Moving object detection is one of the key technologies in the field of target extraction, pattern recognition and motion measurement. The problem of moving object detection based on high-speed video sequence images is investigated in this paper. First, the high-speed video tracking system is introduced. Second, an improved hybrid detection method combined background subtraction with frame difference is proposed, and the moving object is post-processed by using the threshold area de-noising and morphology filter. Finally, the experiment results show that the proposed method detects the moving object from the high-speed video sequence images precisely and effectively.
Paper
Full text
Moving object detection based on high-speed video sequence images
Semantic Scholar · Computer Science · 2019
Abstract
Moving object detection is one of the key technologies in the field of target extraction, pattern recognition and motion measurement. The problem of moving object detection based on high-speed video sequence images is investigated in this paper. First, the high-speed video tracking system is introduced. Second, an improved hybrid detection method combined background subtraction with frame difference is proposed, and the moving object is post-processed by using the threshold area de-noising and morphology filter. Finally, the experiment results show that the proposed method detects the moving object from the high-speed video sequence images precisely and effectively.