Real-Time Detection of Full-Scale Forest Fire Smoke Based on Deep Convolution Neural Network
To reduce the loss induced by forest fires, it is very important to detect the forest fire smoke in real time so that early and timely warning can be issued. Machine vision and image processing technology is widely used for detecting forest fire smoke. However, most of the traditional image detectio...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/3/536 |
| _version_ | 1797485092404199424 |
|---|---|
| author | Xin Zheng Feng Chen Liming Lou Pengle Cheng Ying Huang |
| author_facet | Xin Zheng Feng Chen Liming Lou Pengle Cheng Ying Huang |
| author_sort | Xin Zheng |
| collection | DOAJ |
| description | To reduce the loss induced by forest fires, it is very important to detect the forest fire smoke in real time so that early and timely warning can be issued. Machine vision and image processing technology is widely used for detecting forest fire smoke. However, most of the traditional image detection algorithms require manual extraction of image features and, thus, are not real-time. This paper evaluates the effectiveness of using the deep convolutional neural network to detect forest fire smoke in real time. Several target detection deep convolutional neural network algorithms evaluated include the EfficientDet (EfficientDet: Scalable and Efficient Object Detection), Faster R-CNN (Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks), YOLOv3 (You Only Look Once V3), and SSD (Single Shot MultiBox Detector) advanced CNN (Convolutional Neural Networks) model. The YOLOv3 showed a detection speed up to 27 FPS, indicating it is a real-time smoke detector. By comparing these algorithms with the current existing forest fire smoke detection algorithms, it can be found that the deep convolutional neural network algorithms result in better smoke detection accuracy. In particular, the EfficientDet algorithm achieves an average detection accuracy of 95.7%, which is the best real-time forest fire smoke detection among the evaluated algorithms. |
| first_indexed | 2024-03-09T23:13:49Z |
| format | Article |
| id | doaj.art-91f4b49e268340249fdbf4b4e6d0fe3f |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T23:13:49Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-91f4b49e268340249fdbf4b4e6d0fe3f2023-11-23T17:39:20ZengMDPI AGRemote Sensing2072-42922022-01-0114353610.3390/rs14030536Real-Time Detection of Full-Scale Forest Fire Smoke Based on Deep Convolution Neural NetworkXin Zheng0Feng Chen1Liming Lou2Pengle Cheng3Ying Huang4School of Technology, Beijing Forestry University, Beijing 100083, ChinaSchool of Nature Conservation, Beijing Forestry University, Beijing 100083, ChinaSchool of Technology, Beijing Forestry University, Beijing 100083, ChinaSchool of Technology, Beijing Forestry University, Beijing 100083, ChinaDepartment of Civil, Construction, and Environmental Engineering, North Dakota State University, Fargo, ND 58102, USATo reduce the loss induced by forest fires, it is very important to detect the forest fire smoke in real time so that early and timely warning can be issued. Machine vision and image processing technology is widely used for detecting forest fire smoke. However, most of the traditional image detection algorithms require manual extraction of image features and, thus, are not real-time. This paper evaluates the effectiveness of using the deep convolutional neural network to detect forest fire smoke in real time. Several target detection deep convolutional neural network algorithms evaluated include the EfficientDet (EfficientDet: Scalable and Efficient Object Detection), Faster R-CNN (Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks), YOLOv3 (You Only Look Once V3), and SSD (Single Shot MultiBox Detector) advanced CNN (Convolutional Neural Networks) model. The YOLOv3 showed a detection speed up to 27 FPS, indicating it is a real-time smoke detector. By comparing these algorithms with the current existing forest fire smoke detection algorithms, it can be found that the deep convolutional neural network algorithms result in better smoke detection accuracy. In particular, the EfficientDet algorithm achieves an average detection accuracy of 95.7%, which is the best real-time forest fire smoke detection among the evaluated algorithms.https://www.mdpi.com/2072-4292/14/3/536forest fire smoke detectionconvolutional neural networksdeep learningreal-time detection |
| spellingShingle | Xin Zheng Feng Chen Liming Lou Pengle Cheng Ying Huang Real-Time Detection of Full-Scale Forest Fire Smoke Based on Deep Convolution Neural Network Remote Sensing forest fire smoke detection convolutional neural networks deep learning real-time detection |
| title | Real-Time Detection of Full-Scale Forest Fire Smoke Based on Deep Convolution Neural Network |
| title_full | Real-Time Detection of Full-Scale Forest Fire Smoke Based on Deep Convolution Neural Network |
| title_fullStr | Real-Time Detection of Full-Scale Forest Fire Smoke Based on Deep Convolution Neural Network |
| title_full_unstemmed | Real-Time Detection of Full-Scale Forest Fire Smoke Based on Deep Convolution Neural Network |
| title_short | Real-Time Detection of Full-Scale Forest Fire Smoke Based on Deep Convolution Neural Network |
| title_sort | real time detection of full scale forest fire smoke based on deep convolution neural network |
| topic | forest fire smoke detection convolutional neural networks deep learning real-time detection |
| url | https://www.mdpi.com/2072-4292/14/3/536 |
| work_keys_str_mv | AT xinzheng realtimedetectionoffullscaleforestfiresmokebasedondeepconvolutionneuralnetwork AT fengchen realtimedetectionoffullscaleforestfiresmokebasedondeepconvolutionneuralnetwork AT liminglou realtimedetectionoffullscaleforestfiresmokebasedondeepconvolutionneuralnetwork AT penglecheng realtimedetectionoffullscaleforestfiresmokebasedondeepconvolutionneuralnetwork AT yinghuang realtimedetectionoffullscaleforestfiresmokebasedondeepconvolutionneuralnetwork |