Traffic danger detection by visual attention model of sparse sampling
来源期刊:中南大学学报(英文版)2015年第10期
论文作者:XIA Li-min LIU Tao TAN Lun-zheng
文章页码:3916 - 3924
Key words:traffic dangers; visual attention model; sparse sampling; Bayesian probability model; multiscale saliency
Abstract: A method to detect traffic dangers based on visual attention model of sparse sampling was proposed. The hemispherical sparse sampling model was used to decrease the amount of calculation which increases the detection speed. Bayesian probability model and Gaussian kernel function were applied to calculate the saliency of traffic videos. The method of multiscale saliency was used and the final saliency was the average of all scales, which increased the detection rates extraordinarily. The detection results of several typical traffic dangers show that the proposed method has higher detection rates and speed, which meets the requirement of real-time detection of traffic dangers.
XIA Li-min(夏利民), LIU Tao(刘涛), TAN Lun-zheng(谭论正)
(School of Information Science and Engineering, Central South University, Changsha 410083, China)
Abstract:A method to detect traffic dangers based on visual attention model of sparse sampling was proposed. The hemispherical sparse sampling model was used to decrease the amount of calculation which increases the detection speed. Bayesian probability model and Gaussian kernel function were applied to calculate the saliency of traffic videos. The method of multiscale saliency was used and the final saliency was the average of all scales, which increased the detection rates extraordinarily. The detection results of several typical traffic dangers show that the proposed method has higher detection rates and speed, which meets the requirement of real-time detection of traffic dangers.
Key words:traffic dangers; visual attention model; sparse sampling; Bayesian probability model; multiscale saliency