Abstract
Outdoor vision sensing systems often struggle with poor weather conditions, such as snow and rain, which poses a great challenge to existing video desnowing and deraining methods. In this paper, we propose a novel video desnowing and deraining model that utilizes the salience information of moving objects to address this problem. First, we remove the snow and rain from the video by low-rank tensor decomposition, which makes full use of the spatial location information and the correlation between the three channels of the color video. Second, because existing algorithms often regard sparse snowflakes and rain streaks as moving objects, this paper injects salience information into moving object detection, which reduces the false alarms and missed alarms of moving objects. At the same time, feature point matching is used to mine the redundant information of moving objects in continuous frames, and a dual adaptive minimum filtering algorithm in the spatiotemporal domain is proposed by us to remove snow and rain in front of moving objects. Both qualitative and quantitative experimental results show that the proposed algorithm is more competitive than other state-of-the-art snow and rain removal methods.
Highlights
Outdoor vision systems in traffic and safety applications have greatly promoted the development of society
We introduce a saliency map into moving object detection, which improves the ability of moving object detection in snow and rain videos because almost all moving objects in snow and rain videos have salience information, while snowflakes and rain streaks do not
We regard the snow video as a tensor, remove snow in the video by low-rank tensor decomposition, and combine the saliency map with moving object detection to eliminate the interference of sparse snow, while extracting accurate moving objects
Summary
Outdoor vision systems in traffic and safety applications have greatly promoted the development of society. Computer vision technologies, such as target tracking and human detection, are widely used. These technologies often confront challenges, such as heavy snow, rainstorms, strong winds and other poor weather conditions. Snowflakes and rain streaks can obscure key information in the video, and strong winds can shake the camera, which will make subsequent video processing more difficult. Removing snow and rain is an important part of computer vision. The photometric properties of rain were used to detect raindrops [1]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have