MTMMC: A Large-Scale Real-World Multi-Modal Camera Tracking Benchmark

arXiv:2403.20225v1 Announce Type: new
Abstract: Multi-target multi-camera tracking is a crucial task that involves identifying and tracking individuals over time using video streams from multiple cameras. This task has practical applications in various fields, such as visual surveillance, crowd behavior analysis, and anomaly detection. However, due to the difficulty and cost of collecting and labeling data, existing datasets for this task are either synthetically generated or artificially constructed within a controlled camera network setting, which limits their ability to model …

abstract analysis anomaly anomaly detection applications arxiv behavior behavior analysis benchmark cameras cost cs.cv detection fields however modal multi-modal multiple practical scale surveillance tracking type video video streams visual world