A Neuromorphic Person Re-Identification Framework for Video Surveillance

Abstract

In this article, we present a Neuromorphic Person Re-Identification (NPReId) framework to establish the correspondence among individuals observed across two disjoint camera views. The framework comprises three modules (observation, cognition, and contemplation), inspired by the Form-and-Color-and-Depth (FACADE) theory model of object recognition system. In observation module, a semantic partitioning scheme is introduced to segment a pedestrian into several logical parts, and an exhaustive set of experiments have been carried out to select the best possible complementary feature cues. In cognition module, an unsupervised procedure is suggested to partition the gallery candidates into multiple consensus clusters with high intra-cluster and low inter-cluster similarity. A supervised classifier is then deployed to learn the relationship between each gallery candidate and its associated cluster, which is subsequently used to identify a set of inlier consensus clusters. This module also includes weighing of contribution of each feature channel towards defining a consensus cluster. Finally, in contemplation module, the contributory weights are employed in a correlation-based similarity measure to find the corresponding match within the inlier set. The proposed framework is compared with several state-of-the-art methods on three challenging datasets: VIPeR, iLIDS-VID, and CUHK01. The tabular results alongside the performance curves demonstrate the superiority of NPReId over the counterparts.