A scene segmentation algorithm combining the body and the edge of the object
作者：
Highlights：
• 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.
摘要
•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.
论文关键词：Scene segmentation,Object misclassification,Body consistency,Body context information,Edge attention module
论文评审过程：Received 16 August 2021, Revised 16 November 2021, Accepted 23 November 2021, Available online 1 December 2021, Version of Record 1 December 2021.
论文官网地址：https://doi.org/10.1016/j.ipm.2021.102840
