Chang, H.J. Park, M.S. Jeong, H. Choi, J.Y. 2024-01-12T06:57:02Z 2024-01-12T06:57:02Z 2022-03-07 2011-09 1522-4880 https://pubs.kist.re.kr/handle/201004/80445 In this paper, we present a tracking failure detection method by imitating human visual system. By adopting log-polar transformation, we could simulate properties of retina image, such as rotation and scaling invariance and foveal predominance. The rotation and scaling invariance helps to reduce false alarms caused by pose changes and intensify translational changes. Foveal predominant property helps to detect the tracking failing moment by amplifying the resolution around focus (tracking box center) and blurring the peripheries. Each ganglion cell corresponds to a pixel of log-polar image, and its adaptation is modeled as Gaussian mixture model. Its validity is shown through various experiments. ？ 2011 IEEE. English IEEE Tracking failure detection by imitating human visual perception Conference 10.1109/ICIP.2011.6116374 1 2011 18th IEEE International Conference on Image Processing, ICIP 2011, pp.3293 - 3296 2011 18th IEEE International Conference on Image Processing, ICIP 2011 3293 3296 US Brussels 2011-09-11 Proceedings - International Conference on Image Processing, ICIP 2-s2.0-84863040109