Supervised learning and evaluation of KITTI's cars detector with DPM

This paper carries out a discussion on the supervised learning of a car detector built as a Discriminative Part-based Model (DPM) from images in the recently published KITTI benchmark suite as part of the object detection and orientation estimation challenge. We present a wide set of experiments and many hints on the different ways to supervise and enhance the well-known DPM on a challenging and naturalistic urban dataset as KITTI. The evaluation algorithm and metrics, the selection of a clean but representative subset of training samples and the DPM tuning are key factors to learn an object detector in a supervised fashion. We provide evidence of subtle differences in performance depending on these aspects. Besides, the generalization of the trained models to an independent dataset is validated by 5-fold cross-validation.

[1]  P. Fua,et al.  Pose estimation for category specific multiview object localization , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Fakhri Karray,et al.  Intelligent Parking System Design Using FPGA , 2006, 2006 International Conference on Field Programmable Logic and Applications.

[3]  Deva Ramanan,et al.  Analyzing 3D Objects in Cluttered Images , 2012, NIPS.

[4]  Peter V. Gehler,et al.  Occlusion Patterns for Object Class Detection , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Thomas B. Moeslund,et al.  Vision-Based Traffic Sign Detection and Analysis for Intelligent Driver Assistance Systems: Perspectives and Survey , 2012, IEEE Transactions on Intelligent Transportation Systems.

[6]  Charless C. Fowlkes,et al.  Multiresolution Models for Object Detection , 2010, ECCV.

[7]  조재호.  Active Safety 동향 및 도전과제 , 2014 .

[8]  Silvio Savarese,et al.  Deformable part models revisited: A performance evaluation for object category pose estimation , 2011, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops).

[9]  I. Kokkinos.  Rapid Deformable Object Detection using Bounding-based Techniques , 2012 .

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

[11]  Mohan M. Trivedi,et al.  A review of recent developments in vision-based vehicle detection , 2013, 2013 IEEE Intelligent Vehicles Symposium (IV).

[12]  Andrew M. Wallace,et al.  Efficient Resource Allocation for Attentive Automotive Vision Systems , 2012, IEEE Transactions on Intelligent Transportation Systems.

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

[14]  Uwe Franke,et al.  From stixels to objects — A conditional random field based approach , 2013, 2013 IEEE Intelligent Vehicles Symposium (IV).

[15]  Hermann Rohling,et al.  Radar sensor for car applications , 1994, Proceedings of IEEE Vehicular Technology Conference (VTC).

[16]  I. Parra,et al.  Automatic LightBeam Controller for driver assistance , 2011, Machine Vision and Applications.

[17]  Bernt Schiele,et al.  Monocular Visual Scene Understanding: Understanding Multi-Object Traffic Scenes , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Sven J. Dickinson,et al.  3D Object Detection and Viewpoint Estimation with a Deformable 3D Cuboid Model , 2012, NIPS.

[19]  Charless C. Fowlkes,et al.  Do We Need More Training Data or Better Models for Object Detection? , 2012, BMVC.

[20]  Andreas Geiger,et al.  Joint 3D Estimation of Objects and Scene Layout , 2011, NIPS.

[21]  Andreas Geiger,et al.  Are we ready for autonomous driving? The KITTI vision benchmark suite , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

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

[23]  Michael Brady.  Intelligent vision , 1990 .

[24]  Pietro Perona,et al.  Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[25]  Sebastian Thrun,et al.  Junior: The Stanford entry in the Urban Challenge , 2008, J. Field Robotics.

[26]  Peter V. Gehler,et al.  3D2PM - 3D Deformable Part Models , 2012, ECCV.