SKKUAutoLab/TSBOW
[AAAI 2026] TSBOW – Traffic Surveillance Benchmark for Occluded Vehicles Under Various Weather Conditions
This project offers a comprehensive dataset of real-world traffic surveillance videos collected from urban areas. It provides over 32 hours of video with detailed annotations for vehicles, micromobility devices, and pedestrians, covering various weather conditions and occlusion levels. Transportation planners, urban developers, and researchers in intelligent transportation systems would use this to build and test advanced traffic monitoring and accident prevention systems.
Use this if you need a diverse dataset of traffic camera footage, especially under challenging conditions like adverse weather or obscured views, to develop robust object detection models for urban traffic.
Not ideal if your focus is solely on clear, unobstructed traffic scenarios or if your application does not involve vision-based vehicle detection.
Stars
11
Forks
2
Language
HTML
License
Apache-2.0
Category
Last pushed
Mar 17, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/SKKUAutoLab/TSBOW"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ShisatoYano/AutonomousVehicleControlBeginnersGuide
Python sample codes and documents about Autonomous vehicle control algorithm. This project can...
yyyanbj/arxiv-daily
🎓 Automatically Update Some Fields Papers Daily using Github Actions (Update Every 12th hours)
JdeRobot/BehaviorMetrics
Autonomous driving neural network comparison tool
gmberton/VPR-datasets-downloader
Automatic download VPR datasets in a standard format
open-forest-observatory/geograypher
Enabling Geospatial Predictions from Individual Drone Images