Visible Thermal Person Reidentification via Mutual Learning Convolutional Neural Network in 6G-Enabled Visual Internet of Things

Abstract

Visible thermal person reidentification (VT Re-ID) in the 6G-enabled Visual Internet of Things (VIoT) is essential for implementing 24-h surveillance in wide-area space. The existing methods mainly focus on reducing the visual difference between visible and thermal visual streams (V-streams). However, they cannot fully exploit the information of visible and thermal V-streams, which leads to suboptimal representations. In this article, we propose a novel deep network termed the mutual learning convolutional neural network (MLCNN) to transfer useful information between visible and thermal V-streams for VT Re-ID in 6G-enabled VIoT. The proposed MLCNN consists of the feature generation module and the mutual learning module. The feature generation module aims to map the input samples into a more discriminative feature space in order to decrease the intramodality difference. The mutual learning module employs the identification loss to supervise the predictive identity accuracy and utilizes the Kullback–Leibler divergence to constitute the mutual learning loss for useful information transfer. Extensive experiments on two popular visible thermal data sets (SYSU-MM01 and RegDB) prove the effectiveness of the proposed MLCNN.