A line staff behavior recognition method and system

Abstract

The application discloses a production line personnel behavior recognition method and system, comprising: acquiring original video stream data of a production line, and inputting the original video stream data into a pre-trained improved key point detection model to obtain key point coordinate data of a human skeleton in each frame of image; organizing key point coordinate data of continuous n frames into a time sequence key point sequence; inputting the time sequence key point sequence into a pre-trained behavior recognition model to output a behavior category corresponding to the time sequence key point sequence. The production line personnel behavior recognition method and system effectively solve the problem that the prior art cannot simultaneously consider precision and real-time performance under occlusion and complex background, and provide reliable technical support for intelligent safety monitoring and quality tracing of the production line.

Description

Technical Field

[0001] This invention relates to the field of computer vision technology, and in particular to a method and system for recognizing the behavior of production line personnel. Background Technology

[0002] In the new energy vehicle manufacturing industry, the motor is a core component, and its quality directly affects the performance and safety of new energy vehicles. Whether the work behavior of personnel on the production line complies with regulations is related to production efficiency and employee safety. To address this issue, an AI-based behavior recognition and detection model algorithm is introduced to accurately identify and promptly detect factory work behaviors. The factory personnel work behavior action standard recognition and detection system can monitor the work behavior of personnel on the factory production line in real time, promptly identify and correct non-compliant actions, and provide scientific data support for subsequent motor fault tracing.

[0003] Currently, the main deep learning-based human pose recognition models in existing technologies are as follows: (1) MediaPipe model: MediaPipe detects multiple key points of the human body (e.g., joints and body parts). For human pose estimation, the model typically detects 33 key points of the human body (including head, shoulders, elbows, knees, ankles, etc.). The position of each key point is represented by two-dimensional coordinates (position in the image) or three-dimensional coordinates (position in space).

[0004] (2) Chinese Patent No. CN117935309A obtains radar point cloud data, extracts multidimensional data related to human posture, selects strong correlation features and weak correlation features, obtains feature subsets corresponding to each human posture, deletes noisy data, trains human posture detection model based on training dataset, obtains radar point cloud data of the human body to be tested, extracts feature data from it and inputs it into human posture detection model to obtain human posture classification results.

[0005] (3) Chinese Patent No. CN114529984A proposes a skeletal action recognition method based on learnable PL-GCN and ECLSTM. It can solve the problems of limited feature capture ability of key frames and significant moving joints and weak similar action classification ability in the process of skeletal action recognition. The patent proposes a learnable graph convolutional network (PL-GCN) to improve the physical structure of the model; proposes ECLSTM to enhance the ability to capture key frames; completes the construction of the skeletal graph by using the graph topology structure of skeletal sequence data; and integrates the spatial features from graph convolution and the temporal features extracted by ECLSTM network to improve the feature expression ability of the network. Finally, the fused features are subjected to average pooling and convolution for feature classification, which greatly improves the accuracy of human pose recognition.

[0006] (4) The YOLOv11-Pose model is an extension of the YOLO target detection framework, adding a keypoint detection task branch. It can predict keypoints of human bodies or objects while detecting targets, and is suitable for real-time action recognition tasks of industrial operators. The paper "A Multi-Pose Estimation Method Based on Improved YOLO11-pose" uses the FasterNet module to improve the backbone part of the network, enhances the network's feature extraction capability for images, and improves the feature extraction capability of the network through the feature pyramid structure, thereby increasing the accuracy and generalization ability of the algorithm to adapt to the poses of targets of different sizes.

[0007] However, existing visual inspection technologies still have the following problems in tasks involving the behavior recognition of production line operators: (1) Insufficient accuracy: MediaPipe's pose estimation is severely affected in complex environments, especially when workers' movements are complex or obstructed, leading to a decrease in recognition accuracy. In production line conditions, millimeter-wave radar faces increased data processing difficulties due to data complexity and noise interference when acquiring point cloud data, resulting in poor recognition of details and small workpieces. This makes millimeter-wave radar perform poorly in production line operator behavior recognition tasks, failing to provide sufficient accuracy and efficiency. In scenarios such as construction sites and factories, YOLOv11-Pose will fail to detect key points when personnel are partially obstructed (wearing safety helmets, reflective clothing, or being blocked by machines), and can only output skeleton key points, making it difficult to directly recognize complex or subtle movements.

