Forest Fire Smoke Recognition Based on Anchor Box Adaptive Generation Method
There are major problems in the field of image-based forest fire smoke detection, including the low recognition rate caused by the changeable and complex state of smoke in the forest environment and the high false alarm rate caused by various interferential objects in the recognition process. Here,...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-02-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/10/5/566 |
| _version_ | 1797417283009642496 |
|---|---|
| author | Enting Zhao Yang Liu Junguo Zhang Ye Tian |
| author_facet | Enting Zhao Yang Liu Junguo Zhang Ye Tian |
| author_sort | Enting Zhao |
| collection | DOAJ |
| description | There are major problems in the field of image-based forest fire smoke detection, including the low recognition rate caused by the changeable and complex state of smoke in the forest environment and the high false alarm rate caused by various interferential objects in the recognition process. Here, a forest fire smoke identification method based on the integration of environmental information is proposed. The model uses (1) the Faster R-CNN as the basic framework, (2) a component perception module to generate a receptive field of integrated environmental information through separable convolution to improve recognition accuracy, and (3) a multi-level Region of Interest (ROI)pooling structure to reduce the deviation caused by rounding in the ROI pooling process. The results showed that the model achieved a recognition accuracy rate of 96.72%, an Intersection Over Union (IOU) of 78.96%, and an average recognition speed for each picture of 1.5 ms; the false alarm rate was 2.35% and the false-negative rate was 3.28%. Compared with other models, the proposed model can effectively enhance the recognition accuracy and recognition speed of forest fire smoke, which provides a technical basis for the real-time and accurate detection of forest fires. |
| first_indexed | 2024-03-09T06:16:26Z |
| format | Article |
| id | doaj.art-3561167aff5f4301b8c733ef3e3efd32 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-09T06:16:26Z |
| publishDate | 2021-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-3561167aff5f4301b8c733ef3e3efd322023-12-03T11:52:25ZengMDPI AGElectronics2079-92922021-02-0110556610.3390/electronics10050566Forest Fire Smoke Recognition Based on Anchor Box Adaptive Generation MethodEnting Zhao0Yang Liu1Junguo Zhang2Ye Tian3School of Technology, Beijing Forestry University, Beijing 100083, ChinaSchool of Technology, Beijing Forestry University, Beijing 100083, ChinaSchool of Technology, Beijing Forestry University, Beijing 100083, ChinaSchool of Technology, Beijing Forestry University, Beijing 100083, ChinaThere are major problems in the field of image-based forest fire smoke detection, including the low recognition rate caused by the changeable and complex state of smoke in the forest environment and the high false alarm rate caused by various interferential objects in the recognition process. Here, a forest fire smoke identification method based on the integration of environmental information is proposed. The model uses (1) the Faster R-CNN as the basic framework, (2) a component perception module to generate a receptive field of integrated environmental information through separable convolution to improve recognition accuracy, and (3) a multi-level Region of Interest (ROI)pooling structure to reduce the deviation caused by rounding in the ROI pooling process. The results showed that the model achieved a recognition accuracy rate of 96.72%, an Intersection Over Union (IOU) of 78.96%, and an average recognition speed for each picture of 1.5 ms; the false alarm rate was 2.35% and the false-negative rate was 3.28%. Compared with other models, the proposed model can effectively enhance the recognition accuracy and recognition speed of forest fire smoke, which provides a technical basis for the real-time and accurate detection of forest fires.https://www.mdpi.com/2079-9292/10/5/566forest fire smokeFaster R-CNNreceptive fieldanchor boxmulti-level ROI pooling |
| spellingShingle | Enting Zhao Yang Liu Junguo Zhang Ye Tian Forest Fire Smoke Recognition Based on Anchor Box Adaptive Generation Method Electronics forest fire smoke Faster R-CNN receptive field anchor box multi-level ROI pooling |
| title | Forest Fire Smoke Recognition Based on Anchor Box Adaptive Generation Method |
| title_full | Forest Fire Smoke Recognition Based on Anchor Box Adaptive Generation Method |
| title_fullStr | Forest Fire Smoke Recognition Based on Anchor Box Adaptive Generation Method |
| title_full_unstemmed | Forest Fire Smoke Recognition Based on Anchor Box Adaptive Generation Method |
| title_short | Forest Fire Smoke Recognition Based on Anchor Box Adaptive Generation Method |
| title_sort | forest fire smoke recognition based on anchor box adaptive generation method |
| topic | forest fire smoke Faster R-CNN receptive field anchor box multi-level ROI pooling |
| url | https://www.mdpi.com/2079-9292/10/5/566 |
| work_keys_str_mv | AT entingzhao forestfiresmokerecognitionbasedonanchorboxadaptivegenerationmethod AT yangliu forestfiresmokerecognitionbasedonanchorboxadaptivegenerationmethod AT junguozhang forestfiresmokerecognitionbasedonanchorboxadaptivegenerationmethod AT yetian forestfiresmokerecognitionbasedonanchorboxadaptivegenerationmethod |