TY - GEN
T1 - Aerial video image object detection and tracing based on motion vector compensation and statistic analysis
AU - Jiang, Zhe
AU - Ding, Wenrui
AU - Li, Hongguang
PY - 2009
Y1 - 2009
N2 - Object detection in aviation video is very important in many occasions. Through research on characteristic of aviation video image, and analyzing of motion estimation theory, an object detection technique based on motion vector compensation and statistical analysis is proposed. Through effective image preprocessing, noise that influenced the capacity of algorithm is removed through a Bayesian estimation based wavelet denoising method; a compensation is carry out between the motion vector computedfrom parameters of camera and the motion estimation that usually used in all kinds of image compression algorithm. The compensation makes it easy to distinguish object motion from background. Then statistic analysis, a clustering using center and density of compensated motion vector is performed to eliminate isolate motion vector and realize object detection. Settings of the threshold can prevent some errors of global estimation which derivedfrom the parameters from compensation, and have some accessorial effect in motion vector clustering and object detection.
AB - Object detection in aviation video is very important in many occasions. Through research on characteristic of aviation video image, and analyzing of motion estimation theory, an object detection technique based on motion vector compensation and statistical analysis is proposed. Through effective image preprocessing, noise that influenced the capacity of algorithm is removed through a Bayesian estimation based wavelet denoising method; a compensation is carry out between the motion vector computedfrom parameters of camera and the motion estimation that usually used in all kinds of image compression algorithm. The compensation makes it easy to distinguish object motion from background. Then statistic analysis, a clustering using center and density of compensated motion vector is performed to eliminate isolate motion vector and realize object detection. Settings of the threshold can prevent some errors of global estimation which derivedfrom the parameters from compensation, and have some accessorial effect in motion vector clustering and object detection.
UR - https://www.scopus.com/pages/publications/77949600625
U2 - 10.1109/PRIMEASIA.2009.5397385
DO - 10.1109/PRIMEASIA.2009.5397385
M3 - 会议稿件
AN - SCOPUS:77949600625
SN - 9781424446698
T3 - 1st Asia Pacific Conference on Postgraduate Research in Microelectronics and Electronics, PrimeAsia 2009
SP - 302
EP - 305
BT - 1st Asia Pacific Conference on Postgraduate Research in Microelectronics and Electronics, PrimeAsia 2009
T2 - 1st Asia Pacific Conference on Postgraduate Research in Microelectronics and Electronics, PrimeAsia 2009
Y2 - 19 November 2009 through 21 November 2009
ER -