People detection in top-view fisheye imaging

We address the problem of people detection in top-view fisheye imaging. Even within the same top-view fisheye frame, upright people appear slanted in various directions and are distorted in different ways. Due to this variability, standard people detectors are not directly applicable to top-view fisheye frames, and dedicated people detectors for the top-view fisheye domain are hard to design. We extract features in the fisheye frame, unwrap them to a perspectivelike feature map, and forward them to a people detector designed and trained for common perspective images. Extracting the features before unwrapping prevents harmful smoothing of the gradient information. To facilitate feature unwrapping, we employ dense feature extraction and compute the unwrapping Jacobian. Distortion-free unwrapping is known to be impossible. We optimize the unwrapping method for the explicit goal of people detection performance. Applying a tunable fisheye camera model to project the fisheye image plane onto a unit half sphere, followed by the stereographic map projection, we obtain people detection performance similar to the standard perspective case. We complete the solution by introducing a convenient purposive fisheye-camera calibration process, optimized for subsequent people detection performance.

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

[2]  John Platt,et al.  Probabilistic Outputs for Support vector Machines and Comparisons to Regularized Likelihood Methods , 1999 .

[3]  Bernt Schiele,et al.  A Performance Evaluation of Single and Multi-feature People Detection , 2008, DAGM-Symposium.

[4]  Shree K. Nayar,et al.  Generation of Perspective and Panoramic Video from Omnidirectional Video , 1997 .

[5]  P. L. Venetianer,et al.  A Robust Human Detection and Tracking System Using a Human-Model-Based Camera Calibration , 2016 .

[6]  Andrew Hunter,et al.  A Fast Model-Free Morphology-Based Object Tracking Algorithm , 2002, BMVC.

[7]  Masafumi Hashimoto,et al.  People detection and tracking from fish-eye image based on probabilistic appearance model , 2011, SICE Annual Conference 2011.

[8]  Albert Ali Salah,et al.  Feature-based tracking on a multi-omnidirectional camera dataset , 2012, 2012 5th International Symposium on Communications, Control and Signal Processing.

[9]  Andrew Hunter,et al.  Measurement of retinal vessel widths from fundus images based on 2-D modeling , 2004, IEEE Transactions on Medical Imaging.

[10]  Kostas Daniilidis,et al.  A Unifying Theory for Central Panoramic Systems and Practical Applications , 2000, ECCV.

[11]  John P. Snyder,et al.  Map Projections: A Working Manual , 2012 .

[12]  Christian Wiede,et al.  Virtual perspective views for real-time people detection using an omnidirectional camera , 2014, 2014 IEEE International Conference on Imaging Systems and Techniques (IST) Proceedings.

[13]  Sun-Tae Chung,et al.  ConvNets and AGMM based real-time human detection under fisheye camera for embedded surveillance , 2016, 2016 International Conference on Information and Communication Technology Convergence (ICTC).

[14]  Wang Fengwen,et al.  Generation of Panoramic View from 360 Degree Fisheye Images Based on Angular Fisheye Projection , 2011, 2011 10th International Symposium on Distributed Computing and Applications to Business, Engineering and Science.

[15]  Yohan Dupuis,et al.  Enhanced omnidirectional image unwrapping for face detection , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[16]  Pascal Frossard,et al.  OmniSIFT: Scale invariant features in omnidirectional images , 2010, 2010 IEEE International Conference on Image Processing.

[17]  Pietro Perona,et al.  Integral Channel Features , 2009, BMVC.

[18]  Alvin F. Martin,et al.  The DET curve in assessment of detection task performance , 1997, EUROSPEECH.

[19]  Yohan Dupuis,et al.  A direct approach for face detection on omnidirectional images , 2011, 2011 IEEE International Symposium on Robotic and Sensors Environments (ROSE).

[20]  Philippe Martinet,et al.  Evaluation of the Unified Model of the Sphere for Fisheye Cameras in Robotic Applications , 2012, Adv. Robotics.

[21]  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).

[22]  Pietro Perona,et al.  Pedestrian Detection: An Evaluation of the State of the Art , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  Juho Kannala,et al.  A generic camera model and calibration method for conventional, wide-angle, and fish-eye lenses , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Ming-Liang Wang,et al.  An Intelligent Surveillance System Based on an Omnidirectional Vision Sensor , 2006, 2006 IEEE Conference on Cybernetics and Intelligent Systems.

[25]  Donald Fenna,et al.  Cartographic Science: A Compendium of Map Projections, with Derivations , 2006 .

[26]  Yalin Bastanlar,et al.  A Direct approach for human detection with catadioptric omnidirectional cameras , 2014, 2014 22nd Signal Processing and Communications Applications Conference (SIU).

[27]  Pietro Perona,et al.  The Fastest Pedestrian Detector in the West , 2010, BMVC.

[28]  Yao Wang,et al.  Human detection in fish-eye images using HOG-based detectors over rotated windows , 2014, 2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW).