WCSE 2022 Spring
ISBN: 978-981-18-5852-9 DOI: 10.18178/wcse.2022.04.011

DeepLabv3+ Semantic Segmentation Network Optimized by Double Weighted Feature Fusion

Hong Zhang, Yue Gao, Jianchen Miao

Abstract— Intelligent identificat ion to prohibited items in lug-gage is of great significance to ensure the safety of passengers. In this paper, we propose CWF-DeepLabv3+ semantic segmentation network to improve the segmentation accuracy to small size objects in X-Ray security images, and reduce the object pixel loss caused by complex background. The CWF-DeepLabv3+ network is based on the DeepLabv3+ network, which improves both the Xception backbone and the Atrous Spatial Pyramid Pooling (ASPP) module. Firstly, we combine the Cross Stage Partial Network (CSPNet) structure to propose a new CSP-Xception backbone network. The CSPNet network is capable of improving the learning ability of the network by using gradient split to build rich gradient combinations. Secondly, we design the Double Weighted Feature Fusion (DWFF) in the ASPP module. Weighted feature fusion by learning the importance of input features, and in this way, the segmentation accuracy of images with small size objects and complex background will be improved. The experimental results of training and testing on X-Ray security images show that the mPA value and mIoU value of CWF-DeepLabv3+ network reach to 90.85% and 81.64% respectively. Furthermore, compared with DeepLabv3+, Unet, and Bisenetv2 semantic segmentation network, the mean pixel segmentation accuracy of our proposed network is improved by at least 3.13%.

Index Terms— X-Ray Security Images, Semant ic Segmentation, DeepLabv3+, CSPNet, Double Weighted Feature Fusion.

Hong Zhang
Xi'an University of Posts and Telecommunications, China;Automatic Sorting Technology Research Center, State Post Bureau of the People’s Republic of China
Yue Gao
Xi'an University of Posts and Telecommunications, China;Automatic Sorting Technology Research Center, State Post Bureau of the People’s Republic of China
Jianchen Miao
Xi'an University of Posts and Telecommunications, Xi’an, China

[Download]


Cite: Hong Zhang, Yue Gao, Jianchen Miao, "DeepLabv3+ Semantic Segmentation Network Optimized by Double Weighted Feature Fusion," WCSE 2022 Spring Event: 2022 9th International Conference on Industrial Engineering and Applications, pp. 87-95, Sanya, China, April 15-18, 2022.