This study proposes a motion cue based pedestrian detection method with two-trame-filtering （Tff） for video surveillance. The novel motion cue is exploited by the gray value variation between two frames. Then Tff pr...This study proposes a motion cue based pedestrian detection method with two-trame-filtering （Tff） for video surveillance. The novel motion cue is exploited by the gray value variation between two frames. Then Tff processing filters the gradient magnitude image by the variation map. Summa- tions of the Tff gradient magnitudes in cells are applied to train a pre-deteetor to exclude most of the background regions. Histogram of Tff oriented gradient （HTffOG） feature is proposed for pedestrian detection. Experimental results show that this method is effective and suitable for real-time surveil- lance applications.展开更多
This paper describes a reactive navigation proposed for a differentially driven robot. The aim of the reactive navigation is to prescribe behavior to the robot based on actual sensor values that is collision-free. Ana...This paper describes a reactive navigation proposed for a differentially driven robot. The aim of the reactive navigation is to prescribe behavior to the robot based on actual sensor values that is collision-free. Analysis of reactive navigation methods shows that there is no reliable reactive collision-free method. However, method VFH＋ is suboptimal reactive navigation method for static environment. Original method was proposed for ultrasonic rangefinders. Nowadays, much more sophisticated sensors are available. That is why our modification is proposed for a laser rangefinder attached to indoor mobile robot. Results are presented as simulation in Matlab and also as experiments with real robot. Based on these experiments, it can be claimed that VFH＋ is very effective reactive navigation method for various sensors and environments and it can be modified for different requirements on robot behavior.展开更多
基金Supported by the National High Technology Research and Development Program of China(No.2007AA01Z164)the National Natural Science Foundation of China(No.61273258)
文摘This study proposes a motion cue based pedestrian detection method with two-trame-filtering （Tff） for video surveillance. The novel motion cue is exploited by the gray value variation between two frames. Then Tff processing filters the gradient magnitude image by the variation map. Summa- tions of the Tff gradient magnitudes in cells are applied to train a pre-deteetor to exclude most of the background regions. Histogram of Tff oriented gradient （HTffOG） feature is proposed for pedestrian detection. Experimental results show that this method is effective and suitable for real-time surveil- lance applications.
文摘This paper describes a reactive navigation proposed for a differentially driven robot. The aim of the reactive navigation is to prescribe behavior to the robot based on actual sensor values that is collision-free. Analysis of reactive navigation methods shows that there is no reliable reactive collision-free method. However, method VFH＋ is suboptimal reactive navigation method for static environment. Original method was proposed for ultrasonic rangefinders. Nowadays, much more sophisticated sensors are available. That is why our modification is proposed for a laser rangefinder attached to indoor mobile robot. Results are presented as simulation in Matlab and also as experiments with real robot. Based on these experiments, it can be claimed that VFH＋ is very effective reactive navigation method for various sensors and environments and it can be modified for different requirements on robot behavior.
