Comparison of People Detection Techniques from 2 D Laser Range Data

For a mobile robot operating in human environments detection of people is very crucial for carrying out different tasks. This paper presents our comparison of different approaches for people detection using geometric features. We compared a boosting system against Inscribed Angle Variance (IAV) method suitable for arc/circle detection. A bounding box approach is our baseline method. For segmentation purpose a simple jump distance algorithm is applied. We present experimental results of our comparison based on real data scanned by a laser range finder sensor.

[1]  António E. Ruano,et al.  Fast Line, Arc/Circle and Leg Detection from Laser Scan Data in a Player Driver , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.

[2]  Cristiano Premebida.  Segmentation and Geometric Primitives Extraction from 2D Laser Range Data for Mobile Robot Applications , 2005 .

[3]  Wolfram Burgard,et al.  Using Boosted Features for the Detection of People in 2D Range Data , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[4]  Ben J. A. Kröse,et al.  Part based people detection using 2D range data and images , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.