Network Consistent Data Association

Abstract

Existing data association techniques mostly focus on matching pairs of data-point sets and then repeating this process along space-time to achieve long term correspondences. However, in many problems such as person re-identification, a set of data-points may be observed at multiple spatio-temporal locations and/or by multiple agents in a network and simply combining the local pairwise association results between sets of data-points often leads to inconsistencies over the global space-time horizons. In this paper, we propose a Novel Network Consistent Data Association (NCDA) framework formulated as an optimization problem that not only maintains consistency in association results across the network, but also improves the pairwise data association accuracies. The proposed NCDA can be solved as a binary integer program leading to a globally optimal solution and is capable of handling the challenging data-association scenario where the number of data-points varies across different sets of instances in the network. We also present an online implementation of NCDA method that can dynamically associate new observations to already observed data-points in an iterative fashion, while maintaining network consistency. We have tested both the batch and the online NCDA in two application areas-person re-identification and spatio-temporal cell tracking and observed consistent and highly accurate data association results in all the cases.

Person Re-identification: Current Approaches and Future Challenges

“…Building on preliminary result on network consistent re-id [16,17], we now ask whether consistency can be used to reduce the labeling effort. However, in order to take advantage of consistency relations for reducing the labeling effort, we have to choose image pairs in a judicious manner.…”

The Future of Camera Networks

“…In addition, cameras need to ensure they track the same object. This requires efficient data association across multiple cameras [6,19].…”

Person re-identification using multiple first-person-views on wearable devices

“…The problem of network inconsistency in classic person re-identification tasks was introduced in [12] and later expanded in [10]. A binary integer program for establishing consistency in re-identification and thereby improving association accuracy was proposed in these works and termed as Network Consistent Re-identification (NCR) [12] or Network Consistent Data Association (NCDA) [10].…”

“…A binary integer program for establishing consistency in re-identification and thereby improving association accuracy was proposed in these works and termed as Network Consistent Re-identification (NCR) [12] or Network Consistent Data Association (NCDA) [10].…”