Abstract
We consider real-time visual tracking with targets undergoing viewpoint changes. The problem is evaluated on a new and extensive dataset of vehicles undergoing large viewpoint changes. We propose an evaluation method in which tracking accuracy is measured under real-time computational complexity constraints and find that state-of-the-art agnostic trackers, as well as class detectors, are still struggling with this task. We study tracking schemes fusing real-time agnostic trackers with a non-real-time class detector used for template update, with two dominating update strategies emerging. We rigorously analyze the template update latency and demonstrate that such methods significantly outperform stand-alone trackers and class detectors. Results are demonstrated using two different trackers and a state-of-the-art classifier, and at several operating points of algorithm/hardware computational speed.
Original language | English |
---|---|
Pages (from-to) | 507-518 |
Number of pages | 12 |
Journal | Machine Vision and Applications |
Volume | 26 |
Issue number | 4 |
DOIs | |
State | Published - 1 May 2015 |
Externally published | Yes |
Keywords
- Detection
- Fusion
- Real time
- Tracking
ASJC Scopus subject areas
- Software
- Hardware and Architecture
- Computer Vision and Pattern Recognition
- Computer Science Applications