CaltechAUTHORS
  A Caltech Library Service

Online, Real-Time Tracking Using a Category-to-Individual Detector

Hall, David and Perona, Pietro (2014) Online, Real-Time Tracking Using a Category-to-Individual Detector. In: Computer Vision (ECCV) 2014. Lecture Notes in Computer Science. No.8689. Springer , Cham, Switzerland, pp. 361-376. ISBN 978-3-319-10589-5. https://resolver.caltech.edu/CaltechAUTHORS:20150112-112834961

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20150112-112834961

Abstract

A method for online, real-time tracking of objects is presented. Tracking is treated as a repeated detection problem where potential target objects are identified with a pre-trained category detector and object identity across frames is established by individual-specific detectors. The individual detectors are (re-) trained online from a single positive example whenever there is a coincident category detection. This ensures that the tracker is robust to drift. Real-time operation is possible since an individual-object detector is obtained through elementary manipulations of the thresholds of the category detector and therefore only minimal additional computations are required. Our tracking algorithm is benchmarked against nine state-of-the-art trackers on two large, publicly available and challenging video datasets. We find that our algorithm is 10% more accurate and nearly as fast as the fastest of the competing algorithms, and it is as accurate but 20 times faster than the most accurate of the competing algorithms.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
http://dx.doi.org/10.1007/978-3-319-10590-1_24DOIArticle
http://link.springer.com/chapter/10.1007%2F978-3-319-10590-1_24PublisherArticle
ORCID:
AuthorORCID
Perona, Pietro0000-0002-7583-5809
Additional Information:© 2014 13th European Conference on Computer Vision (ECCV), Zurich, Switzerland, Sep 06-12, 2014. This work is funded by the ARO-JPL NASA Stennis NAS7.03001 grant and the MURI ONR N00014-10-l-0933 grant.
Funders:
Funding AgencyGrant Number
NASANAS7.03001
Office of Naval Research (ONR)N00014-10-l-0933
Army Research Office (ARO)UNSPECIFIED
Series Name:Lecture Notes in Computer Science
Issue or Number:8689
Record Number:CaltechAUTHORS:20150112-112834961
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20150112-112834961
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:53573
Collection:CaltechAUTHORS
Deposited By: Ruth Sustaita
Deposited On:13 Jan 2015 02:27
Last Modified:03 Oct 2019 07:50

Repository Staff Only: item control page