A YOLOv5-based pipeline with day/night specialized models, upsampled hard cases, multi-stage transfer learning, pseudo data, and selective ensembling reports 13.7% mAP improvement on a fisheye vehicle detection benchmark.
Vehicle detection and tracking techniques: A concise review
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
An Optimized YOLOv5 Based Approach For Real-time Vehicle Detection At Road Intersections Using Fisheye Cameras
A YOLOv5-based pipeline with day/night specialized models, upsampled hard cases, multi-stage transfer learning, pseudo data, and selective ensembling reports 13.7% mAP improvement on a fisheye vehicle detection benchmark.