Exploiting Multiple Detections for Person Re-Identification

Abstract

Re-identification systems aim at recognizing the same individuals in multiple cameras, and one of the most relevant problems is that the appearance of same individual varies across cameras due to illumination and viewpoint changes. This paper proposes the use of cumulative weighted brightness transfer functions (CWBTFs) to model these appearance variations. Different from recently proposed methods which only consider pairs of images to learn a brightness transfer function, we exploit such a multiple-frame-based learning approach that leverages consecutive detections of each individual to transfer the appearance. We first present a CWBTF framework for the task of transforming appearance from one camera to another. We then present a re-identification framework where we segment the pedestrian images into meaningful parts and extract features from such parts, as well as from the whole body. Jointly, both of these frameworks contribute to model the appearance variations more robustly. We tested our approach on standard multi-camera surveillance datasets, showing consistent and significant improvements over existing methods on three different datasets without any other additional cost. Our approach is general and can be applied to any appearance-based method.

Object Re-Identification Using Multimodal Aerial Imagery and Conditional Adversarial Networks

“…The problem of object re-identification is important for various computer vision applications, such multi-modal image segmentation and object detection, autonomous driving, security etc. So currently it attracts attention of many researches (Farenzena et al, 2010, Gong et al, 2014, Wu et al, 2017, Wang et al, 2019, Bhuiyan et al, 2018, Prosser et al, 2008, Bhuiyan et al, 2015. New methods of re-identification allow to significantly improve the matching performance.…”

A Multi-Camera Tracker for Monitoring Pedestrians in Enclosed Environments

“…A popular CNN architecture is ResNet He et al (2016), which is used as a backbone for feature extraction in various applications. Bhuiyan et al (2018) learn feature extraction using cumulative weighted brightness transfer functions (CWBTFs) to model appearance variations. Sun et al (2018) propose a part based convolution (PBC) network.…”

Appearance model update based on online learning and soft‐biometrics traits for people re‐identification in multi‐camera environments

“…PKU‐REID, SAIVT‐SoftBio, iLIDS‐VID, and PRID. With the purpose of transfer, the appearance variations in [18] proposed a model using cumulative weighted brightness transfer function employing a set of images instead of image‐per‐image transfer. For the experiments, the VIPeR, CAVIAR4REID, PRID2011, and SAIVT‐SoftBio data sets were considered.…”

“…The compared works are proposed in [12, 13, 15–20], all described in Section 2. Here, it can be seen that in the CAVIAR4REID data set, the best result was obtained with our proposed methodology, in contrast, with the SAIVT‐SoftBio data set, the best result was obtained with the work presented in [15]; nevertheless, they only use images from four cameras, instead of the total of eight cameras included in this data set.…”