LIDAR and vision‐based pedestrian detection system

A perception system for pedestrian detection in urban scenarios using information from a LIDAR and a single camera is presented. Two sensor fusion architectures are described, a centralized and a decentralized one. In the former, the fusion process occurs at the feature level, i.e., features from LIDAR and vision spaces are combined in a single vector for posterior classification using a single classifier. In the latter, two classifiers are employed, one per sensor-feature space, which were offline selected based on information theory and fused by a trainable fusion method applied over the likelihoods provided by the component classifiers. The proposed schemes for sensor combination, and more specifically the trainable fusion method, lead to enhanced detection performance and, in addition, maintenance of false-alarms under tolerable values in comparison with singlebased classifiers. Experimental results highlight the performance and effectiveness of the proposed pedestrian detection system and the related sensor data combination strategies.

[1]  Seungkeun Park,et al.  Multi-Classifier Based LIDAR and Camera Fusion , 2007, 2007 IEEE Intelligent Transportation Systems Conference.

[2]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[3]  Fatih Murat Porikli,et al.  Human Detection via Classification on Riemannian Manifolds , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Shigeo Abe.  Support Vector Machines for Pattern Classification (Advances in Pattern Recognition) , 2005 .

[5]  Fuhui Long,et al.  Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Urbano Nunes,et al.  Trainable classifier-fusion schemes: An application to pedestrian detection , 2009, 2009 12th International IEEE Conference on Intelligent Transportation Systems.

[7]  M. Mahlisch,et al.  Sensorfusion Using Spatio-Temporal Aligned Video and Lidar for Improved Vehicle Detection , 2006, 2006 IEEE Intelligent Vehicles Symposium.

[8]  Dieter Fox,et al.  A spatio-temporal probabilistic model for multi-sensor object recognition , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[9]  Fatih Murat Porikli,et al.  Region Covariance: A Fast Descriptor for Detection and Classification , 2006, ECCV.

[10]  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.

[11]  Favio R. Masson,et al.  Simultaneous localization and map building using natural features and absolute information , 2002, Robotics Auton. Syst..

[12]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

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

[14]  Pascal Vasseur,et al.  Introduction to Multisensor Data Fusion , 2005, The Industrial Information Technology Handbook.

[15]  Roland Siegwart,et al.  Human detection using multimodal and multidimensional features , 2008, 2008 IEEE International Conference on Robotics and Automation.

[16]  Urbano Nunes,et al.  Improving the Generalization Properties of Neural Networks: an Application to Vehicle Detection , 2008, 2008 11th International IEEE Conference on Intelligent Transportation Systems.

[17]  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.

[18]  Cristiano Premebida,et al.  A Multi-Target Tracking and GMM-Classifier for Intelligent Vehicles , 2006, 2006 IEEE Intelligent Transportation Systems Conference.

[19]  K. Dietmayer,et al.  Object tracking and classification using a multiple hypothesis approach , 2004, IEEE Intelligent Vehicles Symposium, 2004.

[20]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[21]  Laurence NGAKO PANGOP,et al.  A Bayesian Multisensor Fusion Approach Integrating Correlated Data applied to a Real-time Pedestrian Detection System , 2008 .

[22]  Tarak Gandhi,et al.  Pedestrian Protection Systems: Issues, Survey, and Challenges , 2007, IEEE Transactions on Intelligent Transportation Systems.

[23]  Nanning Zheng,et al.  Interactive Road Situation Analysis for Driver Assistance and Safety Warning Systems: Framework and Algorithms , 2007, IEEE Transactions on Intelligent Transportation Systems.

[24]  Robert Pless,et al.  Extrinsic calibration of a camera and laser range finder (improves camera calibration) , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).