A FAST AND ROBUST NOISE REDUCTION METHOD FOR TINY CONTOURS IN IMAGE SEQUENCE

摘要：

Remote object contours abstracted from image sequence obtained by space optical sensor were often tiny and inclined to be stained by noise. It would deteriorate the results of most contour based algorithms. In order to solve the problem a fast and robust noise reduction technique for tiny contour in image sequence was presented in this paper. In the proposed technique, every contour in the sequence were described in frequency domain by the Fourier Descriptors (FDs). And then, a set of Kalman filters were used to filter the noise in every frequency point of the contours FDs. The contour after noise reduction was retrieved by inverting the filtered contour FDs. The experimental results showed the proposed method was useful and effective.

关键词： Fourier Descriptors (FDs) Kalman filter image contour

作者: M.Zhai J.M.Wu B.W.Liu

作者单位: National Key Laboratory of Science and Technology on Avionics System Integration, Shanghai, China

会议类型: 国际会议

会议名称: 2012 International Conference on System Simulation(2012年国际系统仿真学术会议)

会议地点: 上海

会议语种:英文

页码: 333-337

在线出版日期: 2012-04-06（万方平台首次上网日期，不代表论文的发表时间）