Aiming at the problem of small moving object detection on dynamic water surface background, a moving object detection algorithm of interval background model is proposed. The algorithm first learns the range of background values on each coordinate point in the video sequence from a video of a non-moving object, and forms an interval background model. when the moving target is detected, the detection is carried out by point-by-point scanning, the value of the current pixel is compared with the value of the background model, if the value of the pixel point is within the range of the background module, the pixel point is the background, otherwise, the moving object is the background. After all pixel points are detected, they are combined into an initial moving target image. Finally, initial movement The target image is subjected to de-interference processing to obtain a final moving target image. The experimental results show that the algorithm has good detection effect on dynamic water surface moving targets and is fast in speed.

Date Published: 6 May 2019
PDF: 6 pages
Proc. SPIE 11069, Tenth International Conference on Graphics and Image Processing (ICGIP 2018), 110693Z (6 May 2019); doi: 10.1117/12.2524153

Published in SPIE Proceedings Vol. 11069:
Tenth International Conference on Graphics and Image Processing (ICGIP 2018)
Chunming Li; Hui Yu; Zhigeng Pan; Yifei Pu, Editor(s)