Repository hosted by TU Delft Library

Home · Contact · About · Disclaimer ·
 

Real-time resource allocation for tracking systems

Publication files not online:

Author: Satsangi, Y. · Whiteson, S. · Oliehoek, F.A. · Bouma, H.
Type:article
Date:2017
Publisher: AUAI Press Corvallis
Source:Elidan, G.Kersting, K., 33rd Conference on Uncertainty in Artificial Intelligence, UAI 2017. 11 August 2017 through 15 August 2017
Identifier: 781880
Keywords: Artificial intelligence · Error analysis · Pixels · Tracking (position) · Automated tracking · Candidate pixels · Computational costs · Computer vision applications · Particle filter · Person detector · Tracking performance · Ultrahigh resolution · Real time systems · 2015 Observation, Weapon & Protection Systems · II - Intelligent Imaging · TS - Technical Sciences

Abstract

Automated tracking is key to many computer vision applications. However, many tracking systems struggle to perform in real-time due to the high computational cost of detecting people, especially in ultra high resolution images. We propose a new algorithm called PartiMax that greatly reduces this cost by applying the person detector only to the relevant parts of the image. PartiMax exploits information in the particle filter to select k of the n candidate pixel boxes in the image. We prove that Parti- Max is guaranteed to make a near-optimal selection with error bounds that are independent of the problem size. Furthermore, empirical results on a real-life dataset show that our system runs in real-time by processing only 10% of the pixel boxes in the image while still retaining 80% of the original tracking performance achieved when processing all pixel boxes. Amazon Web Services; Artificial Intelligence Journal; Disney Research; et al.; Google Inc.; Microsoft Research