A 360-degree LiDAR detection system using equivariant features achieves stable performance on vehicles in unstructured urban traffic but struggles with smaller road users.
arXiv preprint arXiv:2410.07701 (2024)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
YOLOv11n reports 46.6% mAP@50, 3.2% higher precision, and 22% fewer FLOPs than YOLOv8n on a custom IDD+BDD100K dataset for adverse-weather mixed traffic detection.
citing papers explorer
-
Eyes All Around: Design and Analysis of 360-Degree LiDAR Perception Using Equivariant Feature Learning in Unstructured Traffic
A 360-degree LiDAR detection system using equivariant features achieves stable performance on vehicles in unstructured urban traffic but struggles with smaller road users.
-
Performance Analysis of YOLOv11 and YOLOv8 for Mixed Traffic Object Detection under Adverse Weather Conditions in Developing Countries
YOLOv11n reports 46.6% mAP@50, 3.2% higher precision, and 22% fewer FLOPs than YOLOv8n on a custom IDD+BDD100K dataset for adverse-weather mixed traffic detection.