[0008] (2) Real-time issues: The MediaPipe model performs well in many application scenarios, but in production line conditions, especially in video streams that require real-time processing, processing delays lead to untimely action recognition, affecting operational efficiency or safety monitoring. The point cloud data acquired by radar from the motor production line is too complex, noise is difficult to filter out, and it is time-consuming and resource-intensive, increasing the reaction delay and failing to achieve real-time detection. In factory scenarios, the YOLOv11-Pose model, if optimized with a lightweight model + TensorRT, can achieve a stable 30-60 FPS on commonly used GPUs, which basically meets the requirements for real-time detection. However, under occlusion and complex actions, although skeleton detection can maintain real-time performance, it is insufficient to accurately identify subtle movements and is difficult to accurately capture key points. Summary of the Invention

[0009] To address the technical problems existing in the background art, this invention proposes a method and system for recognizing the behavior of production line personnel.

[0010] The present invention proposes a method for recognizing the behavior of production line personnel, comprising the following steps: S1. Obtain the raw video stream data of the production line and input the raw video stream data into the pre-trained improved key point detection model to obtain the key point coordinate data of the human skeleton in each frame image; S2. Organize the key point coordinate data of n consecutive frames into a temporal key point sequence; S3. Input the time-series key point sequence into a pre-trained behavior recognition model to output the behavior category corresponding to the time-series key point sequence.

[0011] Preferably, the improved keypoint detection model is specifically an improved YOLOv11-Pose model, wherein the improved YOLOv11-Pose model embeds a MAGC module in the backbone network of the YOLOv11-Pose model and a CFB module in its neck network.

[0012] Preferably, the training process of the improved keypoint detection model includes: Obtain a dataset consisting of production line operation images and corresponding human key point annotations; The images in the dataset are standardized and data augmentation operations are applied, including random flipping, rotation, translation, scaling, and adding Gaussian noise or motion blur. An initial YOLOv11-Pose model is constructed, wherein the backbone network of the initial YOLOv11-Pose model integrates the MAGC module, and the neck network of the initial YOLOv11-Pose model integrates the CFB module. The GIoU loss function is used as the bounding box regression loss, and the initial model is trained based on the processed dataset to obtain a trained improved keypoint detection model.

[0013] Preferably, the dataset is divided into training set, validation set and test set in a ratio of 7:2:1.

[0014] Preferably, the MAGC module processes input features in the following manner: First, a 1x1 convolution is used to double the number of channels in the input feature map; The expanded feature map is then decomposed into four feature branches. The first branch is processed using standard convolution, the second branch is processed using depthwise separable convolution, and the third and fourth branches directly retain some of the original feature information through channel splitting. The features of the fourth branch are input into multiple cascaded bottleneck units based on graph convolution for feature extraction; Finally, the outputs of the four feature branches are concatenated along the channel dimension, and channel compression is performed using a 1x1 convolution to output the fused features.

[0015] Preferably, the CFB module comprises multiple cascaded CFBlock units, each of which processes the input features in the following manner: First, channel alignment is performed using a 1x1 convolution; Then, the spatial domain features are recalibrated using a convolutional attention mechanism; Next, a multilayer perceptron consisting of two pointwise convolutional layers is used to perform a nonlinear transformation on the recalibrated features; Both the convolutional attention mechanism sublayer and the multilayer perceptron sublayer employ residual connections and introduce a random depth regularization mechanism.

[0016] Preferably, the behavior category includes at least one of standard operating behavior, dangerous behavior, or work status behavior.

[0017] Preferably, the behavior recognition model is a PoseC3D network; the training process of the behavior recognition model includes: Obtain a training sample set, which includes multiple temporal key point sequences and the corresponding real behavior category labels for each sequence; The temporal key point sequence is input into the initial PoseC3D network for forward propagation, and the predicted behavior category is output. Calculate the cross-entropy loss between the predicted behavior category and the actual behavior category label; Based on the cross-entropy loss, the model parameters of the initial PoseC3D network are updated in reverse using the gradient descent algorithm until the model converges, thus obtaining a trained behavior recognition model.

[0018] This invention proposes a production line personnel behavior recognition system, comprising: The data acquisition module is used to acquire raw video stream data from the production line. The key point detection module is used to input the raw video stream data into a pre-trained improved key point detection model to obtain the key point coordinate data of the human skeleton in each frame of the image; The sequence organization module is used to organize the keypoint coordinate data of n consecutive frames into a temporal keypoint sequence; The behavior recognition module is used to input the temporal key point sequence into a pre-trained behavior recognition model to output the behavior category corresponding to the temporal key point sequence.

[0019] The present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method as described in any of the above.

[0020] This invention proposes a production line personnel behavior recognition method and system. By introducing MAGC and CFB modules, it significantly improves the model's feature representation and spatial context awareness capabilities under challenging conditions such as occlusion, complex backgrounds, and personnel wearing protective equipment. The GIoU loss function is used to optimize bounding box regression, effectively enhancing localization accuracy and model robustness. By efficiently connecting the improved keypoint detection network and the temporal behavior recognition network, a precise mapping from static pose estimation to dynamic behavior understanding is achieved. Ultimately, this application simultaneously achieves a synergistic improvement in keypoint detection stability, behavior recognition accuracy, and system inference real-time performance in complex production line environments, providing reliable technical support for production safety and quality monitoring. Attached Figure Description

[0021] Figure 1 This is a schematic diagram of the workflow of a production line personnel behavior recognition method proposed in this invention; Figure 2 This is a schematic diagram of an improved YOLOv11-pose network structure for one embodiment of a production line personnel behavior recognition method proposed in this invention. Figure 3 This is a schematic diagram of the MAGC module in a production line personnel behavior recognition method proposed in this invention. Figure 4 This is a schematic diagram of the CFB module in a production line personnel behavior recognition method proposed in this invention. Figure 5 This is a schematic diagram of the system architecture of a production line personnel behavior recognition system proposed in this invention. Detailed Implementation

[0022] Reference Figures 1-5 The present invention proposes a method for recognizing the behavior of production line personnel, comprising the following steps: S1. Obtain the raw video stream data of the production line and input the raw video stream data into the pre-trained improved key point detection model to obtain the key point coordinate data of the human skeleton in each frame image.

[0023] In this embodiment, a high-resolution industrial camera is used to capture operation videos including those of the operators. The captured operating conditions include various situations such as changes in lighting and different occlusions, in order to enhance the robustness of the model.

[0024] In this embodiment, the improved key point detection model is specifically the improved YOLOv11-Pose model. The improved YOLOv11-Pose model embeds the MAGC module in the backbone network of the YOLOv11-Pose model and the CFB module in its neck network.

[0025] In this embodiment, the training process of the improved keypoint detection model includes: Obtain a dataset consisting of production line operation images and corresponding human key point annotations; The images in the dataset are standardized and data augmentation operations are applied, including random flipping, rotation, translation, scaling, and adding Gaussian noise or motion blur. An initial YOLOv11-Pose model is constructed. The backbone network of the initial YOLOv11-Pose model integrates the MAGC module, and the neck network of the initial YOLOv11-Pose model integrates the CFB module. The GIoU loss function is used as the bounding box regression loss, and the initial model is trained based on the processed dataset to obtain a trained and improved keypoint detection model.

[0026] Specifically, the dataset is divided into training, validation, and test sets in a ratio of 7:2:1.

[0027] Specifically, during the processing of model training data, the Labelme image annotation tool was used to manually and meticulously annotate the key points of the human body in each image, generating corresponding JSON format files. The images, annotation files, and category labels were then organized into a YOLOv11-Pose compatible data structure, divided into training, validation, and test sets (7:2:1) to ensure the consistency and repeatability of model training and evaluation.

[0028] In this embodiment, the original image data is uniformly scaled to the YOLOv11-Pose input size (640×640), and the pixel values ​​are normalized to accelerate training convergence. Multiple data augmentation strategies are introduced to increase the diversity of training samples, including random image flipping, rotation, translation, and scaling; Gaussian noise and blurring are added to perturbation. All augmentation operations are applied simultaneously to the image and label (bounding box, mask) data to ensure input consistency.

