It is meaningful for moving target detection to maximize the advantages of the three-frame difference method and the background difference method and compensate their respective disadvantages. Therefore, this paper proposes the fusion of three-frame difference method and background difference method for infrared human motion target detection and uses a mixed gaussian model for background modeling. Aiming at the ghost region problem caused by mixed gaussian background modeling in the fusion process of two algorithms, the proposed solution is to determine whether the results of the mixed gaussian background modeling method include the results of the three-frame difference method. Through the experimental demonstration on the OTCBVS Benchmark Database, the results show that the proposed method is better than using the three-frame difference method and the background difference method alone in moving target detection.
Fusion of Three-frame Difference Method and Background Difference Method to Achieve Infrared Human Target Detection
2019-10-01
334443 byte
Conference paper
Electronic Resource
English
The Application of Difference Method to Dim Point Target Detection in Infrared Images
British Library Conference Proceedings | 1994
|British Library Online Contents | 2007
|Static vehicle detection method and system based on frame difference method
European Patent Office | 2020
|