Abstract: A contextual visual-based synthetic-aperture radar (SAR) target detection method and apparatus, and a storage medium, belonging to the field of target detection is described. The method includes: obtaining an SAR image; and inputting the SAR image into a target detection model, and positioning and recognizing a target in the SAR image by using the target detection model, to obtain a detection result. In the present disclosure, a two-way multi-scale connection operation is enhanced through top-down and bottom-up attention, to guide learning of dynamic attention matrices and enhance feature interaction under different resolutions. The model can extract the multi-scale target feature information with higher accuracy, for bounding box regression and classification, to suppress interfering background information, thereby enhancing the visual expressiveness.

Abstract: The present disclosure provides a method for fine-grained detection of driver distraction based on unsupervised learning, belonging to the field of driving behavior analysis. The method includes: acquiring distracted driving image data; and inputting the acquired distracted driving image data into an unsupervised learning detection model, analyzing the distracted driving image data by using the unsupervised learning detection model, and determining a driver distraction state according to an analysis result. The unsupervised learning detection model includes a backbone network, projection heads, and a loss function; the backbone network is a RepMLP network structure incorporating a multilayer perceptron (MLP); the projection heads are each an MLP incorporating a residual structure; and the loss function is a loss function based on contrastive learning and a stop-gradient strategy.

Abstract: The present disclosure provides a transformer-based driver distraction detection method and apparatus, belonging to the field of driving behavior analysis. The method includes: acquiring districted driving image data; building a driver distraction detection model FPT; inputting the acquired distracted driving image data into the driver distraction detection model FPT, analyzing the distracted driving image data by using the driver distraction detection model FPT, and determining a driver distraction state according to an analysis result. The present disclosure proposes a new network model, i.e., a driver distraction detection model FPT, based on Swin, Twins, and other models. Compared with a deep learning model, the FPT model compensates for the drawback that the deep learning model can only extract local features; the FPT model improves the classification accuracy and reduces the parameter quantity and calculation amount compared with the transformer model.

Abstract: The present disclosure provides a fire source detection method and device under the condition of a small sample size, and a storage medium, and belongs to the field of target detection and industrial deployment. The method includes the steps of acquiring fire source image data from an industrial site; constructing a fire source detection model; inputting the fire source image data to the fire source detection model, and analyzing the fire source image data via the fire source detection model to obtain a detection result, where the detection result includes a specific location, precision and type of a fire source. By means of the method, the problems of insufficient sample capacity and difficulty in training under the condition of a small sample size are solved, and different enhancement methods are used to greatly increase the number and quality of samples and improve the over-fitting ability of models.

Abstract: The present disclosure provides a transformer-based driver distraction detection method and apparatus, belonging to the field of driving behavior analysis. The method includes: acquiring districted driving image data; building a driver distraction detection model FPT; inputting the acquired distracted driving image data into the driver distraction detection model FPT, analyzing the distracted driving image data by using the driver distraction detection model FPT, and determining a driver distraction state according to an analysis result. The present disclosure proposes a new network model, i.e., a driver distraction detection model FPT, based on Swin, Twins, and other models. Compared with a deep learning model, the FPT model compensates for the drawback that the deep learning model can only extract local features; the FPT model improves the classification accuracy and reduces the parameter quantity and calculation amount compared with the transformer model.

Abstract: The present disclosure provides a method for fine-grained detection of driver distraction based on unsupervised learning, belonging to the field of driving behavior analysis. The method includes: acquiring distracted driving image data; and inputting the acquired distracted driving image data into an unsupervised learning detection model, analyzing the distracted driving image data by using the unsupervised learning detection model, and determining a driver distraction state according to an analysis result. The unsupervised learning detection model includes a backbone network, projection heads, and a loss function; the backbone network is a RepMLP network structure incorporating a multilayer perceptron (MLP); the projection heads are each an MLP incorporating a residual structure; and the loss function is a loss function based on contrastive learning and a stop-gradient strategy.

Abstract: The present disclosure provides a fire source detection method and device under the condition of a small sample size, and a storage medium, and belongs to the field of target detection and industrial deployment. The method includes the steps of acquiring fire source image data from an industrial site; constructing a fire source detection model; inputting the fire source image data to the fire source detection model, and analyzing the fire source image data via the fire source detection model to obtain a detection result, where the detection result includes a specific location, precision and type of a fire source. By means of the method, the problems of insufficient sample capacity and difficulty in training under the condition of a small sample size are solved, and different enhancement methods are used to greatly increase the number and quality of samples and improve the over-fitting ability of models.

Abstract: A contextual visual-based synthetic-aperture radar (SAR) target detection method and apparatus, and a storage medium, belonging to the field of target detection is described. The method includes: obtaining an SAR image; and inputting the SAR image into a target detection model, and positioning and recognizing a target in the SAR image by using the target detection model, to obtain a detection result. In the present disclosure, a two-way multi-scale connection operation is enhanced through top-down and bottom-up attention, to guide learning of dynamic attention matrices and enhance feature interaction under different resolutions. The model can extract the multi-scale target feature information with higher accuracy, for bounding box regression and classification, to suppress interfering background information, thereby enhancing the visual expressiveness.