Multi-camera Multi-Object Tracking

TL;DR

This paper introduces a multi-camera multi-object tracking pipeline that models the problem as a global graph and uses a generalized maximum multi-clique algorithm, integrating appearance and motion data for improved tracking across multiple cameras.

Contribution

It presents a novel graph-based approach for multi-camera multi-object tracking that jointly considers cross-camera and cross-frame data association using advanced similarity measures.

Findings

Effective in complex multi-camera environments

Outperforms existing methods on benchmark datasets

Integrates appearance and motion features for robust tracking

Abstract

In this paper, we propose a pipeline for multi-target visual tracking under multi-camera system. For multi-camera system tracking problem, efficient data association across cameras, and at the same time, across frames becomes more important than single-camera system tracking. However, most of the multi-camera tracking algorithms emphasis on single camera across frame data association. Thus in our work, we model our tracking problem as a global graph, and adopt Generalized Maximum Multi Clique optimization problem as our core algorithm to take both across frame and across camera data correlation into account all together. Furthermore, in order to compute good similarity scores as the input of our graph model, we extract both appearance and dynamic motion similarities. For appearance feature, Local Maximal Occurrence Representation(LOMO) feature extraction algorithm for ReID is conducted. When it comes to capturing the dynamic information, we build Hankel matrix for each tracklet of target and apply rank estimation with Iterative Hankel Total Least Squares(IHTLS) algorithm to it. We evaluate our tracker on the challenging Terrace Sequences from EPFL CVLAB as well as recently published Duke MTMC dataset.