计算机与数字工程2024，Vol.52Issue(6)：1636-1642,7.DOI:10.3969/j.issn.1672-9722.2024.06.008
一种基于混合注意力的高效阴影检测算法
An Efficient Shadow Detection Algorithm Based on Hybrid Attention Mechanism
戴晓峰 1黄刚 1刘帅1
作者信息
- 1. 南京邮电大学计算机学院 南京 210000
- 折叠
摘要
Abstract
In the computer vision task,the presence of shadow pixels will have a negative impact on algorithms.Therefore,it is of certain research significance to improve the performance and effect of shadow detection network.The existing shadow detection algorithms using attention mechanism are not sufficient to extract cross-channel features and global pixel information.To solve this problem,this paper studies shadow feature information and combines the design idea of hybrid attention mechanism to build a new network Res-CCNet that integrates channel attention and spatial attention,and uses dense connection and feature fusion to reuse ne-glected features.Experiments are conducted on datasets SBU and UCF with three different evaluation criteria SER,NER and BER.The results show that the network algorithm has efficient shadow detection capabilities and application prospects.关键词
阴影检测/注意力机制/卷积神经网络/特征提取/语义信息Key words
shadow detection/attention mechanism/CNN/feature extraction/semantic information分类
信息技术与安全科学引用本文复制引用
戴晓峰,黄刚,刘帅..一种基于混合注意力的高效阴影检测算法[J].计算机与数字工程,2024,52(6):1636-1642,7.
