Cascaded Vehicle Matching and Short-Term Spatial-Temporal Network for Smoky Vehicle Detection
Vehicle exhaust is the main source of air pollution with the rapid increase of fuel vehicles. Automatic smoky vehicle detection in videos is a superior solution to traditional expensive remote sensing with ultraviolet-infrared light devices for environmental protection agencies. However, it is chall...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/8/4841 |
| _version_ | 1797606547198574592 |
|---|---|
| author | Xiaojiang Peng Xiaomao Fan Qingyang Wu Jieyan Zhao Pan Gao |
| author_facet | Xiaojiang Peng Xiaomao Fan Qingyang Wu Jieyan Zhao Pan Gao |
| author_sort | Xiaojiang Peng |
| collection | DOAJ |
| description | Vehicle exhaust is the main source of air pollution with the rapid increase of fuel vehicles. Automatic smoky vehicle detection in videos is a superior solution to traditional expensive remote sensing with ultraviolet-infrared light devices for environmental protection agencies. However, it is challenging to distinguish vehicle smoke from shadow and wet regions in cluttered roads, and could be worse due to limited annotated data. In this paper, we first introduce a real-world large-scale smoky vehicle dataset with 75,000 annotated smoky vehicle images, facilitating the effective training of advanced deep learning models. To enable a fair algorithm comparison, we also built a smoky vehicle video dataset including 163 long videos with segment-level annotations. Second, we present a novel efficient cascaded framework for smoky vehicle detection which largely integrates prior knowledge and advanced deep networks. Specifically, it starts from an improved frame-based smoke detector with a high recall rate, and then applies a vehicle matching strategy to fast eliminate non-vehicle smoke proposals, and finally refines the detection with an elaborately-designed short-term spatial-temporal network in consecutive frames. Extensive experiments in four metrics demonstrated that our framework is significantly superior to hand-crafted feature based methods and recent advanced methods. |
| first_indexed | 2024-03-11T05:16:44Z |
| format | Article |
| id | doaj.art-32b6a39f30204c56a27c2366f2ccec23 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T05:16:44Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-32b6a39f30204c56a27c2366f2ccec232023-11-17T18:10:01ZengMDPI AGApplied Sciences2076-34172023-04-01138484110.3390/app13084841Cascaded Vehicle Matching and Short-Term Spatial-Temporal Network for Smoky Vehicle DetectionXiaojiang Peng0Xiaomao Fan1Qingyang Wu2Jieyan Zhao3Pan Gao4College of Big Data and Internet, Shenzhen Technology University, Shenzhen 518118, ChinaCollege of Big Data and Internet, Shenzhen Technology University, Shenzhen 518118, ChinaCollege of Big Data and Internet, Shenzhen Technology University, Shenzhen 518118, ChinaBusiness School, Central South University, Changsha 410083, ChinaCollege of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, ChinaVehicle exhaust is the main source of air pollution with the rapid increase of fuel vehicles. Automatic smoky vehicle detection in videos is a superior solution to traditional expensive remote sensing with ultraviolet-infrared light devices for environmental protection agencies. However, it is challenging to distinguish vehicle smoke from shadow and wet regions in cluttered roads, and could be worse due to limited annotated data. In this paper, we first introduce a real-world large-scale smoky vehicle dataset with 75,000 annotated smoky vehicle images, facilitating the effective training of advanced deep learning models. To enable a fair algorithm comparison, we also built a smoky vehicle video dataset including 163 long videos with segment-level annotations. Second, we present a novel efficient cascaded framework for smoky vehicle detection which largely integrates prior knowledge and advanced deep networks. Specifically, it starts from an improved frame-based smoke detector with a high recall rate, and then applies a vehicle matching strategy to fast eliminate non-vehicle smoke proposals, and finally refines the detection with an elaborately-designed short-term spatial-temporal network in consecutive frames. Extensive experiments in four metrics demonstrated that our framework is significantly superior to hand-crafted feature based methods and recent advanced methods.https://www.mdpi.com/2076-3417/13/8/4841smoky vehicle detectionsmoke recognitiondeep learningconvolutional neural networks |
| spellingShingle | Xiaojiang Peng Xiaomao Fan Qingyang Wu Jieyan Zhao Pan Gao Cascaded Vehicle Matching and Short-Term Spatial-Temporal Network for Smoky Vehicle Detection Applied Sciences smoky vehicle detection smoke recognition deep learning convolutional neural networks |
| title | Cascaded Vehicle Matching and Short-Term Spatial-Temporal Network for Smoky Vehicle Detection |
| title_full | Cascaded Vehicle Matching and Short-Term Spatial-Temporal Network for Smoky Vehicle Detection |
| title_fullStr | Cascaded Vehicle Matching and Short-Term Spatial-Temporal Network for Smoky Vehicle Detection |
| title_full_unstemmed | Cascaded Vehicle Matching and Short-Term Spatial-Temporal Network for Smoky Vehicle Detection |
| title_short | Cascaded Vehicle Matching and Short-Term Spatial-Temporal Network for Smoky Vehicle Detection |
| title_sort | cascaded vehicle matching and short term spatial temporal network for smoky vehicle detection |
| topic | smoky vehicle detection smoke recognition deep learning convolutional neural networks |
| url | https://www.mdpi.com/2076-3417/13/8/4841 |
| work_keys_str_mv | AT xiaojiangpeng cascadedvehiclematchingandshorttermspatialtemporalnetworkforsmokyvehicledetection AT xiaomaofan cascadedvehiclematchingandshorttermspatialtemporalnetworkforsmokyvehicledetection AT qingyangwu cascadedvehiclematchingandshorttermspatialtemporalnetworkforsmokyvehicledetection AT jieyanzhao cascadedvehiclematchingandshorttermspatialtemporalnetworkforsmokyvehicledetection AT pangao cascadedvehiclematchingandshorttermspatialtemporalnetworkforsmokyvehicledetection |