A High-Precision Ensemble Model for Forest Fire Detection in Large and Small Targets
Forest fires are major forestry disasters that cause loss of forest resources, forest ecosystem safety, and personal injury. It is often difficult for current forest fire detection models to achieve high detection accuracy on both large and small targets at the same time. In addition, most of the ex...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-10-01
|
Series: | Forests |
Subjects: | |
Online Access: | https://www.mdpi.com/1999-4907/14/10/2089 |
_version_ | 1797573775218180096 |
---|---|
author | Jiachen Qian Di Bai Wanguo Jiao Ling Jiang Renjie Xu Haifeng Lin Tian Wang |
author_facet | Jiachen Qian Di Bai Wanguo Jiao Ling Jiang Renjie Xu Haifeng Lin Tian Wang |
author_sort | Jiachen Qian |
collection | DOAJ |
description | Forest fires are major forestry disasters that cause loss of forest resources, forest ecosystem safety, and personal injury. It is often difficult for current forest fire detection models to achieve high detection accuracy on both large and small targets at the same time. In addition, most of the existing forest fire detection models are single detection models, and using only a single model for fire detection in a complex forest environment has a high misclassification rate, and the accuracy rate needs to be improved. Aiming at the above problems, this paper designs two forest fire detection models (named WSB and WSS) and proposes an integrated learning-based forest fire detection model (named WSB_WSS), which also obtains high accuracy in the detection of forest fires with large and small targets. In order to help the model predict the location and size of forest fire targets more accurately, a new edge loss function, Wise-Faster Intersection over Union (WFIoU), is designed in this paper, which effectively improves the performance of the forest fire detection algorithm. The WSB model introduces the Simple-Attention-Module (SimAM) attention mechanism to make the image feature extraction more accurate and introduces the bi-directional connectivity and cross-layer feature fusion to enhance the information mobility and feature expression ability of the feature pyramid network. The WSS model introduces the Squeeze-and-Excitation Networks (SE) attention mechanism so that the model can pay more attention to the most informative forest fire features and suppress unimportant features, and proposes Spatial Pyramid Pooling-Fast Cross Stage Partial Networks (SPPFCSPC) to enable the network to extract features better and speed up the operation of the model. The experimental findings demonstrate that the WSB model outperforms other approaches in the context of identifying forest fires characterized by small-scale targets, achieving a commendable accuracy rate of 82.4%, while the WSS model obtains a higher accuracy of 92.8% in the identification of large target forest fires. Therefore, in this paper, a more efficient forest fire detection model, WSB_WSS, is proposed by integrating the two models through the method of Weighted Boxes Fusion (WBF), and the accuracy of detecting forest fires characterized by small-scale targets attains 83.3%, while for forest fires with larger dimensions, the accuracy reaches an impressive 93.5%. This outcome effectively leverages the strengths inherent in both models, consequently achieving the dual objective of high-precision detection for both small and large target forest fires concurrently. |
first_indexed | 2024-03-10T21:14:43Z |
format | Article |
id | doaj.art-7146d96a7c664beea26fd019e543bc8d |
institution | Directory Open Access Journal |
issn | 1999-4907 |
language | English |
last_indexed | 2024-03-10T21:14:43Z |
publishDate | 2023-10-01 |
publisher | MDPI AG |
record_format | Article |
series | Forests |
spelling | doaj.art-7146d96a7c664beea26fd019e543bc8d2023-11-19T16:33:35ZengMDPI AGForests1999-49072023-10-011410208910.3390/f14102089A High-Precision Ensemble Model for Forest Fire Detection in Large and Small TargetsJiachen Qian0Di Bai1Wanguo Jiao2Ling Jiang3Renjie Xu4Haifeng Lin5Tian Wang6The College of Information Science and Technology, Nanjing Forestry University, Nanjing 210037, ChinaCollege of Information Management, Nanjing Agricultural University, Nanjing 210095, ChinaThe College of Information Science and Technology, Nanjing Forestry University, Nanjing 210037, ChinaThe College of Information Science and Technology, Nanjing Forestry University, Nanjing 210037, ChinaDepartment of Computing and Software, McMaster University, Hamilton, ON L8S 4L8, CanadaThe College of Information Science and Technology, Nanjing Forestry University, Nanjing 210037, ChinaThe College of Information Science and Technology, Nanjing Forestry University, Nanjing 210037, ChinaForest fires are major forestry disasters that cause loss