Multi-camera People Tracking With Mixture of Realistic and Synthetic Knowledge

Nguyen, Quang Qui-Vinh; Chau, Tom; Trung, Luu Duc; Chung, Nhat Minh; Ha, Synh Viet-Uyen

doi:10.1109/cvprw59228.2023.00581

Cited by 9 publications

(2 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Kim et al [35] used pose estimation to accurately obtain the position of a person. Nguyen et al [36] performed clustering within each camera before associating across cameras. This model placed second in Track 1 of the AI City Challenge 2023 and was the most accurate model without camera calibration.…”

Section: Multi-camera People Trackingmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Camera People Tracking With Spatio-Temporal and Group Considerations

Sakaguchi,

Amagasaki,

Kiyama

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Multi-camera people tracking (MCPT) has become increasingly relevant in recent years as the demand for accurate people-tracking systems has increased along with the growing number of surveillance cameras. There are challenges that MCPT must overcome, such as changes in a person's appearance due to illumination and changes in viewpoint and posture between cameras. Additionally, occlusion is likely to occur in crowded places like tourist spots, making it even more difficult to perform accurate tracking based on a person's appearance. To address these problems, we propose an MCPT system that uses additional spatio-temporal and group information. First, the system uses spatio-temporal filtering to remove candidates that are considered irrelevant. Then, group-aware matching is used to correct ID matching errors based solely on the features of an individual's appearance. In this paper, we evaluate this system on data collected from surveillance cameras at Kumamoto Castle, a tourist spot designated as a National Important Cultural Property. This dataset contains images of people in a wide age range and with various degrees of crowding. We demonstrate that our system is effective in scenarios with large crowds, and that the additional contextual information is helpful when it is difficult to track based on a person's appearance alone.INDEX TERMS Computer vision, multi-camera people tracking, multi-object tracking, person reidentification, group tracking

show abstract

Section: Multi-camera People Trackingmentioning

confidence: 99%

“…We compared our system to HCMIU-CVIP [36], which was the most accurate model without camera calibration in Track 1 of the AI City Challenge 2023. HCMIU-CVIP uses DeepSort as the default MOT model.…”

Section: ) Overall Performancementioning

confidence: 99%