Cross-Domain Person Reidentification Using Domain Adaptation Ranking SVMs

• Published in: IEEE transactions on image processing Vol. 24; no. 5; pp. 1599 - 1613
• Main Authors: Ma, Andy J., Jiawei Li, Yuen, Pong C., Ping Li
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.05.2015
• Subjects: Adaptation models; Adaptive Learning; Algorithms; Biometric Identification - methods; Biometry - methods; Cameras; Data models; Domain Adaptation; Equations; Feature extraction; Humans; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Mathematical model; Person Re-Identification; Photography - methods; Ranking SVMs; Reproducibility of Results; Sensitivity and Specificity; Subtraction Technique; Target Positive Mean; Vectors; ranking SVMs; target positive mean; domain adaptation; Person re-identification; adaptive learning
• ISSN: 1057-7149; 1941-0042
• DOI: 10.1109/TIP.2015.2395715

This paper addresses a new person reidentification problem without label information of persons under nonoverlapping target cameras. Given the matched (positive) and unmatched (negative) image pairs from source domain cameras, as well as unmatched (negative) and unlabeled image pairs from target domain cameras, we propose an adaptive ranking support vector machines (AdaRSVMs) method for reidentification under target domain cameras without person labels. To overcome the problems introduced due to the absence of matched (positive) image pairs in the target domain, we relax the discriminative constraint to a necessary condition only relying on the positive mean in the target domain. To estimate the target positive mean, we make use of all the available data from source and target domains as well as constraints in person reidentification. Inspired by adaptive learning methods, a new discriminative model with high confidence in target positive mean and low confidence in target negative image pairs is developed by refining the distance model learnt from the source domain. Experimental results show that the proposed AdaRSVM outperforms existing supervised or unsupervised, learning or non-learning reidentification methods without using label information in target cameras. Moreover, our method achieves better reidentification performance than existing domain adaptation methods derived under equal conditional probability assumption.