J 2022

Tracking subjects and detecting relationships in crowded city videos

ELIÁŠ, Petr, Matúš MACKO, Jan SEDMIDUBSKÝ a Pavel ZEZULA

Základní údaje

Originální název

Tracking subjects and detecting relationships in crowded city videos

Autoři

ELIÁŠ, Petr (203 Česká republika, garant, domácí), Matúš MACKO (703 Slovensko, domácí), Jan SEDMIDUBSKÝ (203 Česká republika, domácí) a Pavel ZEZULA (203 Česká republika, domácí)

Vydání

Multimedia Tools and Applications, Springer, 2022, 1380-7501

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

10200 1.2 Computer and information sciences

Stát vydavatele

Spojené státy

Utajení

není předmětem státního či obchodního tajemství

Odkazy

Impakt faktor

Impact factor: 3.600

Kód RIV

RIV/00216224:14330/22:00129021

Organizační jednotka

Fakulta informatiky

DOI

UT WoS

000743891900007

Klíčová slova anglicky

Multi-subject tracking;Relationship detection;2D skeleton sequences;Video analysis;Smart cities

Štítky

Příznaky

Mezinárodní význam, Recenzováno
Změněno: 10. 3. 2023 12:58, doc. RNDr. Jan Sedmidubský, Ph.D.

Anotace

V originále

Multi-subject tracking in crowded videos is an established yet challenging research direction in computer vision and information processing. High applicability of multi-subject tracking is demonstrated in smart cities (e.g., public safety, crowd management, urban planning), autonomous driving vehicles, robotic vision, or psychology (e.g., social interaction and crowd behavior understanding). In this work, we propose a real-time approach that reveals tracks of subjects in ordinary videos, captured in highly populated pedestrian areas, such as squares, malls, and stations. The tracks are discovered based on the proximity of detected bounding boxes of subjects in consecutive video frames. The reduction of track fragmentation and identity switching is achieved by the re-identification phase that uses caching of unassociated detections and mutual projection of interrupted tracks. As the proposed approach does not require time-consuming extraction of appearance-based features, the superior tracking speed is achieved. In addition, we demonstrate tracker usability and applicability by extracting valuable information about body-joint positions from discovered tracks, which opens promising possibilities for detecting human relationships and interactions. We demonstrate accurate detection of couples based on their holding hand activity and families based on children's body proportions. The discovery of these entitative groups is especially challenging in crowded city scenes where many subjects appear in each frame.

Návaznosti

GA19-02033S, projekt VaV
Název: Vyhledávání, analytika a anotace datových toků lidských pohybů
Investor: Grantová agentura ČR, Searching, Mining, and Annotating Human Motion Streams