Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published September 6, 2014 | Accepted Version
Conference Paper Open

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

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.

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.

Attached Files

Accepted Version - ECCV2014_HALL.pdf

Files

ECCV2014_HALL.pdf
Files (7.3 MB)
Name Size Download all
md5:4b257f5120ec6bd1f10c4d7c3c69b3fe
7.3 MB Preview Download

Additional details

Created:
August 20, 2023
Modified:
October 20, 2023