Detection, Tracking, and Counting Meets Drones in Crowds: A Benchmark
This work addresses the challenge of analyzing dense crowds from drone footage, which is important for surveillance and crowd management, but it is incremental as it builds on existing detection and tracking techniques.
The authors tackled the problem of detecting, tracking, and counting people in drone-captured crowd videos by introducing a new dataset called DroneCrowd with 112 video clips and 33,600 frames, and they proposed the STNNet method, which achieved favorable performance against state-of-the-art methods.
To promote the developments of object detection, tracking and counting algorithms in drone-captured videos, we construct a benchmark with a new drone-captured largescale dataset, named as DroneCrowd, formed by 112 video clips with 33,600 HD frames in various scenarios. Notably, we annotate 20,800 people trajectories with 4.8 million heads and several video-level attributes. Meanwhile, we design the Space-Time Neighbor-Aware Network (STNNet) as a strong baseline to solve object detection, tracking and counting jointly in dense crowds. STNNet is formed by the feature extraction module, followed by the density map estimation heads, and localization and association subnets. To exploit the context information of neighboring objects, we design the neighboring context loss to guide the association subnet training, which enforces consistent relative position of nearby objects in temporal domain. Extensive experiments on our DroneCrowd dataset demonstrate that STNNet performs favorably against the state-of-the-arts.