TAD: A Large-Scale Benchmark for Traffic Accidents Detection From Video Surveillance
Automatic traffic accident detection has attracted the attention of the machine vision community for the rapid development of autonomous intelligent transportation systems (ITS). However, previous studies in this domain have been constrained by small-scale datasets with limited scope, impeding their...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10815954/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536186403782656 |
|---|---|
| author | Yajun Xu Huan Hu Chuwen Huang Yibing Nan Yuyao Liu Kai Wang Zhaoxiang Liu Shiguo Lian |
| author_facet | Yajun Xu Huan Hu Chuwen Huang Yibing Nan Yuyao Liu Kai Wang Zhaoxiang Liu Shiguo Lian |
| author_sort | Yajun Xu |
| collection | DOAJ |
| description | Automatic traffic accident detection has attracted the attention of the machine vision community for the rapid development of autonomous intelligent transportation systems (ITS). However, previous studies in this domain have been constrained by small-scale datasets with limited scope, impeding their effectiveness and applicability. Specifically, highway traffic accidents, often resulting in severe consequences due to higher speeds, require a more comprehensive approach to detection. The use of video surveillance provides a unique perspective, capturing the entire accident sequence. Unfortunately, existing traffic accident datasets are either not sourced from surveillance cameras, not publicly available, or not tailored for highway scenarios. An open-sourced traffic accident dataset with various scenes from surveillance cameras is in great need and of practical importance. To fulfill the above urgent need, we endeavor to collect abundant video data of real traffic accidents and propose a large-scale traffic accidents dataset, named TAD. Various experiments on image classification, video classification, and object detection tasks, using public mainstream vision algorithms or frameworks are conducted in this work to demonstrate the performance of different methods. The proposed dataset together with the experimental results are presented as a new benchmark to improve computer vision research, especially in ITS. The dataset is publicly available at <uri>https://github.com/UnicomAI/UnicomBenchmark/tree/main/TADBench</uri>. |
| format | Article |
| id | doaj-art-8189d00addb5480f9fbbb92f7c646d04 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-8189d00addb5480f9fbbb92f7c646d042025-01-15T00:01:52ZengIEEEIEEE Access2169-35362025-01-01132018203310.1109/ACCESS.2024.352238410815954TAD: A Large-Scale Benchmark for Traffic Accidents Detection From Video SurveillanceYajun Xu0Huan Hu1Chuwen Huang2Yibing Nan3Yuyao Liu4https://orcid.org/0009-0006-3695-3841Kai Wang5https://orcid.org/0000-0002-1171-0281Zhaoxiang Liu6https://orcid.org/0000-0002-1267-0277Shiguo Lian7AI Innovation Center, China Unicom, Beijing, ChinaAI Innovation Center, China Unicom, Beijing, ChinaAI Innovation Center, China Unicom, Beijing, ChinaAI Innovation Center, China Unicom, Beijing, ChinaSchool of Information Science and Technology, Tsinghua University, Beijing, ChinaAI Innovation Center, China Unicom, Beijing, ChinaAI Innovation Center, China Unicom, Beijing, ChinaAI Innovation Center, China Unicom, Beijing, ChinaAutomatic traffic accident detection has attracted the attention of the machine vision community for the rapid development of autonomous intelligent transportation systems (ITS). However, previous studies in this domain have been constrained by small-scale datasets with limited scope, impeding their effectiveness and applicability. Specifically, highway traffic accidents, often resulting in severe consequences due to higher speeds, require a more comprehensive approach to detection. The use of video surveillance provides a unique perspective, capturing the entire accident sequence. Unfortunately, existing traffic accident datasets are either not sourced from surveillance cameras, not publicly available, or not tailored for highway scenarios. An open-sourced traffic accident dataset with various scenes from surveillance cameras is in great need and of practical importance. To fulfill the above urgent need, we endeavor to collect abundant video data of real traffic accidents and propose a large-scale traffic accidents dataset, named TAD. Various experiments on image classification, video classification, and object detection tasks, using public mainstream vision algorithms or frameworks are conducted in this work to demonstrate the performance of different methods. The proposed dataset together with the experimental results are presented as a new benchmark to improve computer vision research, especially in ITS. The dataset is publicly available at <uri>https://github.com/UnicomAI/UnicomBenchmark/tree/main/TADBench</uri>.https://ieeexplore.ieee.org/document/10815954/Traffic accidentslarge-scalesurveillance camerasopen-sourced |
| spellingShingle | Yajun Xu Huan Hu Chuwen Huang Yibing Nan Yuyao Liu Kai Wang Zhaoxiang Liu Shiguo Lian TAD: A Large-Scale Benchmark for Traffic Accidents Detection From Video Surveillance IEEE Access Traffic accidents large-scale surveillance cameras open-sourced |
| title | TAD: A Large-Scale Benchmark for Traffic Accidents Detection From Video Surveillance |
| title_full | TAD: A Large-Scale Benchmark for Traffic Accidents Detection From Video Surveillance |
| title_fullStr | TAD: A Large-Scale Benchmark for Traffic Accidents Detection From Video Surveillance |
| title_full_unstemmed | TAD: A Large-Scale Benchmark for Traffic Accidents Detection From Video Surveillance |
| title_short | TAD: A Large-Scale Benchmark for Traffic Accidents Detection From Video Surveillance |
| title_sort | tad a large scale benchmark for traffic accidents detection from video surveillance |
| topic | Traffic accidents large-scale surveillance cameras open-sourced |
| url | https://ieeexplore.ieee.org/document/10815954/ |
| work_keys_str_mv | AT yajunxu tadalargescalebenchmarkfortrafficaccidentsdetectionfromvideosurveillance AT huanhu tadalargescalebenchmarkfortrafficaccidentsdetectionfromvideosurveillance AT chuwenhuang tadalargescalebenchmarkfortrafficaccidentsdetectionfromvideosurveillance AT yibingnan tadalargescalebenchmarkfortrafficaccidentsdetectionfromvideosurveillance AT yuyaoliu tadalargescalebenchmarkfortrafficaccidentsdetectionfromvideosurveillance AT kaiwang tadalargescalebenchmarkfortrafficaccidentsdetectionfromvideosurveillance AT zhaoxiangliu tadalargescalebenchmarkfortrafficaccidentsdetectionfromvideosurveillance AT shiguolian tadalargescalebenchmarkfortrafficaccidentsdetectionfromvideosurveillance |