Video-Based Person Re-identification with Adaptive Multi-part Features Learning

Video-based person re-identification plays a significant role in the video surveillance, which can automatically judge whether two non-overlapping video sequences of the pedestrian belong to the same class or not. However, many factors make it challenging, such as different viewpoints and illumination among different cameras, the occlusion, etc. Aiming at increasing the robustness to the occlusion, this paper extracts multi-part appearance features and the feature weight of each part is learned according to its importance. Besides, in order to fully utilize the information included in the video sequences, this paper combines the appearance features and spatial-temporal features of pedestrian by learning several independent metric kernels and fusing the learned metric distances. Extensive experiments on two public benchmark datasets, i.e., the iLIDS-VID and PRID-2011 datasets, demonstrate the effectiveness of the proposed method.

[1]  Xiang Li,et al.  Top-Push Video-Based Person Re-identification , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Xiao-Yuan Jing,et al.  Video-Based Person Re-Identification by Simultaneously Learning Intra-Video and Inter-Video Distance Metrics , 2016, IEEE Transactions on Image Processing.

[3]  Xiao-Yuan Jing,et al.  Semi-Supervised Cross-View Projection-Based Dictionary Learning for Video-Based Person Re-Identification , 2018, IEEE Transactions on Circuits and Systems for Video Technology.

[4]  Jesús Martínez del Rincón,et al.  Recurrent Convolutional Network for Video-Based Person Re-identification , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Horst Bischof,et al.  Person Re-identification by Descriptive and Discriminative Classification , 2011, SCIA.

[6]  Cordelia Schmid,et al.  A Spatio-Temporal Descriptor Based on 3D-Gradients , 2008, BMVC.

[7]  Horst Bischof,et al.  Relaxed Pairwise Learned Metric for Person Re-identification , 2012, ECCV.

[8]  Zhen Zhou,et al.  See the Forest for the Trees: Joint Spatial and Temporal Recurrent Neural Networks for Video-Based Person Re-identification , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Yoichi Sato.  [Foreword] Welcome to the Special Section on Doctoral Student Papers , 2019 .

[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]  Shaogang Gong,et al.  Transfer re-identification: From person to set-based verification , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Xiaogang Wang,et al.  Locally Aligned Feature Transforms across Views , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Tao Mei,et al.  PROVID: Progressive and Multimodal Vehicle Reidentification for Large-Scale Urban Surveillance , 2018, IEEE Transactions on Multimedia.

[14]  Zheng Liu,et al.  A fast adaptive spatio-temporal 3D feature for video-based person re-identification , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[15]  Hao Liu,et al.  Local region partition for person re-identification , 2019, Multimedia Tools and Applications.

[16]  Kuk-Jin Yoon,et al.  Improving Person Re-identification via Pose-Aware Multi-shot Matching , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Xiaodong Cai,et al.  Deep convolutional neural networks with adaptive spatial feature for person re-identification , 2017, 2017 IEEE 2nd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC).

[18]  Shengcai Liao,et al.  Deep Metric Learning for Person Re-identification , 2014, 2014 22nd International Conference on Pattern Recognition.

[19]  Xiaodong Yu,et al.  Learning Bidirectional Temporal Cues for Video-Based Person Re-Identification , 2018, IEEE Transactions on Circuits and Systems for Video Technology.

[20]  Yongdong Zhang,et al.  Multi-task deep visual-semantic embedding for video thumbnail selection , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Wu Liu,et al.  A Progressive Search Paradigm for the Internet of Things , 2018, IEEE MultiMedia.

[22]  Qi Tian,et al.  Video-Based Person Re-identification by Deep Feature Guided Pooling , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[23]  Shaogang Gong,et al.  Person Re-Identification by Discriminative Selection in Video Ranking , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Yu Cheng,et al.  Jointly Attentive Spatial-Temporal Pooling Networks for Video-Based Person Re-identification , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[25]  Jin Wang,et al.  Temporally aligned pooling representation for video-based person re-identification , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[26]  Shuicheng Yan,et al.  Video-Based Person Re-Identification With Accumulative Motion Context , 2017, IEEE Transactions on Circuits and Systems for Video Technology.

[27]  Bingpeng Ma,et al.  Video-Based Pedestrian Re-Identification by Adaptive Spatio-Temporal Appearance Model , 2017, IEEE Transactions on Image Processing.

[28]  Bo Yang,et al.  Integration of deep features and hand-crafted features for person re-identification , 2017, 2017 IEEE International Conference on Multimedia & Expo Workshops (ICMEW).