G2P: A new descriptor for pedestrian detection

Pedestrian detection plays an important role in intelligent vehicle applications. Since its birth 12 years ago, the Histogram-Of-Gradient (HOG) descriptor has become a popular descriptor for pedestrian detection, thanks to its effectiveness in capturing implicit human characteristics. Besides its original instantiation, the HOG also reflects a general methodology of constructing descriptors based on histograms of gradients of certain image sub-blocks. Following this general methodology, a number of HOG-style descriptors have been reported in literature. Three contributions are made in this work. First, a general model called Descriptor Generation Model (DGM) is proposed, which can be used to systematically construct a wide range of HOG-style descriptors for pedestrian detection. Second, based on the DGM, a pedestrian detection experimental framework (PDEF) is introduced to find the optimal HOG-style descriptor. In the PDEF, the performance of each descriptor can be evaluated. At last, the genetic algorithm is employed to search the optimal (or semi-optimal) HOG-style descriptor in the descriptor space. And a new descriptor named Second-order Gradient for Pedestrian detection (G2P) is presented. Experimental results demonstrate the advantage of the G2P descriptor over the standard HOG descriptor with ETH, CVC-02-system, NITCA and KITTI dataset, which also reflects the effectiveness of the DGM-based PDEF in finding better descriptors for pedestrian detection.

[1]  David Gerónimo Gómez,et al.  2D-3D-based on-board pedestrian detection system , 2010, Comput. Vis. Image Underst..

[2]  Xinge You,et al.  A Blind Watermarking Scheme Using New Nontensor Product Wavelet Filter Banks , 2010, IEEE Transactions on Image Processing.

[3]  N. Pettersson,et al.  A new pedestrian dataset for supervised learning , 2008, 2008 IEEE Intelligent Vehicles Symposium.

[4]  Emilio Frazzoli,et al.  Intention-Aware Motion Planning , 2013, WAFR.

[5]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[6]  Darrell Whitley,et al.  A genetic algorithm tutorial , 1994, Statistics and Computing.

[7]  Mohan M. Trivedi,et al.  Part-Based Pedestrian Detection and Feature-Based Tracking for Driver Assistance: Real-Time, Robust Algorithms, and Evaluation , 2013, IEEE Transactions on Intelligent Transportation Systems.

[8]  Henning Lategahn,et al.  How to learn an illumination robust image feature for place recognition , 2013, 2013 IEEE Intelligent Vehicles Symposium (IV).

[9]  Henning Lategahn,et al.  DIRD is an illumination robust descriptor , 2014, 2014 IEEE Intelligent Vehicles Symposium Proceedings.

[10]  Luc Van Gool,et al.  Depth and Appearance for Mobile Scene Analysis , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[11]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  C. G. Keller,et al.  Will the Pedestrian Cross? A Study on Pedestrian Path Prediction , 2014, IEEE Transactions on Intelligent Transportation Systems.

[13]  Zhenyu He,et al.  Robust Object Tracking via Key Patch Sparse Representation , 2017, IEEE Transactions on Cybernetics.

[14]  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).