[0029] In this embodiment, GIoU loss is used instead of CIoU loss during model training to improve fitting ability in scenarios such as non-overlapping bounding boxes and irregularly shaped objects. Training parameters are set as follows: image input size is 640×640; the number of data samples processed by the neural network in one training iteration is set to 16; training momentum is 0.9; initial learning rate is set to 0.01; weight decay is 0.0005; and 300 iterations are performed. The optimizer uses SGD (Stochastic Gradient Descent) and is trained in conjunction with a learning rate decay strategy. Model training and validation include: multiple rounds of iterative training on the training set, and real-time evaluation of metrics such as segmentation mIoU, detection mAP, and keypoint mAP using the validation set; if the validation results are unsatisfactory, the module structure, loss function weights, and enhancement strategies are adjusted accordingly.

[0030] Specifically, the formula for the GIoU loss function is: ; Where IoU is the intersection-union ratio of regions A and B; A is the predicted bounding box, B is the ground truth bounding box, and C is the minimum bounding rectangle of A and B.

[0031] It should be noted that the MAGC module processes input features in the following way: First, a 1x1 convolution is used to double the number of channels in the input feature map; The expanded feature map is then decomposed into four feature branches. The first branch is processed using standard convolution, the second branch is processed using depthwise separable convolution, and the third and fourth branches directly retain some of the original feature information through channel splitting. The features of the fourth branch are input into multiple cascaded bottleneck units based on graph convolution for feature extraction. Finally, the outputs of the four feature branches are concatenated along the channel dimension, and channel compression is performed using a 1x1 convolution to output the fused features.

[0032] In this embodiment, the CFB module includes multiple cascaded CFBlock units, each of which processes the input features in the following manner: First, channel alignment is performed using a 1x1 convolution; Then, the spatial domain features are recalibrated using a convolutional attention mechanism; Next, a multilayer perceptron consisting of two pointwise convolutional layers is used to perform a nonlinear transformation on the recalibrated features; The convolutional attention mechanism sublayer and the multilayer perceptron sublayer both employ residual connections and introduce a random depth regularization mechanism.

[0033] Specifically, the backbone and neck network of YOLOv11-Pose were optimized by introducing MAGC and CFB modules to enhance feature extraction capabilities and spatial attention mechanisms, thereby improving the accuracy and robustness of human keypoint detection. In the neck network, multi-scale feature fusion combined with CFBlock's convolutional attention mechanism enhances the model's feature representation at small scales and in local regions, enabling the model to accurately predict skeletal keypoints even in factory environments with partial occlusion of the human body.

[0034] It should be noted that the MAGC module, based on the local context modeling capabilities of multi-branch convolutional feature fusion and graph convolution (GCConv), introduces global and local feature interactions through an improved bottleneck residual structure. This allows high-level semantic information and local details to be fully combined, thereby enhancing the expressive power of the feature maps. This improvement not only increases the segmentation accuracy of human key points in complex scenes but also optimizes the network's inference speed while maintaining lightweight computational overhead, ensuring real-time performance. The CFB module, on the other hand, introduces convolutional attention and feature fusion units based on the C3k2 structure. Through multi-layer CFBlock stacking, it achieves inter-channel and spatial feature recalibration, enabling the network to focus on key human regions and suppress irrelevant background interference. It maintains stable gradient propagation and strong discriminative ability during multi-scale feature fusion.

[0035] Specifically, the improved YOLOv11-pose network structure is as follows: Figure 2 As shown, the overall improved YOLOv11-Pose network architecture consists of three parts: the first part is the optimized backbone network, which introduces MAGC to enhance the collaborative representation of semantic features and local details; the second part is the improved neck network, which introduces CFB to achieve high-precision prediction and multi-scale fusion of key points; the third part is the output stage, which takes the human skeleton key points predicted by the multi-layer feature map as input to the PoseC3D network and uses temporal modeling capabilities to achieve the recognition of continuous actions. While maintaining end-to-end real-time inference capabilities, it effectively improves the robustness of human key point detection and achieves the goal of action recognition and behavior analysis in factory scenarios through combination with temporal networks.

