TransTrack: Tracking Multiple Targets by Sensing Their Zone Transitions
| Autor: | Erin Griffiths, Avinash Kalyanaraman, Kamin Whitehouse |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Radar tracker
010504 meteorology & atmospheric sciences Computer science business.industry 020206 networking & telecommunications Tracking system 02 engineering and technology Tracking (particle physics) 01 natural sciences 0202 electrical engineering electronic engineering information engineering Key (cryptography) Signal processing algorithms Computer vision Artificial intelligence business 0105 earth and related environmental sciences |
| Zdroj: | DCOSS |
| DOI: | 10.1109/dcoss.2016.27 |
| Popis: | In this paper, we consider a variant of the multi-targettracking problem in which the tracking region is dividedinto zones and targets can only be monitored as they transitionbetween these zones. We call this the transition tracking problem. The key challenge in Transition Tracking is to estimate the numberof targets in the tracking region without being able to senseall targets simultaneously. In this paper, we propose an approachto the Transition Tracking problem called TransTrack. Unlikemost other tracking algorithms that maximize the likelihood ofthe sensor data, TransTrack applies penalty functions to find theminimum number of targets that can explain the sensor data. These penalties allow tracks with larger numbers of targets only ifthey have sufficiently fewer errors than other, alternative tracks. To evaluate this approach, we apply TransTrack to a datasetcontaining 3275 transitions between rooms in a home. We observean average room tracking accuracy of up to 94.5%. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|