A Lightweight Model for Real-Time Detection of Vehicle Black Smoke
This paper discusses the application of deep learning technology in recognizing vehicle black smoke in road traffic monitoring videos. The use of massive surveillance video data imposes higher demands on the real-time performance of vehicle black smoke detection models. The YOLOv5s model, known for...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/23/9492 |
| _version_ | 1797399552242745344 |
|---|---|
| author | Ke Chen Han Wang Yingchao Zhai |
| author_facet | Ke Chen Han Wang Yingchao Zhai |
| author_sort | Ke Chen |
| collection | DOAJ |
| description | This paper discusses the application of deep learning technology in recognizing vehicle black smoke in road traffic monitoring videos. The use of massive surveillance video data imposes higher demands on the real-time performance of vehicle black smoke detection models. The YOLOv5s model, known for its excellent single-stage object detection performance, has a complex network structure. Therefore, this study proposes a lightweight real-time detection model for vehicle black smoke, named MGSNet, based on the YOLOv5s framework. The research involved collecting road traffic monitoring video data and creating a custom dataset for vehicle black smoke detection by applying data augmentation techniques such as changing image brightness and contrast. The experiment explored three different lightweight networks, namely ShuffleNetv2, MobileNetv3 and GhostNetv1, to reconstruct the CSPDarknet53 backbone feature extraction network of YOLOv5s. Comparative experimental results indicate that reconstructing the backbone network with MobileNetv3 achieved a better balance between detection accuracy and speed. The introduction of the squeeze excitation attention mechanism and inverted residual structure from MobileNetv3 effectively reduced the complexity of black smoke feature fusion. Simultaneously, a novel convolution module, GSConv, was introduced to enhance the expression capability of black smoke features in the neck network. The combination of depthwise separable convolution and standard convolution in the module further reduced the model’s parameter count. After the improvement, the parameter count of the model is compressed to 1/6 of the YOLOv5s model. The lightweight vehicle black smoke real-time detection network, MGSNet, achieved a detection speed of 44.6 frames per second on the test set, an increase of 18.9 frames per second compared with the YOLOv5s model. The mAP@0.5 still exceeded 95%, meeting the application requirements for real-time and accurate detection of vehicle black smoke. |
| first_indexed | 2024-03-09T01:42:50Z |
| format | Article |
| id | doaj.art-2f1ef9fa77cc40c29aa413241185b86a |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T01:42:50Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-2f1ef9fa77cc40c29aa413241185b86a2023-12-08T15:26:11ZengMDPI AGSensors1424-82202023-11-012323949210.3390/s23239492A Lightweight Model for Real-Time Detection of Vehicle Black SmokeKe Chen0Han Wang1Yingchao Zhai2College of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaSchool of Environment and Spatial Informatics, China University of Mining and Technology, Xuzhou 221116, ChinaCollege of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaThis paper discusses the application of deep learning technology in recognizing vehicle black smoke in road traffic monitoring videos. The use of massive surveillance video data imposes higher demands on the real-time performance of vehicle black smoke detection models. The YOLOv5s model, known for its excellent single-stage object detection performance, has a complex network structure. Therefore, this study proposes a lightweight real-time detection model for vehicle black smoke, named MGSNet, based on the YOLOv5s framework. The research involved collecting road traffic monitoring video data and creating a custom dataset for vehicle black smoke detection by applying data augmentation techniques such as changing image brightness and contrast. The experiment explored three different lightweight networks, namely ShuffleNetv2, MobileNetv3 and GhostNetv1, to reconstruct the CSPDarknet53 backbone feature extraction network of YOLOv5s. Comparative experimental results indicate that reconstructing the backbone network with MobileNetv3 achieved a better balance between detection accuracy and speed. The introduction of the squeeze excitation attention mechanism and inverted residual structure from MobileNetv3 effectively reduced the complexity of black smoke feature fusion. Simultaneously, a novel convolution module, GSConv, was introduced to enhance the expression capability of black smoke features in the neck network. The combination of depthwise separable convolution and standard convolution in the module further reduced the model’s parameter count. After the improvement, the parameter count of the model is compressed to 1/6 of the YOLOv5s model. The lightweight vehicle black smoke real-time detection network, MGSNet, achieved a detection speed of 44.6 frames per second on the test set, an increase of 18.9 frames per second compared with the YOLOv5s model. The mAP@0.5 still exceeded 95%, meeting the application requirements for real-time and accurate detection of vehicle black smoke.https://www.mdpi.com/1424-8220/23/23/9492intelligent trafficblack smoke exhaustMGSNet modellightweight network MobileNetv3GSConv module |
| spellingShingle | Ke Chen Han Wang Yingchao Zhai A Lightweight Model for Real-Time Detection of Vehicle Black Smoke Sensors intelligent traffic black smoke exhaust MGSNet model lightweight network MobileNetv3 GSConv module |
| title | A Lightweight Model for Real-Time Detection of Vehicle Black Smoke |
| title_full | A Lightweight Model for Real-Time Detection of Vehicle Black Smoke |
| title_fullStr | A Lightweight Model for Real-Time Detection of Vehicle Black Smoke |
| title_full_unstemmed | A Lightweight Model for Real-Time Detection of Vehicle Black Smoke |
| title_short | A Lightweight Model for Real-Time Detection of Vehicle Black Smoke |
| title_sort | lightweight model for real time detection of vehicle black smoke |
| topic | intelligent traffic black smoke exhaust MGSNet model lightweight network MobileNetv3 GSConv module |
| url | https://www.mdpi.com/1424-8220/23/23/9492 |
| work_keys_str_mv | AT kechen alightweightmodelforrealtimedetectionofvehicleblacksmoke AT hanwang alightweightmodelforrealtimedetectionofvehicleblacksmoke AT yingchaozhai alightweightmodelforrealtimedetectionofvehicleblacksmoke AT kechen lightweightmodelforrealtimedetectionofvehicleblacksmoke AT hanwang lightweightmodelforrealtimedetectionofvehicleblacksmoke AT yingchaozhai lightweightmodelforrealtimedetectionofvehicleblacksmoke |