A study on features for pedestrian detection using a low resolution LIDAR

In recent years, LIDAR (LIght Detection And Ranging) is focused as a sensor for recognizing surrounding environment around the vehicle. It is now used for some commercial products such as collision avoidance systems. In addition, some research groups have tried to use LIDAR for pedestrian detection. However, most of them used high resolution LIDAR for pedestrian detection, and it is quite expensive to be equipped into consumer products. Therefore, demand for pedestrian detection using low resolution LIDAR is increasing. To solve this problem, this report proposes novel features for detecting pedestrians by using low resolution LIDAR. We conducted experiments using data obtained in an actual environment. Experimental results showed that the proposed method could detect pedestrians accurately from low resolution LIDAR data.

[1]  Cristiano Premebida,et al.  Exploiting LIDAR-based features on pedestrian detection in urban scenarios , 2009, 2009 12th International IEEE Conference on Intelligent Transportation Systems.

[2]  Takashi Naito,et al.  Pedestrian recognition using high-definition LIDAR , 2011, 2011 IEEE Intelligent Vehicles Symposium (IV).

[3]  鈴木 康弘,et al.  Pedestrian Detection and Tracking using in-vehicle Lidar for Automotive Application (特集 センサ&センシング技術) , 2012 .

[4]  Kai Oliver Arras,et al.  Tracking people in 3D using a bottom-up top-down detector , 2011, 2011 IEEE International Conference on Robotics and Automation.

[5]  Martial Hebert,et al.  Pedestrian Detection and Tracking Using Three-dimensional LADAR Data , 2010, Int. J. Robotics Res..