Tracking subjects and detecting relationships in crowded city videos

• Published in: Multimedia tools and applications Vol. 83; no. 5; pp. 15339 - 15361
• Main Authors: Elias, Petr, Macko, Matus, Sedmidubsky, Jan, Zezula, Pavel
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.02.2024; Springer Nature B.V
• Subjects: 1158T: Role of Computer Vision in Smart Cities: Applications and Research Challenges; Boxes; Cities; Computer Communication Networks; Computer Science; Computer vision; Couples; Crowd monitoring; Data processing; Data Structures and Information Theory; Deep learning; Information processing; Machine vision; Multimedia; Multimedia Information Systems; Public safety; Safety management; Smart cities; Social factors; Social interaction; Special Purpose and Application-Based Systems; Tracking; Urban planning; Usability; Video; Relationship detection; Smart cities; 2D skeleton sequences; Multi-subject tracking; Video analysis

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 vehicl...