Title :
Collision detection using a neurual computational model
Author :
Wang, Ling ; Yao, Dezhong
Author_Institution :
Sch. of Life Sci. & Technol., Univ. of Electron. Sci. & Technol. of China, Chengdu, China
Abstract :
The computation of the time-to-collision (TTC) in collision course is a critical issue for an animal to response quickly and accurately to avoid a looming object. The physical formula of TTC was not feasible for neural computation realization. We deduced a new approximation of TTC and constructed a neural computational model (NCM). The simulated results showed that NCM with neurons of sigmoid response can accurately estimate TTC and well reconstruct the practical animal collision experiments. NCM might be a potential and realizable model to imitate the physiological neural mechanism of the visual information processing in the looming collision course.
Keywords :
biology computing; image reconstruction; neural nets; object detection; physiological models; animal; looming object; neural computational model; physiological neural mechanism; sigmoid response; time-to-collision computation; visual information processing; Animals; Approximation methods; Brain modeling; Computational modeling; Neurons; Retina; Visualization; Collision Detection; Computational Model; Neural Mechanism; Neural Network;
Conference_Titel :
Biomedical Engineering and Informatics (BMEI), 2010 3rd International Conference on
Conference_Location :
Yantai
Print_ISBN :
978-1-4244-6495-1
DOI :
10.1109/BMEI.2010.5639601
