Title :
Research of Moving Targets Detection and Identification
Author :
Jin Min ; Shi Lei
Author_Institution :
Dept. of Comput. Sci. & Technol., Heilongjiang Inst. of Technol., Harbin, China
Abstract :
Accurate detection of moving targets is the main contents of researching for computer vision and image encoding, which has an extensive applicative prospect. The traditional dynamic template matching algorithm has the disadvantage when it detects the affine deformation target, it is easy to distinguish the target by mistake. For that reason, a novel improved dynamic template matching algorithm is proposed in this paper. Firstly, the improved temporal difference algorithm is used to detect the moving targets. Secondly, affine invariant moment is used as the invariable characteristic. Experimental results indicate that, compared with traditional dynamic template matching algorithm, our method has better detection performance.
Keywords :
computer vision; image coding; image matching; image motion analysis; object detection; affine deformation target; affine invariant moment; computer vision; dynamic template matching; image encoding; moving targets detection; target identification; temporal difference; Automation; Change detection algorithms; Computer vision; Heuristic algorithms; Image coding; Image recognition; Image sequences; Intelligent robots; Object detection; Target recognition;
Conference_Titel :
Intelligent Computation Technology and Automation, 2009. ICICTA '09. Second International Conference on
Print_ISBN :
978-0-7695-3804-4
DOI :
10.1109/ICICTA.2009.316