[0036] In this embodiment, to enhance the network's generalization ability under complex conditions, this application introduces a MAGC module into the backbone network of YOLOv11-Pose. Its structure employs a multi-branch strategy to ensure that the input features contain both the transformed abstract information and the original, preserved details. For example... Figure 3 As shown, the global / gating mechanism introduced by GCConv enhances the expressive power of features. Furthermore, by combining concatenation with 1×1 convolution, high-dimensional feature aggregation is achieved with relatively low computational overhead. Figure 3In this context, Input represents the input feature map, Conv1 1 represents 1 The convolution operation with a value of 1 is used to adjust the number of channels. Chunk (blocking operation) dim=1 means that the feature information is split in two along the channel dimension. Conv2d represents the convolution operation with adaptive padding. Three Conv2d operations will adjust the size of their respective received feature maps to the same size. The plus sign (+) indicates that the feature maps output by the three Conv2d operations are concatenated along the channel dimension. SiLU represents the activation function, and Output represents the output feature map.

[0037] Specifically, such as Figure 4 As shown, the CFB module contains several CFBlock units. Each CFBlock unit first performs channel alignment through a 1×1 convolution, then uses a convolutional attention network to perform multi-head attention computation in the spatial domain, learning local structure and long-range dependencies in a convolutional parameterized manner. Next, an MLP consisting of pointwise convolutions and nonlinearities is used to nonlinearly reconstruct the channel dimensions. Here, Input represents the input feature map, and Conv1... 1 represents 1 The convolution operation of 1 is used to adjust the number of channels. MLP stands for Multilayer Perceptron, Conv_Attention stands for Convolutional Attention Module, Droppath stands for Random Depth Operation to avoid overfitting, and ADD stands for Adding Conv1. 1. The output feature map and the feature map processed by Droppath are concatenated along the channel dimension. 0. Output represents the output feature map.

[0038] S2. Organize the key point coordinate data of n consecutive frames into a temporal key point sequence.

[0039] S3. Input the temporal key point sequence into the pre-trained behavior recognition model to output the behavior category corresponding to the temporal key point sequence.

[0040] In this embodiment, the behavior category includes at least one of standard operating behavior, dangerous behavior, or working state behavior.

[0041] In this embodiment, the behavior recognition model is specifically the PoseC3D network; the training process of the behavior recognition model includes: Obtain the training sample set, which includes multiple temporal key point sequences and the corresponding real behavior category labels for each sequence; The temporal key point sequence is input into the initial PoseC3D network for forward propagation, and the predicted behavior category is output. Calculate the cross-entropy loss between the predicted behavior category and the actual behavior category label; Based on cross-entropy loss, the gradient descent algorithm is used to update the model parameters of the initial PoseC3D network in reverse until the model converges, so as to obtain a trained behavior recognition model.

[0042] Reference Figures 1-5 The present invention proposes a production line personnel behavior recognition system, comprising: The data acquisition module is used to acquire raw video stream data from the production line. The key point detection module is used to input the raw video stream data into a pre-trained improved key point detection model to obtain the key point coordinate data of the human skeleton in each frame of the image; The sequence organization module is used to organize the keypoint coordinate data of n consecutive frames into a temporal keypoint sequence; The behavior recognition module is used to input the temporal key point sequence into the pre-trained behavior recognition model to output the behavior category corresponding to the temporal key point sequence.

[0043] This application provides a computer-readable storage medium storing computer-executable instructions. When the computer-executable instructions are executed by a processor, they are used to implement the technical solution shown in the above method embodiments. The implementation principle and beneficial effects are similar and will not be repeated here.

[0044] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A method for recognizing the behavior of production line personnel, characterized in that, Includes the following steps: S1. Obtain the raw video stream data of the production line and input the raw video stream data into the pre-trained improved key point detection model to obtain the key point coordinate data of the human skeleton in each frame image; S2. Organize the key point coordinate data of n consecutive frames into a temporal key point sequence; S3. Input the time-series key point sequence into a pre-trained behavior recognition model to output the behavior category corresponding to the time-series key point sequence; Specifically, the improved key point detection model is the improved YOLOv11-Pose model, which embeds the MAGC module in the backbone network of the YOLOv11-Pose model and the CFB module in its neck network. The MAGC module processes input features in the following manner: First, a 1x1 convolution is used to double the number of channels in the input feature map; The expanded feature map is then decomposed into four feature branches. The first branch is processed using standard convolution, the second branch is processed using depthwise separable convolution, and the third and fourth branches directly retain some of the original feature information through channel splitting. The features of the fourth branch are input into multiple cascaded bottleneck units based on graph convolution for feature extraction; Finally, the outputs of the four feature branches are concatenated along the channel dimension, and channel compression is performed using a 1x1 convolution to output the fused features. The CFB module comprises multiple cascaded CFBlock units, each of which processes the input features in the following manner: First, channel alignment is performed using a 1x1 convolution; Then, the spatial domain features are recalibrated using a convolutional attention mechanism; Next, a multilayer perceptron consisting of two pointwise convolutional layers is used to perform a nonlinear transformation on the recalibrated features; The convolutional attention mechanism sublayer and the multilayer perceptron sublayer both employ residual connections and introduce a random depth regularization mechanism.

