Research on Expressway Traffic Event Detection at Night Based on Mask-SpyNet
Expressway traffic event detection at night is essential for improving rescue efficiency and avoiding secondary accidents. Most expressways in China have built a complete Expressway video monitoring system. However, at night, the expressway traffic event detection still adopts manual detection, whic...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9784922/ |
| _version_ | 1798038362365362176 |
|---|---|
| author | Xianglun Mo Chuanpeng Sun Chenyu Zhang Jinpeng Tian Zhushuai Shao |
| author_facet | Xianglun Mo Chuanpeng Sun Chenyu Zhang Jinpeng Tian Zhushuai Shao |
| author_sort | Xianglun Mo |
| collection | DOAJ |
| description | Expressway traffic event detection at night is essential for improving rescue efficiency and avoiding secondary accidents. Most expressways in China have built a complete Expressway video monitoring system. However, at night, the expressway traffic event detection still adopts manual detection, which is inefficient. In this dissertation, the strategy of expressway traffic event detection at night has been analysed first. On this basis, by combining the Mask method and SpyNet deep learning, this study develops a night highway vehicle detection deep learning network with a dense optical flow formed by night vehicle light flow as the detection object. Finally, the Deepsort algorithm is used to track and measure the velocity of the detected target. The measured data are used to compare the background difference method, classical optical flow method, YOLO-v3 and proposed method in this paper. The results show that the proposed method has the advantages of high detection accuracy and fast detection speed. |
| first_indexed | 2024-04-11T21:39:10Z |
| format | Article |
| id | doaj.art-3062236be091448ea017c277c8220785 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-11T21:39:10Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-3062236be091448ea017c277c82207852022-12-22T04:01:39ZengIEEEIEEE Access2169-35362022-01-0110690536906210.1109/ACCESS.2022.31787149784922Research on Expressway Traffic Event Detection at Night Based on Mask-SpyNetXianglun Mo0Chuanpeng Sun1https://orcid.org/0000-0002-2844-117XChenyu Zhang2Jinpeng Tian3Zhushuai Shao4Department of Transportation, China University of Mining and Technology, Xuzhou, ChinaDepartment of Transportation, China University of Mining and Technology, Xuzhou, ChinaDepartment of Transportation, China University of Mining and Technology, Xuzhou, ChinaDepartment of Transportation, China University of Mining and Technology, Xuzhou, ChinaDepartment of Transportation, China University of Mining and Technology, Xuzhou, ChinaExpressway traffic event detection at night is essential for improving rescue efficiency and avoiding secondary accidents. Most expressways in China have built a complete Expressway video monitoring system. However, at night, the expressway traffic event detection still adopts manual detection, which is inefficient. In this dissertation, the strategy of expressway traffic event detection at night has been analysed first. On this basis, by combining the Mask method and SpyNet deep learning, this study develops a night highway vehicle detection deep learning network with a dense optical flow formed by night vehicle light flow as the detection object. Finally, the Deepsort algorithm is used to track and measure the velocity of the detected target. The measured data are used to compare the background difference method, classical optical flow method, YOLO-v3 and proposed method in this paper. The results show that the proposed method has the advantages of high detection accuracy and fast detection speed.https://ieeexplore.ieee.org/document/9784922/Expressway traffic event detection at nightimage processingmask algorithmSpyNet |
| spellingShingle | Xianglun Mo Chuanpeng Sun Chenyu Zhang Jinpeng Tian Zhushuai Shao Research on Expressway Traffic Event Detection at Night Based on Mask-SpyNet IEEE Access Expressway traffic event detection at night image processing mask algorithm SpyNet |
| title | Research on Expressway Traffic Event Detection at Night Based on Mask-SpyNet |
| title_full | Research on Expressway Traffic Event Detection at Night Based on Mask-SpyNet |
| title_fullStr | Research on Expressway Traffic Event Detection at Night Based on Mask-SpyNet |
| title_full_unstemmed | Research on Expressway Traffic Event Detection at Night Based on Mask-SpyNet |
| title_short | Research on Expressway Traffic Event Detection at Night Based on Mask-SpyNet |
| title_sort | research on expressway traffic event detection at night based on mask spynet |
| topic | Expressway traffic event detection at night image processing mask algorithm SpyNet |
| url | https://ieeexplore.ieee.org/document/9784922/ |
| work_keys_str_mv | AT xianglunmo researchonexpresswaytrafficeventdetectionatnightbasedonmaskspynet AT chuanpengsun researchonexpresswaytrafficeventdetectionatnightbasedonmaskspynet AT chenyuzhang researchonexpresswaytrafficeventdetectionatnightbasedonmaskspynet AT jinpengtian researchonexpresswaytrafficeventdetectionatnightbasedonmaskspynet AT zhushuaishao researchonexpresswaytrafficeventdetectionatnightbasedonmaskspynet |