G2P: a new descriptor for pedestrian detection

Pedestrian detection plays an important role in many applications. Since its birth 13 years ago, Histogram Of Gradient (HOG) descriptor has become a popular descriptor for pedestrian detection. 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 the literature. The generation process of these descriptors is summarized in this work, and a new descriptor is presented for pedestrian detection. 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]  N. Pettersson,et al.  A new pedestrian dataset for supervised learning , 2008, 2008 IEEE Intelligent Vehicles Symposium.

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

[3]  K. J. Stout,et al.  Gaussian filtering of three-dimensional engineering surface topography , 1993, Other Conferences.

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

[5]  Luc Van Gool,et al.  Pedestrian detection at 100 frames per second , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

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

[7]  David A. McAllester,et al.  Object Detection with Discriminatively Trained Part Based Models , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[9]  Luc Van Gool,et al.  Fast Stixel Computation for Fast Pedestrian Detection , 2012, ECCV Workshops.

[10]  Jorge Martínez-Carballido,et al.  Using adaptive threshold to detect pedestrians crossing on a street for Advanced Driver Assistance Systems , 2012, CONIELECOMP 2012, 22nd International Conference on Electrical Communications and Computers.

[11]  Mark Everingham,et al.  Implicit color segmentation features for pedestrian and object detection , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[12]  Qiong Liu,et al.  Segmentation of Far-infrared pedestrians for advanced driver-assistance systems , 2015, 2015 IEEE International Conference on Imaging Systems and Techniques (IST).

[13]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[14]  Shuicheng Yan,et al.  An HOG-LBP human detector with partial occlusion handling , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[15]  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.

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

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

[18]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Ming Yang,et al.  G2P: A new descriptor for pedestrian detection , 2017, 2017 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC).

[20]  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).

[21]  Tomaso A. Poggio,et al.  A general framework for object detection , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[22]  Hans-Georg Beyer,et al.  The Theory of Evolution Strategies , 2001, Natural Computing Series.

[23]  E. Rückert.  Detecting Pedestrians by Learning Shapelet Features , 2007 .

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

[25]  David A. McAllester,et al.  A discriminatively trained, multiscale, deformable part model , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[26]  Ramakant Nevatia,et al.  Detection of multiple, partially occluded humans in a single image by Bayesian combination of edgelet part detectors , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[27]  R. C. Thomas,et al.  Computer Vision: A First Course , 1988 .

[28]  Tommy W. S. Chow,et al.  Object-Level Video Advertising: An Optimization Framework , 2017, IEEE Transactions on Industrial Informatics.

[29]  Li-Ta Hsu,et al.  A Probabilistic Model for the Estimation of Pedestrian Crossing Behavior at Signalized Intersections , 2015, 2015 IEEE 18th International Conference on Intelligent Transportation Systems.

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

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