Handling Occlusions with Franken-Classifiers

Detecting partially occluded pedestrians is challenging. A common practice to maximize detection quality is to train a set of occlusion-specific classifiers, each for a certain amount and type of occlusion. Since training classifiers is expensive, only a handful are typically trained. We show that by using many occlusion-specific classifiers, we outperform previous approaches on three pedestrian datasets, INRIA, ETH, and Caltech USA. We present a new approach to train such classifiers. By reusing computations among different training stages, 16 occlusion-specific classifiers can be trained at only one tenth the cost of one full training. We show that also test time cost grows sub-linearly.

[1]  Piotr Dollár,et al.  Crosstalk Cascades for Frame-Rate Pedestrian Detection , 2012, ECCV.

[2]  Andrew Zisserman,et al.  Structured output regression for detection with partial truncation , 2009, NIPS.

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

[4]  Derek Hoiem,et al.  Diagnosing Error in Object Detectors , 2012, ECCV.

[5]  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.

[6]  Bernt Schiele,et al.  Detection and Tracking of Occluded People , 2014, International Journal of Computer Vision.

[7]  Bernt Schiele,et al.  Monocular 3D scene understanding with explicit occlusion reasoning , 2011, CVPR 2011.

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

[9]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[10]  Christoph H. Lampert,et al.  Learning to Localize Objects with Structured Output Regression , 2008, ECCV.

[11]  Daphne Koller,et al.  A segmentation-aware object detection model with occlusion handling , 2011, CVPR 2011.

[12]  David A. McAllester,et al.  Object Detection with Grammar Models , 2011, NIPS.

[13]  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).

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

[15]  Horst Bischof,et al.  Detecting Partially Occluded Objects with an Implicit Shape Model Random Field , 2012, ACCV.

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

[17]  Antonio Torralba,et al.  Sharing features: efficient boosting procedures for multiclass object detection , 2004, CVPR 2004.

[18]  M. Shelley.  Frankenstein, Or The Modern Prometheus , 2018, Primary Sources on Monsters.

[19]  Luc Van Gool,et al.  Seeking the Strongest Rigid Detector , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[20]  Dariu Gavrila,et al.  Multi-cue pedestrian classification with partial occlusion handling , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.