Human body semantic segmentation method based on Res2Net, TransUNet and collaborative attention

Abstract

The invention provides a human body semantic segmentation method based on Res2Net, TransUNet and collaborative attention. The method comprises the following steps: acquiring a human body part semantic segmentation data set; introducing a Res2Net network, a TransUNet network and a Coordinate Attention mechanism, and constructing a neural network model; designing a loss function, and optimizing the neural network model by using an Adam algorithm; training the optimized neural network model by adopting a data set; and inputting a human body image to be segmented into the trained neural network model to obtain a human body image segmentation result. According to the technical scheme, the problems that in the actually-shot human body image, the image environment is complex, the number of human bodies is large, and in the prior art, during semantic segmentation of the human bodies, the performance is poor, and all parts of the human bodies in the image cannot be accurately segmented are solved.

Description

technical field [0001] The present invention relates to the technical field of image segmentation, in particular to a human body semantic segmentation method based on Res2Net, TransUNet and collaborative attention. Background technique [0002] Semantic segmentation of human body in complex actual scenes is to segment the human body in the image from the actual field scene. By establishing a deep neural network model and using a complete data set for training, it can adapt to various complex actual environments. Ke Gong et al proposed a PGN network to segment human bodies in complex scene images. Feature maps are extracted using ResNet-101. Then, two branches are appended to capture the partial background and the human boundary background, while generating partial score maps and edge score maps. Finally, a refinement branch is performed to refine the predicted segmentation and edge maps by integrating part segmentation and human boundary background. The U-Net series algo...

AI Technical Summary

Problems solved by technology

[0003] However, in the actual human body images, the image environment is complex and the number of human bodies is large. The existing technology often does not perform well in the semantic segmentation of human bodies, and cannot accurately segment the various parts of the human body in the image.

Images