An Ensemble of Invariant Features for Person Reidentification
- 9 December 2016
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 27 (3), 470-483
- https://doi.org/10.1109/tcsvt.2016.2637818
Abstract
This paper proposes an ensemble of invariant features (EIFs), which can properly handle the variations of color difference and human poses/viewpoints for matching pedestrian images observed in different cameras with nonoverlapping field of views. Our proposed method is a direct reidentification (re-id) method, which requires no prior domain learning based on prelabeled corresponding training data. The novel features consist of the holistic and region-based features. The holistic features are extracted by using a publicly available pretrained deep convolutional neural network used in generic object classification. In contrast, the region-based features are extracted based on our proposed two-way Gaussian mixture model fitting, which overcomes the self-occlusion and pose variations. To make a better generalization during recognizing identities without additional learning, the ensemble scheme aggregates all the feature distances using the similarity normalization. The proposed framework achieves robustness against partial occlusion, pose, and viewpoint changes. Moreover, the evaluation results show that our method outperforms the state-of-the-art direct re-id methods on the challenging benchmark viewpoint invariant pedestrian recognition and 3D people surveillance data sets.Keywords
This publication has 37 references indexed in Scilit:
- The Re-identification ChallengePublished by Springer Science and Business Media LLC ,2014
- Probabilistic people tracking with appearance models and occlusion classification: The AD-HOC systemPattern Recognition Letters, 2011
- Person Re-identification by Descriptive and Discriminative ClassificationLecture Notes in Computer Science, 2011
- Object matching in disjoint cameras using a color transfer approachMachine Vision and Applications, 2007
- Person tracking and reidentification: Introducing Panoramic Appearance Map (PAM) for feature representationMachine Vision and Applications, 2007
- Detecting Features in Spatial Point Processes with Clutter via Model-Based ClusteringJournal of the American Statistical Association, 1998
- Linear flaw detection in woven textiles using model-based clusteringPattern Recognition Letters, 1997
- Practical Bayesian Density Estimation Using Mixtures of NormalsJournal of the American Statistical Association, 1997
- Practical Bayesian Density Estimation Using Mixtures of NormalsJournal of the American Statistical Association, 1997
- On Information and SufficiencyThe Annals of Mathematical Statistics, 1951