Tunnel Rear-end Collision Detection Dataset
#target detection #image recognition #traffic safety #accident detection #intelligent driving
- Records
- 5000 records
- Size
- 1.5G
- Format
- JPG/PNG/JSON
- Provider
MOBIUSI INC- Updated
- v1.02026-11-05
AI Analysis & Value Prop
The current transportation industry faces increasingly serious accident issues, especially frequent rear-end collisions in tunnels, posing a significant challenge to traffic safety. Although existing monitoring systems can detect accidents to some extent, they often rely on manual intervention, have delayed responses, and low accuracy. This dataset aims to improve the performance of automated detection systems and reduce the incidence of accidents through high-quality image data. The dataset contains 5000 clearly annotated images of tunnel rear-end collisions, all of which are collected using professional equipment in actual tunnel environments to ensure the reproduction of real scenes. After data collection, multiple rounds of annotation, expert review, and consistency checks ensure high-quality and reliability of the data. The data is stored in JPG format for quick reading and processing.
Overview
Dataset Insights
Preview
Sample Examples
e27a8f0e**.jpg|1920*2560|245.03 KB
98f314d2**.jpg|2560*1920|285.87 KB
cf6fd2a2**.jpg|2560*1920|259.65 KB
80706f91**.jpg|1440*1080|412.36 KB
e9c9a62e**.jpg|3072*4096|744.51 KB
Schema
Technical Specifications
| Field | Type | Description |
|---|---|---|
| file_name | string | File name |
| quality | string | Resolution |
| incident_type | string | The specific type of incident involved in the image, e.g., rear-end collision, crash. |
| number_of_vehicles | int | The number of visible vehicles in the image. |
| lighting_conditions | string | The lighting conditions captured in the image, e.g., daytime, night, tunnel lights. |
| vehicle_types | string | Types of vehicles present in the image, such as cars, trucks, motorcycles, etc. |
| damage_severity | string | The extent of damage to vehicles in the incident, such as minor, moderate, severe. |
| road_condition | string | The condition of the road surface at the accident site, e.g., dry, slippery, waterlogged. |
| tunnel_length | float | The length of the tunnel, measured in meters. |
| tunnel_geometry | string | The geometrical shape of the tunnel, such as straight, curved. |
| visibility_distance | float | The maximum visible distance in the image, measured in meters. |
Trust
Compliance Statement
Authorization Type
Proprietary - Commercial AI Training License (No Redistribution)
Commercial Use
Requires exclusive subscription or authorization contract (monthly or per-invocation charging)
Privacy and Anonymization
No PII, no real company names, simulated scenarios follow industry standards
Compliance System
Compliant with China's Data Security Law / EU GDPR / supports enterprise data access logs
FAQ
Frequently Asked Questions
- What is the Tunnel Rear-End Collision Recognition Dataset?
- The Tunnel Rear-End Collision Recognition Dataset is an image dataset used for detecting and analyzing rear-end collisions in tunnels, aiming to improve traffic safety.
- What modalities of data does the Tunnel Rear-End Collision Recognition Dataset include?
- This dataset includes image data for object detection tasks.
- In which industry is the Tunnel Rear-End Collision Recognition Dataset mainly applied?
- This dataset is mainly applied in the transportation industry to detect and analyze rear-end collisions in tunnels.
- How can the Tunnel Rear-End Collision Recognition Dataset be used to improve traffic safety?
- By using object detection on this dataset, rear-end collisions in tunnels can be effectively identified and analyzed, thereby improving traffic safety.
- What type of machine learning tasks is the Tunnel Rear-End Collision Recognition Dataset suitable for?
- This dataset is suitable for object detection type machine learning tasks.
Can't find the data you need?
Post a request and let data providers reach out to you.
Get this Dataset
High-quality data, ready for your next AI breakthrough.
Cite this Work
@dataset{Mobiusi2025,
title={Tunnel Rear-end Collision Detection Dataset},
author={MOBIUSI INC},
year={2025},
url={https://www.mobiusi.com/datasets/c4c3995f4dfbcb69c72692408cc03802?dataset_scene_id=1},
urldate={2025-09-15},
keywords={tunnel rear-end collision, target detection dataset, traffic safety data, intelligent driving dataset},
version={1.0}
}Using this in research? Please cite us.
placeholder
placeholder
placeholder
placeholder
placeholder
placeholder
placeholder