Tracking by identification using computer vision and radio

Mandeljc, Rok (avtor), Kovačič, Stanislav (avtor), Kristan, Matej (avtor), Perš, Janez (avtor)

We present a novel system for detection, localization and tracking of multiple people, which fuses a multi-view computer vision approach with a radio-based localization system. The proposed fusion combines the best of both worlds, excellent computer-vision-based localization, and strong identity information provided by the radio system, and is therefore able to perform tracking by identification, which makes it impervious to propagated identity switches. We present comprehensive methodology for evaluation of systems that perform person localization in world coordinate system and use it to evaluate the proposed system as well as its components. Experimental results on a challenging indoor dataset, which involves multiple people walking around a realistically cluttered room, confirm that proposed fusion of both systems significantly outperforms its individual components. Compared to the radio-based system, it achieves better localization results, while at the same time it successfully prevents propagation of identity switches that occur in pure computer-vision-based tracking.

• Jezik: Angleški jezik
• Ključne besede: person localization, identification, tracking, radio, computer vision, multi-camera, sensor fusion, tracking-by-identification
• Vrsta gradiva: Članek v reviji
• Tipologija: 1.01 - Izvirni znanstveni članek
• Organizacija: FE - Fakulteta za elektrotehniko
• Status publikacije: Objavljeno
• Različica publikacije: Objavljena publikacija
• Leto izida: 2013
• Št. strani: Str. 241-273
• Številčenje: Vol. 13, iss. 1
• PID: 20.500.12556/RUL-129507
• UDK: 004.932
• ISSN pri članku: 1424-8220
• DOI: 10.3390/s130100241
• COBISS.SI-ID: 9592404
• Datum objave v RUL: 02.09.2021

Gradivo je del revije

• Naslov: Sensors
• Skrajšan naslov: Sensors
• Založnik: MDPI
• ISSN: 1424-8220
• COBISS.SI-ID: 10176278

Licence

• Licenca: CC BY 3.0, Creative Commons Priznanje avtorstva 3.0 Nedoločena
• Povezava: https://creativecommons.org/licenses/by/3.0/deed.sl
• Opis: Dovoljuje kopiranje in razširjanje vsebin v kakršnemkoli mediju in obliki. Dovoljuje remixanje, urejanje, predelava in vključevanje vsebine v lastna dela v vse namene, tudi komercialne. Primerno morate navesti avtorja, povezavo do licence in označiti spremembe, če so kakšne nastale. To lahko storite na kakršenkoli razumen način, vendar ne na način, ki bi namigoval na to, da dajalec licence podpira vas ali vašo uporabo dela. Ne smete uporabiti pravnih določil ali tehničnih ukrepov, ki bi pravno omejili ali onemogočilo druge, da bi storili karkoli, kar licenca dovoli.
• Začetek licenciranja: 01.01.2013

Sekundarni jezik

• Jezik: Slovenski jezik
• Ključne besede: lokalizacija oseb, identifikacija, sledenje, radio, računalniški vid, več kamer, zlivanje senzorjev, sledenje prek identifikacije