DocumentCode
2247136
Title
Moving Objects Detection by Imitating Biologic Vision Based on Fly´s Eyes
Author
Yin, Jun ; Li, Dong-Guang ; Fang, Hui-Min ; Liu, Zhi-Feng
Author_Institution
Sch. of Mechatronics Eng., Beijing Inst. of Technol.
fYear
2004
fDate
22-26 Aug. 2004
Firstpage
763
Lastpage
766
Abstract
Nowadays, detection technology by bionic vision has great application potentials in both civil and military fields. This technology can develop brand-new technology approaches for the research of detection systems. On the bionic basis of fly´s vision system, this paper discussed the correlation-based elementary motion detector, namely EMD, which was proposed by Reichardt. On the basis of single EMD model, the mathematical model of two-dimensional EMDs array is established. Then according to this mathematical model, the computer vision detection system is schemed out to detect moving objects. This system can watch bigger visual fields and get higher image resolution than ordinary monitor systems. For avoiding complicated computation, only one of two frames is processed. In summary, simulative experiments indicate that both the moving object in relatively ideal background without interfering and certain interfered background can be detected in real time. The feasibility of bionic model was fully demonstrated in the engineering application, and it laid a solid foundation for the future study of detection technology by imitating biologic vision
Keywords
computer vision; image motion analysis; image resolution; object detection; 2D EMD array; biological vision; bionic vision; computer vision detection system; elementary motion detector; fly eyes; image resolution; motion detection; moving object detection; Computer vision; Computerized monitoring; Detectors; Eyes; Image resolution; Machine vision; Mathematical model; Motion detection; Object detection; Watches; EMDs array; Elementary Motion Detector(EMD); detection by imitating biologic vision; motion detection;
fLanguage
English
Publisher
ieee
Conference_Titel
Robotics and Biomimetics, 2004. ROBIO 2004. IEEE International Conference on
Conference_Location
Shenyang
Print_ISBN
0-7803-8614-8
Type
conf
DOI
10.1109/ROBIO.2004.1521878
Filename
1521878
Link To Document