TSBOW

TSBOW Logo

T S B O W

Traffic Surveillance Benchmark for Occluded Vehicles under Various Weather Conditions

TSBOW Website Paper Paper arXiv Supplementary Huggingface Hugging Face Dataset GitHub GitHub

ATTRIBUTES

🌦️ WEATHER 🌦️ 🚦 SCENARIO 🚦 🛣️ ROAD TYPE 🛣️ 🔎 SCALE 🔎 🚗 TRAFFIC 🚗

Weather

Videos for the TSBOW dataset were recorded in Suwon under diverse weather condition throughout the year: normal, haze, rain, and snow.

  • Normal: sunny and cloudy
  • Haze: haze or foggy
  • Rain: raindrops or active rainfall are evident
  • Snow: visible snowflkes or snowfall

Normal
Haze
Rain
Snow

Scenario

The scenarios are categorized into four distinct types: road, intersection, special cases, and disaster.

  • Road: straight roads or those where traffi flow remains unaffected by traffi lights
  • Intersection: includes three subtypes—T, Y, or crossroad—and extends to scenes where traffi lights or pedestrian crossings inflence traffi flow
  • Special cases: includes videos featuring shared lanes, overpasses, or mid-road construction
  • Disaster: pertains to scenarios where hostile weather severely degrades video quality

Road
Intersection
Special Cases
Disaster

Road Type

The TSBOW dataset classifies data collection zones by the number of straight lanes per direction, excluding turning lanes, into three road types: urban, standard, and boulevard.

  • Urban: two lanes
  • Standard: four lanes
  • Boulevard: over six lanes

Urban
Standard
Boulevard

Scale

CCTV cameras along routes and intersections vary in angle and height, producing bounding box sizes categorized into three scales: fine, medium, and coarse.

  • Fine: near road surface, detailed object visualization
  • Medium: elevated cameras, discernible license plates but reduced clarity
  • Coarse: distant cameras, high vehicle count but partial visibility due to distance and occlusion

Fine
Medium
Coarse

Traffic

Traffic flow is categorized into light, moderate, and heavy, based on the maximum number of bounding boxes per frame in video.

  • Light: less than 25 bboxes/frame
  • Moderate: 25 to less than 50 bboxes/frame
  • Heavy: over 50 bboxes/frame

Light
Moderate
Heavy

Cite Our Work

If our research is helpful to you, please cite our paper
using the following BibTeX format

BibTeX Icon 
@article{Huynh2026TSBOW, 
    title={TSBOW: Traffic Surveillance Benchmark for Occluded Vehicles Under Various Weather Conditions}, 
    author={Huynh, Ngoc Doan-Minh and Tran, Duong Nguyen-Ngoc and Pham, Long Hoang and Tran, Tai Huu-Phuong and Jeon, Hyung-Joon and Nguyen, Huy-Hung and Khac Vu, Duong and Jeon, Hyung-Min and Phan, Son Hong and Pham-Nam Ho, Quoc and Tran, Chi Dai and Khanh, Trinh Le Ba and Jeon, Jae Wook}, 
    journal={Proceedings of the AAAI Conference on Artificial Intelligence}, 
    volume={40}, 
    number={7}, 
    url={https://ojs.aaai.org/index.php/AAAI/article/view/37439}, 
    DOI={10.1609/aaai.v40i7.37439}, 
    year={2026}, 
    month={Mar.}, 
    pages={5239-5247} 
}