of forest resources, forest ecosystem safety, and personal injury. It is often difficult for current forest fire detection models to achieve high detection accuracy on both large and small targets at the same time. In addition, most of the existing forest fire detection models are single detection models, and using only a single model for fire detection in a complex forest environment has a high misclassification rate, and the accuracy rate needs to be improved. Aiming at the above problems, this paper designs two forest fire detection models (named WSB and WSS) and proposes an integrated learning-based forest fire detection model (named WSB_WSS), which also obtains high accuracy in the detection of forest fires with large and small targets. In order to help the model predict the location and size of forest fire targets more accurately, a new edge loss function, Wise-Faster Intersection over Union (WFIoU), is designed in this paper, which effectively improves the performance of the forest fire detection algorithm. The WSB model introduces the Simple-Attention-Module (SimAM) attention mechanism to make the image feature extraction more accurate and introduces the bi-directional connectivity and cross-layer feature fusion to enhance the information mobility and feature expression ability of the feature pyramid network. The WSS model introduces the Squeeze-and-Excitation Networks (SE) attention mechanism so that the model can pay more attention to the most informative forest fire features and suppress unimportant features, and proposes Spatial Pyramid Pooling-Fast Cross Stage Partial Networks (SPPFCSPC) to enable the network to extract features better and speed up the operation of the model. The experimental findings demonstrate that the WSB model outperforms other approaches in the context of identifying forest fires characterized by small-scale targets, achieving a commendable accuracy rate of 82.4%, while the WSS model obtains a higher accuracy of 92.8% in the identification of large target forest fires. Therefore, in this paper, a more efficient forest fire detection model, WSB_WSS, is proposed by integrating the two models through the method of Weighted Boxes Fusion (WBF), and the accuracy of detecting forest fires characterized by small-scale targets attains 83.3%, while for forest fires with larger dimensions, the accuracy reaches an impressive 93.5%. This outcome effectively leverages the strengths inherent in both models, consequently achieving the dual objective of high-precision detection for both small and large target forest fires concurrently.https://www.mdpi.com/1999-4907/14/10/2089forest fireintegrated learningtarget detection |
spellingShingle | Jiachen Qian Di Bai Wanguo Jiao Ling Jiang Renjie Xu Haifeng Lin Tian Wang A High-Precision Ensemble Model for Forest Fire Detection in Large and Small Targets Forests forest fire integrated learning target detection |
title | A High-Precision Ensemble Model for Forest Fire Detection in Large and Small Targets |
title_full | A High-Precision Ensemble Model for Forest Fire Detection in Large and Small Targets |
title_fullStr | A High-Precision Ensemble Model for Forest Fire Detection in Large and Small Targets |
title_full_unstemmed | A High-Precision Ensemble Model for Forest Fire Detection in Large and Small Targets |
title_short | A High-Precision Ensemble Model for Forest Fire Detection in Large and Small Targets |
title_sort | high precision ensemble model for forest fire detection in large and small targets |
topic | forest fire integrated learning target detection |
url | https://www.mdpi.com/1999-4907/14/10/2089 |
work_keys_str_mv | AT jiachenqian ahighprecisionensemblemodelforforestfiredetectioninlargeandsmalltargets AT dibai ahighprecisionensemblemodelforforestfiredetectioninlargeandsmalltargets AT wanguojiao ahighprecisionensemblemodelforforestfiredetectioninlargeandsmalltargets AT lingjiang ahighprecisionensemblemodelforforestfiredetectioninlargeandsmalltargets AT renjiexu ahighprecisionensemblemodelforforestfiredetectioninlargeandsmalltargets AT haifenglin ahighprecisionensemblemodelforforestfiredetectioninlargeandsmalltargets AT tianwang ahighprecisionensemblemodelforforestfiredetectioninlargeandsmalltargets AT jiachenqian highprecisionensemblemodelforforestfiredetectioninlargeandsmalltargets AT dibai highprecisionensemblemodelforforestfiredetectioninlargeandsmalltargets AT wanguojiao highprecisionensemblemodelforforestfiredetectioninlargeandsmalltargets AT lingjiang highprecisionensemblemodelforforestfiredetectioninlargeandsmalltargets AT renjiexu highprecisionensemblemodelforforestfiredetectioninlargeandsmalltargets AT haifenglin highprecisionensemblemodelforforestfiredetectioninlargeandsmalltargets AT tianwang highprecisionensemblemodelforforestfiredetectioninlargeandsmalltargets |