A Caltech Library Service

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

Hall, David C. and Perona, Pietro (2014) Online, Real-Time Tracking Using a Category-to-Individual Detector. In: ECCV, September 6-12, 2014, Zurich, Switzerland. (Submitted)

PDF - Accepted Version
See Usage Policy.


Use this Persistent URL to link to this item:


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:Conference or Workshop Item (Paper)
Related URLs:
URLURL TypeDescription Website Website
Perona, Pietro0000-0002-7583-5809
Additional Information:Paper 1211. This work is funded by the ARO-JPL NASA Stennis NAS7.03001 grant and the MURI ONR N00014-10-1-0933 grant.
Funding AgencyGrant Number
Office of Naval Research (ONR)N00014-10-1-0933
Record Number:CaltechAUTHORS:20140729-142412448
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:47563
Deposited By: David Hall
Deposited On:29 Jul 2014 22:23
Last Modified:03 Oct 2019 06:55

Repository Staff Only: item control page