A scene segmentation algorithm combining the body and the edge of the object

•This article proposes the BEJNet network structure which combines the main body and the edge of the object for better feature extraction. On the basis of the semantic flow feature alignment module, the U-shaped body context information extraction module with residual connections is designed to comprehensively use the object body local and global context information while keeping the flow model training stable.•This article proposes an edge attention module, which uses high-level information to generate edge features containing semantic information and combines low-level edge features guided by the global pooling module to refine the edge features of objects. So, the segmentation effect of the object edges is improved.•Experimental results of the proposed method on many classic network structures such as FCN, PSPNet, DeepLabv3+ and SFNet structures, which improves the mIoU of semantic segmentation with tiny parameters. In addition, we also conduct tests on several classic scene datasets of Cityscapes, CamVid and KITTI, which indicates that our proposed method have reached good results. Scene segmentation is a very challenging task where convolutional neural networks are used in this field and have achieved very good results. Current scene segmentation methods often ignore the internal consistency of the target object, and lack to make full use of global and local context information which leads to the situation of object misclassification. In addition, most of the previous work focused on the segmentation of the main part of the object, however, there are few researches on the quality of the object edge segmentation. In this article, based on the use of flow information to maintain body consistency, the context feature extraction module is designed to fully consider the global and local body context information of the target object, refining the rough feature map in the intermediate stage. So, the misclassification of the target object is reduced. Besides, in the proposed edge attention module, the low-level feature map guided by the global feature and the edge feature map with semantic information obtained by intermediate process are connected to obtain more accurate edge detail information. Finally, the segmentation quality that contains the body part of the noise and the edge details can be improved. This paper not only conducts experiments on the classic FCN, PSPNet, and DeepLabv3+ several mainstream network architectures, but also on the real-time SFN