Contact for Dataset: jwjeon@skku.edu, ngochdm@skku.edu, automation.skku@gmail.com
(UPDATING.... All links would be updated on the conference day).
- [2026.01.16] 🎆 TSBOW dataset is available on HuggingFace.
- [2025.11.16] 🔥 Our code and website are released!
- [2025.11.08] 🎉 TSBOW has been accepted to AAAI 2026!
Global warming has intensified the frequency and severity of extreme weather events, which degrade CCTV signal and video quality while disrupting traffic flow, thereby increasing traffic accident rates. Existing datasets, often limited to light haze, rain, and snow, fail to capture extreme weather conditions. To address this gap, this study introduces the Traffic Surveillance Benchmark for Occluded Vehicles under Various Weather Conditions (TSBOW), a comprehensive dataset designed to enhance occluded vehicle detection across diverse annual weather scenarios. Comprising over 32 hours of real-world traffic data from densely populated urban areas, TSBOW includes more than 48,000 manually annotated and 3.2 million semi-labeled frames; bounding boxes spanning eight traffic participant classes from large vehicles to micromobility devices and pedestrians. We establish an object detection benchmark for TSBOW, highlighting challenges posed by occlusions and adverse weather. With its varied road types, scales, and viewpoints, TSBOW serves as a critical resource for advancing Intelligent Transportation Systems. Our findings underscore the potential of CCTV-based traffic monitoring, paving the way for new research and applications. The TSBOW dataset is publicly available at the following link.
Code -- https://github.com/SKKUAutoLab/TSBOW
Dataset Statistics
Video Distribution
Other Distributions
Class Distribution
Occlusion Ditribution
Traffic Distribution
TSBOW Introduction
- Hardware: CCTV system + color camera.
- Tasks: object detection.
- Position: South Korea.
- Weather: sunny/cloudy, haze, rain, snow.
- Time: day.
Our data formats are described in TSBOW on HuggingFace section.
The comparison between different datasets are described in Datasets section.
| Year | Pub | Paper | Link | Note |
|---|---|---|---|---|
| 2024 | ICDICI | A review on yolov8 and its advancements | paper | YOLOv8 |
| 2024 | arXiV | YOLOv11: An Overview of the Key Architectural Enhancements | paper | YOLOv11 |
| 2024 | CVPR | DETRs Beat YOLOs on Real-time Object Detection | paper | RT-DETR |
| 2025 | arXiV | A Breakdown of the Key Architectural Features | paper | YOLOv12 |
The source codes for baseline models are provided in Baselines folder. Read Instruction for more information.
Results
Model performances after training 100 epochs and validating with imgsz=1280 on manually labeled test set.
Model performances under different weather conditions
The source code for validating Ablation Studies are provided in validation_ablation.sh. Please read the Instruction for the experiment results and more information.
The TSBOW dataset is distributed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
By completing the form below, users acknowledge and agree that the dataset will be used solely for research purposes.
Submission Guidelines
1. TSBOW - Terms and Conditions Form
- Download and fill out the TSBOW - Terms and Conditions form.
- Ensure all User Information fields are completed.
- Provide a description of your intended use of the dataset.
- Check the agreement box and insert your handwritten signature.
- Save as PDF file. Renaming as: {TSBOW}{Application-Date}{Huggingface-Username}.pdf (i.e. TSBOW_20260120_ngochdm.pdf)
2. Requirement Email
- The subject format: [TSBOW Access Requirement] {Your Name} - {Affiliation}
- The email body includes your HuggingFace account information (username and email). We will verify this information against the access requirements on Hugging Face before approval.
- Send email to all our addresses: jwjeon@skku.edu, ngochdm@skku.edu, automation.skku@gmail.com
3. Send Request on HuggingFace
- Press "Agree and send request to access TSBOW" button on HuggingFace. Our team may take 2-3 days to process your request.
Scripts to download TSBOW from HuggingFace are provided in utils folder. Please refer to the download_TSBOW.py and download_TSBOW.sh for more details.
Thanks to the developers and contributors of the following open-source repositories, whose invaluable work has greatly inspire our project:
Datasets:
- UAVDT: A traffic dataset contains drone footages under sunny and rainy conditions.
- UA-DETRAC: A traffic surveillance dataset captures sunny and rainy weather.
- AAU RainSnow: A traffic surveillance dataset provides segmentation annotations for rain and snow weather.
Github Repo:
- X-AnyLabeling: An open-source tool for precise bounding box creation.
- Ultralytics YOLO: Detection models for training and real-time inferencing.
- YOLOv12: A model for object detection.
Our repository is licensed under the Apache 2.0 License. However, if you use other components in your work, please follow their license.
If our research is helpful to you, please cite our paper using the following BibTeX format
@article{Huynh_TSBOW_AAAI_2026,
title = {TSBOW: Traffic Surveillance Benchmark for Occluded Vehicles Under Various Weather Conditions},
author = {Ngoc Doan-Minh Huynh, Duong Nguyen-Ngoc Tran, Long Hoang Pham, Tai Huu-Phuong Tran, Hyung-Joon Jeon, Huy-Hung Nguyen, Duong Khac Vu, Hyung-Min Jeon, Son Hong Phan, Quoc Pham-Nam Ho, Chi Dai Tran, Trinh Le Ba Khanh, Jae Wook Jeon},
journal = {AAAI 2026},
year = {2025}
}