计算机工程与应用2024，Vol.60Issue(19)：68-79,12.DOI:10.3778/j.issn.1002-8331.2405-0035
基于深度神经网络的视频显著目标检测综述
Review of Video Salient Object Detection Based on Deep Neural Networks
摘要
Abstract
Video salient object detection is one of the widely studied research directions in the field of computer vision,which aims to locate and segment the most salient objects or regions in video.The existing video salient object detection methods mainly extract spatiotemporal features from dynamic video sequences for saliency prediction by constructing deep neural networks.A comprehensive review of video salient object detection methods based on deep learning is con-ducted.Firstly,the basic concepts and application scenarios of video salient object detection are elaborated.Secondly,the video salient object detection methods based on deep learning are classified,and analyzed and discussed in depth by cate-gory.Subsequently,authoritative benchmark test datasets and evaluation metrics in the field of video salient object detec-tion are introduced,and quantitative and qualitative experimental comparative analysis and discussion are conducted on the most advanced models on these benchmark datasets.Finally,the challenges faced by video salient object detection are summarized,and its future development directions are discussed.关键词
视频显著目标检测/时空特征/深度学习Key words
video salient object detection/spatiotemporal features/deep learning分类
信息技术与安全科学引用本文复制引用
杨成帮,王安志,任春洪,唐洁亮..基于深度神经网络的视频显著目标检测综述[J].计算机工程与应用,2024,60(19):68-79,12.基金项目
国家自然科学基金地区基金项目(62162013) （62162013）
贵州师范大学学术新苗基金项目(黔师新苗[2022]30号). （黔师新苗[2022]30号）
