A new crowd-head detection benchmark for railway platforms and event entrances, with 109,913 annotated heads across 1,886 images, shows YOLOv9 and RT-DETR reach about 91% mAP while models trained on existing datasets fall below 57%.
The impact of yolo algorithms within fall detection application: A review
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
RPEE-HEADS: A Novel Benchmark for Pedestrian Head Detection in Crowd Videos
A new crowd-head detection benchmark for railway platforms and event entrances, with 109,913 annotated heads across 1,886 images, shows YOLOv9 and RT-DETR reach about 91% mAP while models trained on existing datasets fall below 57%.