Discriminative Feature Transformation for Occluded Pedestrian Detection

Despite promising performance achieved by deep con- volutional neural networks for non-occluded pedestrian de- tection, it remains a great challenge to detect partially oc- cluded pedestrians. Compared with non-occluded pedes- trian examples, it is generally more difficult to distinguish occluded pedestrian examples from background in featue space due to the missing of occluded parts. In this paper, we propose a discriminative feature transformation which en- forces feature separability of pedestrian and non-pedestrian examples to handle occlusions for pedestrian detection. Specifically, in feature space it makes pedestrian exam- ples approach the centroid of easily classified non-occluded pedestrian examples and pushes non-pedestrian examples close to the centroid of easily classified non-pedestrian ex- amples. Such a feature transformation partially compen- sates the missing contribution of occluded parts in feature space, therefore improving the performance for occluded pedestrian detection. We implement our approach in the Fast R-CNN framework by adding one transformation net- work branch. We validate the proposed approach on two widely used pedestrian detection datasets: Caltech and CityPersons. Experimental results show that our approach achieves promising performance for both non-occluded and occluded pedestrian detection.

[1]  Shuicheng Yan,et al.  Scale-Aware Fast R-CNN for Pedestrian Detection , 2015, IEEE Transactions on Multimedia.

[2]  Xiaoming Liu,et al.  Illuminating Pedestrians via Simultaneous Detection and Segmentation , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[3]  Ming Tang,et al.  PCN: Part and Context Information for Pedestrian Detection with CNNs , 2018, BMVC.

[4]  Bernt Schiele,et al.  CityPersons: A Diverse Dataset for Pedestrian Detection , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Baoxin Li,et al.  Semantic Cues Enhanced Multimodality Multistream CNN for Action Recognition , 2019, IEEE Transactions on Circuits and Systems for Video Technology.

[6]  Anelia Angelova,et al.  Real-Time Pedestrian Detection with Deep Network Cascades , 2015, BMVC.

[7]  Larry S. Davis,et al.  Bilattice-based Logical Reasoning for Human Detection , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

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

[9]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[10]  Gunhee Kim,et al.  Improving Occlusion and Hard Negative Handling for Single-Stage Pedestrian Detectors , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[11]  Shiliang Pu,et al.  Small-Scale Pedestrian Detection Based on Topological Line Localization and Temporal Feature Aggregation , 2018, ECCV.

[12]  Chunluan Zhou,et al.  Bi-box Regression for Pedestrian Detection and Occlusion Estimation , 2018, ECCV.

[13]  Yuning Jiang,et al.  Repulsion Loss: Detecting Pedestrians in a Crowd , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[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]  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.

[16]  Xiaogang Wang,et al.  Pedestrian detection aided by deep learning semantic tasks , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Xiangyu Zhang,et al.  CrowdHuman: A Benchmark for Detecting Human in a Crowd , 2018, ArXiv.

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

[19]  Jian Yang,et al.  Occluded Pedestrian Detection Through Guided Attention in CNNs , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[20]  Shihong Lao,et al.  A Structural Filter Approach to Human Detection , 2010, ECCV.

[21]  Chunluan Zhou,et al.  Learning to Integrate Occlusion-Specific Detectors for Heavily Occluded Pedestrian Detection , 2016, ACCV.

[22]  Gang Wang,et al.  Graininess-Aware Deep Feature Learning for Pedestrian Detection , 2018, ECCV.

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

[24]  Xiaogang Wang,et al.  A discriminative deep model for pedestrian detection with occlusion handling , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[25]  Xiaogang Wang,et al.  Modeling Mutual Visibility Relationship in Pedestrian Detection , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[26]  Liang Lin,et al.  Is Faster R-CNN Doing Well for Pedestrian Detection? , 2016, ECCV.

[27]  Chunluan Zhou,et al.  Occlusion Pattern Discovery for Object Detection and Occlusion Reasoning , 2020, IEEE Transactions on Circuits and Systems for Video Technology.

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

[29]  Yuning Jiang,et al.  What Can Help Pedestrian Detection? , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[30]  Shifeng Zhang,et al.  Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd , 2018, ECCV.

[31]  Luc Van Gool,et al.  Handling Occlusions with Franken-Classifiers , 2013, 2013 IEEE International Conference on Computer Vision.

[32]  Rogério Schmidt Feris,et al.  A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection , 2016, ECCV.

[33]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[34]  Nicu Sebe,et al.  Learning Cross-Modal Deep Representations for Robust Pedestrian Detection , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[35]  Jungwon Lee,et al.  Fused DNN: A Deep Neural Network Fusion Approach to Fast and Robust Pedestrian Detection , 2016, 2017 IEEE Winter Conference on Applications of Computer Vision (WACV).

[36]  Bin Yang,et al.  Convolutional Channel Features , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[37]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[38]  Nuno Vasconcelos,et al.  Learning Complexity-Aware Cascades for Deep Pedestrian Detection , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[39]  Wei Liu,et al.  Learning Efficient Single-Stage Pedestrian Detectors by Asymptotic Localization Fitting , 2018, ECCV.

[40]  王晓刚.  Single-Pedestrian Detection aided by Multi-pedestrian Detection , 2013 .

[41]  Xiaogang Wang,et al.  Joint Deep Learning for Pedestrian Detection , 2013, 2013 IEEE International Conference on Computer Vision.

[42]  Chunluan Zhou,et al.  Multi-label Learning of Part Detectors for Heavily Occluded Pedestrian Detection , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[43]  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.

[44]  Xiaogang Wang,et al.  Deep Learning Strong Parts for Pedestrian Detection , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

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