Visual Tracking of Arbitrary-Shaped Objects in Unconstrained Environments

Please enable javascript in your browser.

Abdollahi Pour Haghighi, Hojjat | 2013

1414 Viewed

Type of Document: M.Sc. Thesis
Language: Farsi
Document No: 44955 (19)
University: Sharif University of Technology
Department: Computer Engineering
Advisor(s): Manzouri, Mohammad Taghi; Jamzad, Mansour
Abstract:
Most of current state-of-the-art methods for object tracking use adaptive tracking-by-detection. The performance of state-of-the-art methods is almost real-time with acceptable accuracy. These methods use tracking-by-detection because of its robustness. Tracking-bydetection methods use a detector as a tracker and sweep input for object of interest. They use their predictions to adapt their parameters and therefore be adaptive to appearance change in target. While suitable for cases when the object does not disappear from the scene, these methods tend to fail on occlusions. In this work, we build on a novel approach called Tracking-Learning-Detection (TLD) that overcomes this problem. In methods based on TLD, a detector is trained with with examples found on the trajectory of a tracker that itself does not depend on the object detector. By decoupling object tracking and object detection we achieve high robustness and outperform existing adaptive tracking-by-detection methods. We show that by using simple features for object detection and by employing a cascaded approach considerable reduction of computing time is achieved. We evaluate our approach on existing standard datasets
Keywords:
Online Learning ; Adaptive Tracking ; Tracking by Detection ; Visual Tracking