ROD-Dataset: A Pedestrian-Perspective Benchmark of Urban Obstacle Classes for YOLO-Based Detection
cs.CV, cs.CY
Submitted: 2026-10-31
Updated: 2026-10-31
Code: https://github.com/Real-time-Obstacle-Detector/ROD-Dataset.3https:
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- SynRailObs: A Synthetic Dataset for Obstacle Detection in Railway Scenarios
- PEDESTRIAN: An Egocentric Vision Dataset for Obstacle Detection on Pavements
- SAM 3: Segment Anything with Concepts
- YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information
- YOLOv10: Real-Time End-to-End Object Detection
- YOLOv11: An Overview of the Key Architectural Enhancements
- YOLOv12: Attention-Centric Real-Time Object Detectors
- YOLO26: Key Architectural Enhancements and Performance Benchmarking for Real-Time Object Detection
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs