Invariant Hough Random Ferns for Object Detection and Tracking
Joint Authors
Yao, Yanbin
Lin, Yimin
Lu, Naiguang
Zou, Fang
Du, Zhaocai
Lou, Xiaoping
Source
Mathematical Problems in Engineering
Issue
Vol. 2014, Issue 2014 (31 Dec. 2014), pp.1-20, 20 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2014-04-08
Country of Publication
Egypt
No. of Pages
20
Main Subjects
Abstract EN
This paper introduces an invariant Hough random ferns (IHRF) incorporating rotation and scale invariance into the local feature description, random ferns classifier training, and Hough voting stages.
It is especially suited for object detection under changes in object appearance and scale, partial occlusions, and pose variations.
The efficacy of this approach is validated through experiments on a large set of challenging benchmark datasets, and the results demonstrate that the proposed method outperforms state-of-the-art conventional methods such as bounding-box-based and part-based methods.
Additionally, we also propose an efficient clustering scheme based on the local patches’ appearance and their geometric relations that can provide pixel-accurate, top-down segmentations from IHRF back-projections.
This refined segmentation can be used to improve the quality of online object tracking because it avoids the drifting problem.
Thus, an online tracking framework based on IHRF, which is trained and updated in each frame to distinguish and segment the object from the background, is established.
Finally, the experimental results on both object segmentation and long-term object tracking show that this method yields accurate and robust tracking performance in a variety of complex scenarios, especially in cases of severe occlusions and nonrigid deformations.
American Psychological Association (APA)
Lin, Yimin& Lu, Naiguang& Lou, Xiaoping& Zou, Fang& Yao, Yanbin& Du, Zhaocai. 2014. Invariant Hough Random Ferns for Object Detection and Tracking. Mathematical Problems in Engineering،Vol. 2014, no. 2014, pp.1-20.
https://search.emarefa.net/detail/BIM-477597
Modern Language Association (MLA)
Lin, Yimin…[et al.]. Invariant Hough Random Ferns for Object Detection and Tracking. Mathematical Problems in Engineering No. 2014 (2014), pp.1-20.
https://search.emarefa.net/detail/BIM-477597
American Medical Association (AMA)
Lin, Yimin& Lu, Naiguang& Lou, Xiaoping& Zou, Fang& Yao, Yanbin& Du, Zhaocai. Invariant Hough Random Ferns for Object Detection and Tracking. Mathematical Problems in Engineering. 2014. Vol. 2014, no. 2014, pp.1-20.
https://search.emarefa.net/detail/BIM-477597
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-477597