Due to the prominent problems of imaging quality in low-illumination environment, the detection and extraction of moving targets in low-illumination video sequences has become a very difficult task. This paper proposes a new method for detecting and extracting moving targets in low-illumination video sequences by combining motion information and gradient information. This method first obtains the initial detection template of the moving area by inter-frame difference and noise filtering. In view of the target missed detection phenomenon caused by low illumination in the initial detection template, the extraction function method is used to detect the moving area with low grayscale values, and finally a complete moving area detection template is formed. The multi-scale morphological gradient operator is used for edge detection. This gradient operator has strong noise resistance. Experimental results show that this method can effectively realize the detection and extraction of moving targets in low-illumination video sequences. Keywords: moving target detection, image segmentation, gradient image
You Might Like
Recommended ContentMore
Open source project More
Popular Components
Searched by Users
Just Take a LookMore
Trending Downloads
Trending ArticlesMore