method, characterized in that: The wheel mixed packet detection model includes: YOLOv10-S network and Triplet / Siamese network; The Triplet / Siamese network is connected to the YOLOv10-S network. The Triplet / Siamese network uses the first 47 layers of the ResNet50 network as feature extraction layers and introduces a channel attention mechanism module and a spatial attention mechanism module. The channel attention mechanism module performs global maximum pooling and global average pooling on the feature maps extracted by the feature extraction layer and inputs them into the shared perceptron; the spatial attention mechanism module processes the feature maps output by the channel attention mechanism module respectively; The training steps for the wheel mix-up detection model include: Get a training set of images, including two category labels: complete wheels and occluded wheels; Input the image training set into the YOLOv10-S network to obtain bounding boxes and category labels; Generate a triplet sample according to the bounding box and the category label, the triplet sample including an anchor sample, a positive sample, and a negative sample; Extracting feature maps of the triplet sample through the feature extraction layer, including feature map 1, feature map 2, and feature map 3; performing global maximum pooling and global average pooling on the feature maps 1, 2, and 3, respectively, and inputting them into the channel attention mechanism module to obtain feature maps 1-1, 2-1, and 3-1; respectively inputting the feature maps 1-1, 2-1, and 3-1 into the spatial attention mechanism module to obtain improved feature maps 1, 2, and 3; The improved feature map 1, the improved feature map 2 and the improved feature map 3 are respectively input into the tiled layer and the fully connected layer in sequence, and then the loss function is calculated.

2. A wheel mixed bag detection method, characterized in that: The wheel mix-up detection model is trained using the wheel mix-up detection model training method according to claim 1, the method comprising: Input the acquired wheel image into the YOLOv10-S network to obtain the bounding box, confidence, and category of the complete wheel category target; Selecting the complete wheel category target with the confidence level above a preset threshold, identifying the complete wheel category target closest to the center point of the wheel image as the anchor target, and setting the other complete wheel category targets as comparison targets; The anchor target and the comparison target are scaled, and a plurality of the comparison targets and the anchor target are formed into a matching queue and input into the Triplet / Siamese network to obtain a detection result.

3. A wheel mix-up detection method according to claim 2, characterized in that: include: The plurality of comparison targets and the anchor target are combined into a matching queue and input into the Triplet / Siamese network to obtain a detection result, further comprising: If the predicted values ​​in the test results are all less than 0.1, the wheels in the wheel images are identical and no processing is performed; If there is a predicted value greater than 0.1 in the detection result, the comparison target is marked on the global map and the sound and light alarm is activated.

4. A wheel mix-up detection method according to claim 2, characterized in that: In the Triplet / Siamese network, the channel attention weight value is directly referenced.

5. A wheel mix-up detection method according to claim 2, characterized in that: The preset threshold is set to 0.

8.

6. A wheel mixed bag detection model training device, characterized in that: The wheel mix-up detection model includes: a YOLOv10-S network and a Triplet / Siamese network; the Triplet / Siamese network is connected to the YOLOv10-S network. The Triplet / Siamese network uses the first 47 layers of the ResNet50 network as the feature extraction layer and introduces a channel attention mechanism module and a spatial attention mechanism module; the channel attention mechanism module performs global maximum pooling and global average pooling on the feature maps extracted by the feature extraction layer, and inputs them into a shared perceptron; the spatial attention mechanism module processes the feature maps output by the channel attention mechanism module separately; The wheel mixed bag detection model training device includes: Get the module and obtain the image training set, including two category labels: complete wheels and occluded wheels; A training module inputs the image training set into the YOLOv10-S network to obtain a bounding box and a category label; generates a triplet sample according to the bounding box and the category label, wherein the triplet sample includes an anchor sample, a positive sample, and a negative sample; extracts the feature map of the triplet sample through the feature extraction layer, including feature map 1, feature map 2, and feature map 3; performs global maximum pooling and global average pooling based on the feature map 1, feature map 2, and feature map 3, respectively, and inputs them into the channel attention mechanism module to obtain feature map 1-1, feature map 2-1, and feature map 3-1; inputs the feature map 1-1, feature map 2-1, and feature map 3-1 into the spatial attention mechanism module, respectively, to obtain an improved feature map 1, an improved feature map 2, and an improved feature map 3; the improved feature map 1, the improved feature map 2, and the improved feature map 3 are respectively input into the tiling layer and the fully connected layer in sequence, and then the loss function is calculated.

7. A wheel mixed bag detection device, characterized in that: The wheel mix-up detection model is trained using the wheel mix-up detection model training device described in claim 6, the device comprising: The input module inputs the acquired wheel image into the YOLOv10-S network to obtain the bounding box, confidence, and category of the complete wheel category target; an identification module, selecting the complete wheel category target whose confidence level is above a preset threshold, identifying the complete wheel category target closest to the center point of the wheel image as the anchor target, and setting the other complete wheel category targets as comparison targets; The detection module scales the anchor target and the comparison target, forms a matching queue with multiple comparison targets and anchor targets, and inputs the matching queue into the Triplet / Siamese network to obtain a detection result.

8. The wheel mix-up detection device according to claim 7, characterized in that: include: The detection module forms a matching queue with the plurality of comparison targets and the anchor target and inputs the matching queue into the Triplet / Siamese network to obtain a detection result, further comprising: If the predicted values ​​in the test results are all less than 0.1, the wheels in the wheel images are identical and no processing is performed; If there is a predicted value greater than 0.1 in the detection result, the comparison target is marked on the global map and the sound and light alarm is activated.

9. The wheel mix-up detection device according to claim 7, characterized in that: In the detection network, the channel attention weight value is directly referenced.

Images