Automatic detection of standing dead trees based on improved YOLOv7 from airborne remote sensing imagery
Detecting and localizing standing dead trees (SDTs) is crucial for effective forest management and conservation. Due to challenges posed by mountainous terrain and road conditions, conducting a swift and comprehensive survey of SDTs through traditional manual inventory methods is considerably diffic...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-01-01
|
| Series: | Frontiers in Plant Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2024.1278161/full |
| _version_ | 1827376884354121728 |
|---|---|
| author | Hongwei Zhou Shangxin Wu Zihan Xu Hong Sun |
| author_facet | Hongwei Zhou Shangxin Wu Zihan Xu Hong Sun |
| author_sort | Hongwei Zhou |
| collection | DOAJ |
| description | Detecting and localizing standing dead trees (SDTs) is crucial for effective forest management and conservation. Due to challenges posed by mountainous terrain and road conditions, conducting a swift and comprehensive survey of SDTs through traditional manual inventory methods is considerably difficult. In recent years, advancements in deep learning and remote sensing technology have facilitated real-time and efficient detection of dead trees. Nevertheless, challenges persist in identifying individual dead trees in airborne remote sensing images, attributed to factors such as small target size, mutual occlusion and complex backgrounds. These aspects collectively contribute to the increased difficulty of detecting dead trees at a single-tree scale. To address this issue, the paper introduces an improved You Only Look Once version 7 (YOLOv7) model that incorporates the Simple Parameter-Free Attention Module (SimAM), an unparameterized attention mechanism. This improvement aims to enhance the network’s feature extraction capabilities and increase the model’s sensitivity to small target dead trees. To validate the superiority of SimAM_YOLOv7, we compared it with four widely adopted attention mechanisms. Additionally, a method to enhance model robustness is presented, involving the replacement of the Complete Intersection over Union (CIoU) loss in the original YOLOv7 model with the Wise-IoU (WIoU) loss function. Following these, we evaluated detection accuracy using a self-developed dataset of SDTs in forests. The results indicate that the improved YOLOv7 model can effectively identify dead trees in airborne remote sensing images, achieving precision, recall and mAP@0.5 values of 94.31%, 93.13% and 98.03%, respectively. These values are 3.67%, 2.28% and 1.56% higher than those of the original YOLOv7 model. This improvement model provides a convenient solution for forest management. |
| first_indexed | 2024-03-08T12:30:20Z |
| format | Article |
| id | doaj.art-8723d5442fac42f4b5087f401107fd17 |
| institution | Directory Open Access Journal |
| issn | 1664-462X |
| language | English |
| last_indexed | 2024-03-08T12:30:20Z |
| publishDate | 2024-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Plant Science |
| spelling | doaj.art-8723d5442fac42f4b5087f401107fd172024-01-22T04:40:28ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2024-01-011510.3389/fpls.2024.12781611278161Automatic detection of standing dead trees based on improved YOLOv7 from airborne remote sensing imageryHongwei Zhou0Shangxin Wu1Zihan Xu2Hong Sun3College of Computer and Control Engineering, Northeast Forestry University, Harbin, ChinaCollege of Computer and Control Engineering, Northeast Forestry University, Harbin, ChinaCollege of Computer and Control Engineering, Northeast Forestry University, Harbin, ChinaKey Laboratory of National Forestry and Grassland Administration on Forest and Grassland Pest Monitoring and Warning, Center for Biological Disaster Prevention and Control, National Forestry and Grassland Administration, Shenyang, ChinaDetecting and localizing standing dead trees (SDTs) is crucial for effective forest management and conservation. Due to challenges posed by mountainous terrain and road conditions, conducting a swift and comprehensive survey of SDTs through traditional manual inventory methods is considerably difficult. In recent years, advancements in deep learning and remote sensing technology have facilitated real-time and efficient detection of dead trees. Nevertheless, challenges persist in identifying individual dead trees in airborne remote sensing images, attributed to factors such as small target size, mutual occlusion and complex backgrounds. These aspects collectively contribute to the increased difficulty of detecting dead trees at a single-tree scale. To address this issue, the paper introduces an improved You Only Look Once version 7 (YOLOv7) model that incorporates the Simple Parameter-Free Attention Module (SimAM), an unparameterized attention mechanism. This improvement aims to enhance the network’s feature extraction capabilities and increase the model’s sensitivity to small target dead trees. To validate the superiority of SimAM_YOLOv7, we compared it with four widely adopted attention mechanisms. Additionally, a method to enhance model robustness is presented, involving the replacement of the Complete Intersection over Union (CIoU) loss in the original YOLOv7 model with the Wise-IoU (WIoU) loss function. Following these, we evaluated detection accuracy using a self-developed dataset of SDTs in forests. The results indicate that the improved YOLOv7 model can effectively identify dead trees in airborne remote sensing images, achieving precision, recall and mAP@0.5 values of 94.31%, 93.13% and 98.03%, respectively. These values are 3.67%, 2.28% and 1.56% higher than those of the original YOLOv7 model. This improvement model provides a convenient solution for forest management.https://www.frontiersin.org/articles/10.3389/fpls.2024.1278161/fullstanding dead treesdeep learningattention mechanismWise-IoU loss functionairborne remote sensing imagery |
| spellingShingle | Hongwei Zhou Shangxin Wu Zihan Xu Hong Sun Automatic detection of standing dead trees based on improved YOLOv7 from airborne remote sensing imagery Frontiers in Plant Science standing dead trees deep learning attention mechanism Wise-IoU loss function airborne remote sensing imagery |
| title | Automatic detection of standing dead trees based on improved YOLOv7 from airborne remote sensing imagery |
| title_full | Automatic detection of standing dead trees based on improved YOLOv7 from airborne remote sensing imagery |
| title_fullStr | Automatic detection of standing dead trees based on improved YOLOv7 from airborne remote sensing imagery |
| title_full_unstemmed | Automatic detection of standing dead trees based on improved YOLOv7 from airborne remote sensing imagery |
| title_short | Automatic detection of standing dead trees based on improved YOLOv7 from airborne remote sensing imagery |
| title_sort | automatic detection of standing dead trees based on improved yolov7 from airborne remote sensing imagery |
| topic | standing dead trees deep learning attention mechanism Wise-IoU loss function airborne remote sensing imagery |
| url | https://www.frontiersin.org/articles/10.3389/fpls.2024.1278161/full |
| work_keys_str_mv | AT hongweizhou automaticdetectionofstandingdeadtreesbasedonimprovedyolov7fromairborneremotesensingimagery AT shangxinwu automaticdetectionofstandingdeadtreesbasedonimprovedyolov7fromairborneremotesensingimagery AT zihanxu automaticdetectionofstandingdeadtreesbasedonimprovedyolov7fromairborneremotesensingimagery AT hongsun automaticdetectionofstandingdeadtreesbasedonimprovedyolov7fromairborneremotesensingimagery |