English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
 Local TagsRelease HistoryDetailsSummary
  Tracking using Multilevel Quantizations

Hong, Z., Wang, C., Mei, X., Prokhorov, D., & Tao, D. (2014). Tracking using Multilevel Quantizations. In D. Fleet, T. Pajdla, B. Schiele, & T. Tuytelaars (Eds.), Computer Vision - ECCV 2014. Proceedings, Part VI (pp. 155-171). Cham et al.: Springer International Publishing.

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/11858/00-001M-0000-0024-C6F8-2 Version Permalink: https://hdl.handle.net/11858/00-001M-0000-0024-C711-F
Genre: Conference Paper

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Hong, Zhibin1, Author
Wang, Chaohui2, Author           
Mei, Xue, Author
Prokhorov, Danil, Author
Tao, Dacheng, Author
Affiliations:
1External Organizations, ou_persistent22              
2Dept. Perceiving Systems, Max Planck Institute for Intelligent Systems, Max Planck Society, ou_1497642              

Content

show
hide
Free keywords: Abt. Black
 Abstract: Most object tracking methods only exploit a single quantization of an image space: pixels, superpixels, or bounding boxes, each of which has advantages and disadvantages. It is highly unlikely that a common optimal quantization level, suitable for tracking all objects in all environments, exists. We therefore propose a hierarchical appearance representation model for tracking, based on a graphical model that exploits shared information across multiple quantization levels. The tracker aims to find the most possible position of the target by jointly classifying the pixels and superpixels and obtaining the best configuration across all levels. The motion of the bounding box is taken into consideration, while Online Random Forests are used to provide pixel- and superpixel-level quantizations and progressively updated on-the-fly. By appropriately considering the multilevel quantizations, our tracker exhibits not only excellent performance in non-rigid object deformation handling, but also its robustness to occlusions. A quantitative evaluation is conducted on two benchmark datasets: a non-rigid object tracking dataset (11 sequences) and the CVPR2013 tracking benchmark (50 sequences). Experimental results show that our tracker overcomes various tracking challenges and is superior to a number of other popular tracking methods.

Details

show
hide
Language(s): eng - English
 Dates: 2014-09
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1007/978-3-319-10599-4_11
BibTex Citekey: HongWMPT:ECCV2014
 Degree: -

Event

show
hide
Title: ECCV 2014 - 13th European Conference on Computer Vision
Place of Event: Zürich
Start-/End Date: 2014-09-06 - 2014-09-12

Legal Case

show

Project information

show

Source 1

show
hide
Title: Computer Vision - ECCV 2014. Proceedings, Part VI
Source Genre: Proceedings
 Creator(s):
Fleet, D., Editor
Pajdla, T., Editor
Schiele, B., Editor
Tuytelaars, T., Editor
Affiliations:
-
Publ. Info: Cham et al. : Springer International Publishing
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 155 - 171 Identifier: ISBN: 978-3-319-10598-7
ISBN: 978-3-319-10599-4

Source 2

show
hide
Title: Lecture Notes in Computer Science
Source Genre: Series
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: 8694 Sequence Number: - Start / End Page: - Identifier: -