10 datasets found

Anomaly detection in crowded scenes

The dataset used for the MOT20 challenge, which consists of 8 different sequences depicting very crowded challenging scenes.

The ETH and UCY datasets consist of various motions of 1,536 pedestrians across five unique scenes: ETH, Hotel, Univ, Zara1 and Zara2. They are recorded in crowded scenes.

Anomaly detection and localization in crowded scenes.

A benchmark dataset for anomaly detection in crowded scenes

ProgS-RCNN: Progressive End-to-End Object Detection in Crowded Scenes

CrowdHuman is a challenging benchmark to evaluate the ability of crowded scene detection of detectors, which contains about 15k training images and 4k images for evaluation.

The Ped2 dataset comprises of 16 training and 12 test videos and all videos have the same scene in the background.

A benchmark for anomaly detection in crowded scenes. It contains 19600 frames captured using two different cameras.

The dataset used for pedestrian detection, occlusion and body part relevance assessment.