2. The production line personnel behavior recognition method according to claim 1, characterized in that, The training process of the improved keypoint detection model includes: Obtain a dataset consisting of production line operation images and corresponding human key point annotations; The images in the dataset are standardized and data augmentation operations are applied, including random flipping, rotation, translation, scaling, and adding Gaussian noise or motion blur. An initial YOLOv11-Pose model is constructed, wherein the backbone network of the initial YOLOv11-Pose model integrates the MAGC module, and the neck network of the initial YOLOv11-Pose model integrates the CFB module. The GIoU loss function is used as the bounding box regression loss, and the initial YOLOv11-Pose model is trained based on the processed dataset to obtain a trained and improved key point detection model.

3. The production line personnel behavior recognition method according to claim 2, characterized in that, The dataset is divided into training, validation, and test sets in a ratio of 7:2:

1.

4. The production line personnel behavior recognition method according to claim 1, characterized in that, The behavior category includes at least one of the following: standard operating behavior, dangerous behavior, or work status behavior.

5. The production line personnel behavior recognition method according to claim 1, characterized in that, The behavior recognition model is specifically the PoseC3D network; The training process of the behavior recognition model includes: Obtain a training sample set, which includes multiple temporal key point sequences and the corresponding real behavior category labels for each sequence; The temporal key point sequence is input into the initial PoseC3D network for forward propagation, and the predicted behavior category is output. Calculate the cross-entropy loss between the predicted behavior category and the actual behavior category label; Based on the cross-entropy loss, the model parameters of the initial PoseC3D network are updated in reverse using the gradient descent algorithm until the model converges, thus obtaining a trained behavior recognition model.

6. A production line personnel behavior recognition system, characterized in that, include: The data acquisition module is used to acquire raw video stream data from the production line. The key point detection module is used to input the raw video stream data into a pre-trained improved key point detection model to obtain the key point coordinate data of the human skeleton in each frame of the image; The sequence organization module is used to organize the keypoint coordinate data of n consecutive frames into a temporal keypoint sequence; The behavior recognition module is used to input the temporal key point sequence into a pre-trained behavior recognition model to output the behavior category corresponding to the temporal key point sequence; Specifically, the improved key point detection model is the improved YOLOv11-Pose model, which embeds the MAGC module in the backbone network of the YOLOv11-Pose model and the CFB module in its neck network. The MAGC module processes input features in the following manner: First, a 1x1 convolution is used to double the number of channels in the input feature map; The expanded feature map is then decomposed into four feature branches. The first branch is processed using standard convolution, the second branch is processed using depthwise separable convolution, and the third and fourth branches directly retain some of the original feature information through channel splitting. The features of the fourth branch are input into multiple cascaded bottleneck units based on graph convolution for feature extraction; Finally, the outputs of the four feature branches are concatenated along the channel dimension, and channel compression is performed using a 1x1 convolution to output the fused features. The CFB module comprises multiple cascaded CFBlock units, each of which processes the input features in the following manner: First, channel alignment is performed using a 1x1 convolution; Then, the spatial domain features are recalibrated using a convolutional attention mechanism; Next, a multilayer perceptron consisting of two pointwise convolutional layers is used to perform a nonlinear transformation on the recalibrated features; The convolutional attention mechanism sublayer and the multilayer perceptron sublayer both employ residual connections and introduce a random depth regularization mechanism.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of the method as described in any one of claims 1 to 5.

Images