English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
  Learning People Detectors for Tracking in Crowded Scenes

Tang, S., Andriluka, M., Milan, A., Schindler, K., Roth, S., & Schiele, B. (2013). Learning People Detectors for Tracking in Crowded Scenes. In ICCV 2013 (pp. 1049-1056). Los Alamitos, CA: IEEE Computer Society. doi:10.1109/ICCV.2013.134.

Item is

Files

show Files
hide Files
:
tang_iccv_13.pdf (Any fulltext), 3MB
 
File Permalink:
-
Name:
tang_iccv_13.pdf
Description:
-
OA-Status:
Visibility:
Private
MIME-Type / Checksum:
application/pdf
Technical Metadata:
Copyright Date:
-
Copyright Info:
-
License:
-

Locators

show

Creators

show
hide
 Creators:
Tang, Siyu1, Author           
Andriluka, Mykhaylo1, Author           
Milan, Anton2, Author
Schindler, Konrad2, Author
Roth, Stefan2, Author
Schiele, Bernt1, Author           
Affiliations:
1Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society, ou_1116547              
2External Organizations, ou_persistent22              

Content

show
hide
Free keywords: -
 Abstract: People tracking in crowded real-world scenes is challenging due to frequent and long-term occlusions. Recent tracking methods obtain the image evidence from object (people) detectors, but typically use off-the-shelf detectors and treat them as black box components. In this paper we argue that for best performance one should explicitly train people detectors on failure cases of the overall tracker instead. To that end, we first propose a novel joint people detector that combines a state-of-the-art single person detector with a detector for pairs of people, which explicitly exploits common patterns of person-person occlusions across multiple viewpoints that are a common failure case for tracking in crowded scenes. To explicitly address remaining failure cases of the tracker we explore two methods. First, we analyze typical failure cases of trackers and train a detector explicitly on those failure cases. And second, we train the detector with the people tracker in the loop, focusing on the most common tracker failures. We show that our joint multi-person detector significantly improves both detection accuracy as well as tracker performance, improving the state-of-the-art on standard benchmarks.

Details

show
hide
Language(s): eng - English
 Dates: 20132013-12
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: BibTex Citekey: 766
DOI: 10.1109/ICCV.2013.134
 Degree: -

Event

show
hide
Title: IEEE International Conference on Computer Vision
Place of Event: Sydney, Australia
Start-/End Date: 2013-12-01 - 2013-12-08

Legal Case

show

Project information

show

Source 1

show
hide
Title: ICCV 2013
  Abbreviation : ICCV 2013
  Subtitle : 2013 IEEE International Conference on Computer Vision ; 1 - 8 December 2013 Sydney, NSW, Australia ; Proceedings
Source Genre: Proceedings
 Creator(s):
Affiliations:
Publ. Info: Los Alamitos, CA : IEEE Computer Society
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 1049 - 1056 Identifier: -