Identification of Smoke from Straw Burning in Remote Sensing Images with the Improved YOLOv5s Algorithm
Controlling straw burning is important for ensuring the ambient air quality and for sustainable agriculture. Detecting burning straw is vital for managing and controlling straw burning. Existing methods for detecting straw combustion mainly look for combustion products, especially smoke. In this stu...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Atmosphere |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4433/13/6/925 |
| _version_ | 1797490144747454464 |
|---|---|
| author | Hua Liu Jian Li Jia Du Boyu Zhao Yating Hu Dongming Li Weilin Yu |
| author_facet | Hua Liu Jian Li Jia Du Boyu Zhao Yating Hu Dongming Li Weilin Yu |
| author_sort | Hua Liu |
| collection | DOAJ |
| description | Controlling straw burning is important for ensuring the ambient air quality and for sustainable agriculture. Detecting burning straw is vital for managing and controlling straw burning. Existing methods for detecting straw combustion mainly look for combustion products, especially smoke. In this study, the improved You Only Look Once version 5 (YOLOv5s) algorithm was used to detect smoke in Sentinel-2 images captured by remote sensing. Although the original YOLOv5s model had a faster detection speed, its detection accuracy was poor. Thus, a convolutional block attention module was added to the original model. In addition, in order to speed up the convergence of the model, this study replaced the leaky Rectified Linear Unit (leaky ReLU) activation function with the Mish activation function. The accuracy of the improved model was approximately 4% higher for the same detection speed. The improved YOLOv5s had a higher detection accuracy and speed compared to common target detection algorithms, such as RetinaNet, mask Region-Based Convolutional Neural Network (R-CNN), Single-Shot Multibox Detector (SSD), and faster R-CNN. The improved YOLOv5s analyzed an image in 2 ms. In addition, mAP<sub>50</sub> exceeded 94%, demonstrating that with this study’s improved method, smoke can be quickly and accurately identified. This work may serve as a reference for improving smoke detection, and for the effective management and control of straw burning. |
| first_indexed | 2024-03-10T00:26:48Z |
| format | Article |
| id | doaj.art-8cf7ad89eef64820908ac1a9b914cb26 |
| institution | Directory Open Access Journal |
| issn | 2073-4433 |
| language | English |
| last_indexed | 2024-03-10T00:26:48Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Atmosphere |
| spelling | doaj.art-8cf7ad89eef64820908ac1a9b914cb262023-11-23T15:32:51ZengMDPI AGAtmosphere2073-44332022-06-0113692510.3390/atmos13060925Identification of Smoke from Straw Burning in Remote Sensing Images with the Improved YOLOv5s AlgorithmHua Liu0Jian Li1Jia Du2Boyu Zhao3Yating Hu4Dongming Li5Weilin Yu6College of Information Technology, University of Jilin Agricultural, Changchun 130118, ChinaCollege of Information Technology, University of Jilin Agricultural, Changchun 130118, ChinaNortheast Institute of Geography and Agroecology, Chinese Academy of Sciences, Changchun 130102, ChinaNortheast Institute of Geography and Agroecology, Chinese Academy of Sciences, Changchun 130102, ChinaCollege of Information Technology, University of Jilin Agricultural, Changchun 130118, ChinaCollege of Information Technology, University of Jilin Agricultural, Changchun 130118, ChinaCollege of Information Technology, University of Jilin Agricultural, Changchun 130118, ChinaControlling straw burning is important for ensuring the ambient air quality and for sustainable agriculture. Detecting burning straw is vital for managing and controlling straw burning. Existing methods for detecting straw combustion mainly look for combustion products, especially smoke. In this study, the improved You Only Look Once version 5 (YOLOv5s) algorithm was used to detect smoke in Sentinel-2 images captured by remote sensing. Although the original YOLOv5s model had a faster detection speed, its detection accuracy was poor. Thus, a convolutional block attention module was added to the original model. In addition, in order to speed up the convergence of the model, this study replaced the leaky Rectified Linear Unit (leaky ReLU) activation function with the Mish activation function. The accuracy of the improved model was approximately 4% higher for the same detection speed. The improved YOLOv5s had a higher detection accuracy and speed compared to common target detection algorithms, such as RetinaNet, mask Region-Based Convolutional Neural Network (R-CNN), Single-Shot Multibox Detector (SSD), and faster R-CNN. The improved YOLOv5s analyzed an image in 2 ms. In addition, mAP<sub>50</sub> exceeded 94%, demonstrating that with this study’s improved method, smoke can be quickly and accurately identified. This work may serve as a reference for improving smoke detection, and for the effective management and control of straw burning.https://www.mdpi.com/2073-4433/13/6/925YOLOv5ssmoke detectionSentinel-2 remote sensing imageCBAMactivation function |
| spellingShingle | Hua Liu Jian Li Jia Du Boyu Zhao Yating Hu Dongming Li Weilin Yu Identification of Smoke from Straw Burning in Remote Sensing Images with the Improved YOLOv5s Algorithm Atmosphere YOLOv5s smoke detection Sentinel-2 remote sensing image CBAM activation function |
| title | Identification of Smoke from Straw Burning in Remote Sensing Images with the Improved YOLOv5s Algorithm |
| title_full | Identification of Smoke from Straw Burning in Remote Sensing Images with the Improved YOLOv5s Algorithm |
| title_fullStr | Identification of Smoke from Straw Burning in Remote Sensing Images with the Improved YOLOv5s Algorithm |
| title_full_unstemmed | Identification of Smoke from Straw Burning in Remote Sensing Images with the Improved YOLOv5s Algorithm |
| title_short | Identification of Smoke from Straw Burning in Remote Sensing Images with the Improved YOLOv5s Algorithm |
| title_sort | identification of smoke from straw burning in remote sensing images with the improved yolov5s algorithm |
| topic | YOLOv5s smoke detection Sentinel-2 remote sensing image CBAM activation function |
| url | https://www.mdpi.com/2073-4433/13/6/925 |
| work_keys_str_mv | AT hualiu identificationofsmokefromstrawburninginremotesensingimageswiththeimprovedyolov5salgorithm AT jianli identificationofsmokefromstrawburninginremotesensingimageswiththeimprovedyolov5salgorithm AT jiadu identificationofsmokefromstrawburninginremotesensingimageswiththeimprovedyolov5salgorithm AT boyuzhao identificationofsmokefromstrawburninginremotesensingimageswiththeimprovedyolov5salgorithm AT yatinghu identificationofsmokefromstrawburninginremotesensingimageswiththeimprovedyolov5salgorithm AT dongmingli identificationofsmokefromstrawburninginremotesensingimageswiththeimprovedyolov5salgorithm AT weilinyu identificationofsmokefromstrawburninginremotesensingimageswiththeimprovedyolov5salgorithm |