Search

In order to reduce the interference of shadow to detection results of moving targets, a shadow detection method is proposed, which can be made as the post-processing step of motion detection methods. On the basis of the target list detected by motion detection methods, this method extracts the brightness, contrast and structural features of the pixels between adjacent frames for the three color channels R, G and B, and fuses the three types of features to generate the similarity measure. And the objective function is designed according to the MMSE(minimum mean square error) criterion. The optimal pixel segmentation thresholds are obtained by the optimal solution, to detect and eliminate the shadow pixels in the motion detection targets. The shadow detection experiments are carried out on the shadow subset of Changedetection.net dataset. The experimental results show that this method has high detection rate and low detection time.

With the success of Vision Transformer (ViT), Transformer is being increasingly used for hyperspectral image (HSI) classification given its ability to extract global context dependencies. However, existing methods based on transformers tend to classify HSI in the traditional patch-wise manner. Thus, these methods cannot obtain true global features because the inputs of the model are local patches. To solve these problems, a hybrid convolution and ViT network (HCVN) is proposed for HSI classification. HCVN realizes the classification task from the perspective of semantic segmentation, and its input is the entire HSI, which makes it possible to obtain truly meaningful global features. By improving the original ViT, an HCV module is proposed, which enhances the ability of local structure characterization while extracting global features. The HCVN hybrid convolution layer and HCV module realize the extraction and fusion of local and global features. Finally, the dual branch network architecture is used to integrate the spatial and spectral features. Extensive experiments on two datasets verify the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]