A data association algorithm for multiple object tracking in video sequences

This dissertation deals with camera-based offline multiple object tracking and explores higher-order data association models. Due to their extensive exploitation of the available information, such models are promising approaches in current research. However, they commonly represent NP-hard optimization problems so that their application in practice is challenging. The first part of this thesis proposes a binary quadratic program that enables to globally fuse signals within a higher-order data association model. This enables to overcome weaknesses of the individual signals. An approximate solver based on the Frank-Wolfe algorithm is presented and analyzed. Its benefit is demonstrated in two setups: fusion of two detectors and combining signals coming from a video and body-worn inertial measurement units. The second part of this thesis proposes an extension of the disjoint path model by higher-order information and connectivity priors, resulting in a binary linear program. Efficient separation algorithms are proposed and integrated into a cutting-plane algorithm, making it possible for the first time to solve higher-order data association globally in practice. Contents 1 Intro...

Download Full-text

Coupled data association andl1 minimization for multiple object tracking under occlusion

10.1117/12.2073887 ◽

2014 ◽

Author(s):

Xue Wang ◽

Qing Wang

Keyword(s):

Object Tracking ◽

Data Association ◽

Multiple Object Tracking ◽

Multiple Object

Download Full-text

An New Method for Multi-Object Tracking Using Energy Minimization-Based Data Association

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.427-429.1822 ◽

2013 ◽

Vol 427-429 ◽

pp. 1822-1825

Author(s):

Zhen Hai Wang ◽

Ki Cheon Hong

Keyword(s):

Object Tracking ◽

Energy Minimization ◽

Moving Objects ◽

Data Association ◽

Multiple Object Tracking ◽

Object Extraction ◽

Frame Difference ◽

Multiple Object ◽

Important Research Topic ◽

Key Steps

multiple object tracking is an active and important research topic. It faces many challenging problems. Object extraction and data association are two most key steps in multiple object tracking. To improve tracking performance, this paper proposed a tracking method which combines Kalman filter and energy minimization-based data association. Moving objects are segmented through frame difference. Its can be consider as the vertex. All detections in adjacent frames are be used to construct a graph. The energy is finally minimized with a graph cuts optimization. Data association can be consider as multiple labeling problems. Object corresponding can be obtained through energy minimization. Experiment results demonstrate this method can be accurately tracking two moving objects.

Download Full-text

Saliency Guided Data Association Measure for Multiple-Object Tracking

Pervasive Systems, Algorithms and Networks - Communications in Computer and Information Science ◽

10.1007/978-3-030-30143-9_3 ◽

2019 ◽

pp. 29-42

Author(s):

Syeda Fouzia ◽

Mark Bell ◽

Reinhard Klette

Keyword(s):

Object Tracking ◽

Data Association ◽

Multiple Object Tracking ◽

Association Measure ◽

Multiple Object

Download Full-text