Published on Fri Jul 28 2017

Group Re-Identification via Unsupervised Transfer of Sparse Features Encoding

Giuseppe Lisanti, Niki Martinel, Alberto Del Bimbo, Gian Luca Foresti

Person re-identification is best known as the problem of associating a single person that is observed from one or more disjoint cameras. We believe that the additional information carried by neighboring individuals provides a relevantvisual context that can be exploited to obtain a more robust match of single person images.

0
0
0
Abstract

Person re-identification is best known as the problem of associating a single person that is observed from one or more disjoint cameras. The existing literature has mainly addressed such an issue, neglecting the fact that people usually move in groups, like in crowded scenarios. We believe that the additional information carried by neighboring individuals provides a relevant visual context that can be exploited to obtain a more robust match of single persons within the group. Despite this, re-identifying groups of people compound the common single person re-identification problems by introducing changes in the relative position of persons within the group and severe self-occlusions. In this paper, we propose a solution for group re-identification that grounds on transferring knowledge from single person re-identification to group re-identification by exploiting sparse dictionary learning. First, a dictionary of sparse atoms is learned using patches extracted from single person images. Then, the learned dictionary is exploited to obtain a sparsity-driven residual group representation, which is finally matched to perform the re-identification. Extensive experiments on the i-LIDS groups and two newly collected datasets show that the proposed solution outperforms state-of-the-art approaches.

Mon Nov 21 2016
Computer Vision
Kernel Cross-View Collaborative Representation based Classification for Person Re-Identification
Collaborative Representation based Classification (CRC) has been employed successfully to address the small-sample-size problem in computer vision. The original CRC formulation is not well-suited for person re-identification since it does not consider that probe and gallery samples are from different cameras.
0
0
0
Fri May 17 2019
Computer Vision
Group Re-Identification with Multi-grained Matching and Integration
Group re-identification (Re-ID) is a very challenging task. The proposed representation seeks to characterize bothappearance and spatial relations of multi-grained objects. Optimal group-wise matching isfacilitated by a multi-order matching process which in turn,dynamically updates the importance weights.
0
0
0
Tue Apr 07 2020
Computer Vision
Unsupervised Person Re-identification via Softened Similarity Learning
Re-identification (re-ID) is an important topic in computer vision. This paper studies the unsupervised setting of re-ID, which does not require any labeled information.
0
0
0
Mon Mar 07 2016
Computer Vision
Learning a Discriminative Null Space for Person Re-identification
Most existing person re-identification (re-id) methods focus on learning the optimal distance metrics across camera views. We propose to overcome the SSS problem in re-id distance metric learning by matching people in a discriminative null space of the training data.
0
0
0
Fri Jun 09 2017
Computer Vision
Unsupervised Adaptive Re-identification in Open World Dynamic Camera Networks
Person re-identification is an open and challenging problem in computer vision. Existing approaches have concentrated on either designing the best feature representation or learning optimal matching metrics in a static setting. Most approaches have neglected the dynamic and open world nature of the re-Identification problem.
0
0
0
Fri Jul 01 2016
Computer Vision
Continuous Adaptation of Multi-Camera Person Identification Models through Sparse Non-redundant Representative Selection
Most traditional person identification systems rely on learning a static model on tediously labeled training data. We propose a convex optimization based iterative framework that progressively and judiciously chooses a sparse but informative set of samples for labeling. We also use a structure preserving a reconstruction based classifier to
0
0
0