Self-adapting part-based pedestrian detection using a fish-eye camera

Nowadays, fish-eye cameras play an increasingly important role in intelligent vehicles because of its wide field of view. Using fish-eye camera, pedestrians around the vehicles could be monitored expediently, but the problem of pedestrian distortion has always existed. This paper creates a new warping pedestrian benchmark using imaging principle of the fish-eye camera based on ETH pedestrian benchmark. With this practical benchmark, warping pedestrians are trained differently according to the position in fish-eye images. A self-adapting part-based algorithm is proposed to detect pedestrian with different degrees of deformation. Moreover, GPU is used to accelerate the whole algorithm to guarantee the real-time performance. Experiments show that the algorithm has competitive accuracy.

[1]  Pietro Perona,et al.  Fast Feature Pyramids for Object Detection , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[3]  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).

[4]  Liam Kilmartin,et al.  A Blind-Zone Detection Method Using a Rear-Mounted Fisheye Camera With Combination of Vehicle Detection Methods , 2016, IEEE Transactions on Intelligent Transportation Systems.

[5]  J. Yamaguchi,et al.  Human tracking using fisheye images , 2007, SICE Annual Conference 2007.

[6]  Vincent Frémont,et al.  Deformable parts model for people detection in heavy machines applications , 2014, 2014 13th International Conference on Control Automation Robotics & Vision (ICARCV).

[7]  Massimo Bertozzi,et al.  360° Detection and tracking algorithm of both pedestrian and vehicle using fisheye images , 2015, 2015 IEEE Intelligent Vehicles Symposium (IV).

[8]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Andrea Signifredi,et al.  A coarse-to-fine vehicle detector running in real-time , 2014, 17th International IEEE Conference on Intelligent Transportation Systems (ITSC).

[10]  Günther Palm,et al.  Surround view pedestrian detection using heterogeneous classifier cascades , 2011, 2011 14th International IEEE Conference on Intelligent Transportation Systems (ITSC).

[11]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[12]  Wolfgang Schulz,et al.  Pedestrian Recognition from a Moving Catadioptric Camera , 2007, DAGM-Symposium.

[13]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[14]  Dan Levi,et al.  Vision-based pedestrian detection for rear-view cameras , 2014, 2014 IEEE Intelligent Vehicles Symposium Proceedings.

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

[16]  Alberto Broggi,et al.  Vehicle detection for autonomous parking using a Soft-Cascade AdaBoost classifier , 2014, 2014 IEEE Intelligent Vehicles Symposium Proceedings.

[17]  Yucheng Liu,et al.  A Surround View Camera Solution for Embedded Systems , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.