Occluded Person Re-Identification

Person re-identification (re-id) suffers from a serious occlusion problem when applied to crowded public places. In this paper, we propose to retrieve a full-body person image by using a person image with occlusions. This differs significantly from the conventional person re-id problem where it is assumed that person images are detected without any occlusion. We thus call this new problem the occluded person re-identitification. To address this new problem, we propose a novel Attention Framework of Person Body (AFPB) based on deep learning, consisting of 1) an Occlusion Simulator (OS) which automatically generates artificial occlusions for full-body person images, and 2) multi-task losses that force the neural network not only to discriminate a person's identity but also to determine whether a sample is from the occluded data distribution or the full-body data distribution. Experiments on a new occluded person re-id dataset and three existing benchmarks modified to include full-body person images and occluded person images show the superiority of the proposed method.

[1]  Luc Van Gool,et al.  A mobile vision system for robust multi-person tracking , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Jian-Huang Lai,et al.  Multi-shot Person Re-identification with Automatic Ambiguity Inference and Removal , 2014, 2014 22nd International Conference on Pattern Recognition.

[3]  Qi Tian,et al.  MARS: A Video Benchmark for Large-Scale Person Re-Identification , 2016, ECCV.

[4]  Shaogang Gong,et al.  Learning a Discriminative Null Space for Person Re-identification , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Francesco Solera,et al.  Performance Measures and a Data Set for Multi-target, Multi-camera Tracking , 2016, ECCV Workshops.

[6]  Jian-Huang Lai,et al.  Person Re-Identification by Camera Correlation Aware Feature Augmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Ali Borji,et al.  Salient Object Detection: A Benchmark , 2015, IEEE Transactions on Image Processing.

[8]  Jian-Huang Lai,et al.  Mirror Representation for Modeling View-Specific Transform in Person Re-Identification , 2015, IJCAI.

[9]  Yi Yang,et al.  Random Erasing Data Augmentation , 2017, AAAI.

[10]  Shengcai Liao,et al.  Person re-identification by Local Maximal Occurrence representation and metric learning , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Yi Yang,et al.  Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in Vitro , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[12]  Jianhuang Lai,et al.  P2SNet: Can an Image Match a Video for Person Re-Identification in an End-to-End Way? , 2018, IEEE Transactions on Circuits and Systems for Video Technology.

[13]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Jian-Huang Lai,et al.  Person re-identification with multi-level adaptive correspondence models , 2015, Neurocomputing.

[15]  Michael Jones,et al.  An improved deep learning architecture for person re-identification , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Liang Lin,et al.  Deep feature learning with relative distance comparison for person re-identification , 2015, Pattern Recognit..

[17]  Yifan Sun,et al.  SVDNet for Pedestrian Retrieval , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[18]  Takahiro Okabe,et al.  Hierarchical Gaussian Descriptor for Person Re-identification , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Xiaogang Wang,et al.  Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identification , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Xiang Li,et al.  Partial Person Re-Identification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[21]  Jian-Huang Lai,et al.  Deep Ranking for Person Re-Identification via Joint Representation Learning , 2015, IEEE Transactions on Image Processing.

[22]  Jian-Huang Lai,et al.  Deep Growing Learning , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).