Deep Learning-Based Pine Nematode Trees’ Identification Using Multispectral and Visible UAV Imagery
Pine wilt disease (PWD) has become increasingly serious recently and causes great damage to the world’s pine forest resources. The use of unmanned aerial vehicle (UAV)-based remote sensing helps to identify pine nematode trees in time and has become a feasible and effective approach to precisely mon...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Drones |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-446X/7/3/183 |
| _version_ | 1797612347710242816 |
|---|---|
| author | Bingxi Qin Fenggang Sun Weixing Shen Bin Dong Shencheng Ma Xinyu Huo Peng Lan |
| author_facet | Bingxi Qin Fenggang Sun Weixing Shen Bin Dong Shencheng Ma Xinyu Huo Peng Lan |
| author_sort | Bingxi Qin |
| collection | DOAJ |
| description | Pine wilt disease (PWD) has become increasingly serious recently and causes great damage to the world’s pine forest resources. The use of unmanned aerial vehicle (UAV)-based remote sensing helps to identify pine nematode trees in time and has become a feasible and effective approach to precisely monitor PWD infection. However, a rapid and high-accuracy detection approach has not been well established in a complex terrain environment. To this end, a deep learning-based pine nematode tree identification method is proposed by fusing visible and multispectral imagery. A UAV equipped with a multispectral camera and a visible camera was used to obtain imagery, where multispectral imagery includes six bands, i.e., red, green, blue, near-infrared, red edge and red edge 750 nm. Two vegetation indexes, NDVI (Normalized Difference Vegetation Index) and NDRE (Normalized Difference Red Edge Index) are extracted as a typical feature according to the reflectance of infected trees in different spectral bands. The YOLOv5 (You Only Look Once v5)-based detection algorithm is adopted and optimized from different aspects to realize the identification of infected pine trees with high detection speed and accuracy. e.g., GhostNet is adopted to reduce the number of model parameters and improve the detection speed; a module combining a CBAM (Convolutional Block Attention Module) and a CA (Coordinate Attention) mechanism is designed to improve the feature extraction for small-scale pine nematode trees; Transformer module and BiFPN (Bidirectional Feature Pyramid Network) structure are applied to improve the feature fusion capability. The experiments show that the mAP@0.5 of the improved YOLOv5 model is 98.7%, the precision is 98.1%, the recall is 97.3%, the average detection speed of single imagery is 0.067 s, and the model size is 46.69 MB. All these metrics outperform other comparison methods. Therefore, the proposed method can achieve a fast and accurate detection of pine nematode trees, providing effective technical support for the control of a pine nematode epidemic. |
| first_indexed | 2024-03-11T06:40:00Z |
| format | Article |
| id | doaj.art-90718e40f3ef40f685cff2dccc18b433 |
| institution | Directory Open Access Journal |
| issn | 2504-446X |
| language | English |
| last_indexed | 2024-03-11T06:40:00Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Drones |
| spelling | doaj.art-90718e40f3ef40f685cff2dccc18b4332023-11-17T10:39:36ZengMDPI AGDrones2504-446X2023-03-017318310.3390/drones7030183Deep Learning-Based Pine Nematode Trees’ Identification Using Multispectral and Visible UAV ImageryBingxi Qin0Fenggang Sun1Weixing Shen2Bin Dong3Shencheng Ma4Xinyu Huo5Peng Lan6College of Information Science and Engineering, Shandong Agricultural University, Tai’an 271018, ChinaCollege of Information Science and Engineering, Shandong Agricultural University, Tai’an 271018, ChinaTaishan Forest Pest Management and Quarantine Station, Tai’an 271018, ChinaTaishan Forest Pest Management and Quarantine Station, Tai’an 271018, ChinaTaishan Forest Pest Management and Quarantine Station, Tai’an 271018, ChinaCollege of Information Science and Engineering, Shandong Agricultural University, Tai’an 271018, ChinaCollege of Information Science and Engineering, Shandong Agricultural University, Tai’an 271018, ChinaPine wilt disease (PWD) has become increasingly serious recently and causes great damage to the world’s pine forest resources. The use of unmanned aerial vehicle (UAV)-based remote sensing helps to identify pine nematode trees in time and has become a feasible and effective approach to precisely monitor PWD infection. However, a rapid and high-accuracy detection approach has not been well established in a complex terrain environment. To this end, a deep learning-based pine nematode tree identification method is proposed by fusing visible and multispectral imagery. A UAV equipped with a multispectral camera and a visible camera was used to obtain imagery, where multispectral imagery includes six bands, i.e., red, green, blue, near-infrared, red edge and red edge 750 nm. Two vegetation indexes, NDVI (Normalized Difference Vegetation Index) and NDRE (Normalized Difference Red Edge Index) are extracted as a typical feature according to the reflectance of infected trees in different spectral bands. The YOLOv5 (You Only Look Once v5)-based detection algorithm is adopted and optimized from different aspects to realize the identification of infected pine trees with high detection speed and accuracy. e.g., GhostNet is adopted to reduce the number of model parameters and improve the detection speed; a module combining a CBAM (Convolutional Block Attention Module) and a CA (Coordinate Attention) mechanism is designed to improve the feature extraction for small-scale pine nematode trees; Transformer module and BiFPN (Bidirectional Feature Pyramid Network) structure are applied to improve the feature fusion capability. The experiments show that the mAP@0.5 of the improved YOLOv5 model is 98.7%, the precision is 98.1%, the recall is 97.3%, the average detection speed of single imagery is 0.067 s, and the model size is 46.69 MB. All these metrics outperform other comparison methods. Therefore, the proposed method can achieve a fast and accurate detection of pine nematode trees, providing effective technical support for the control of a pine nematode epidemic.https://www.mdpi.com/2504-446X/7/3/183pine wood nematode diseasedeep learningmultispectral imageryYOLOv5 |
| spellingShingle | Bingxi Qin Fenggang Sun Weixing Shen Bin Dong Shencheng Ma Xinyu Huo Peng Lan Deep Learning-Based Pine Nematode Trees’ Identification Using Multispectral and Visible UAV Imagery Drones pine wood nematode disease deep learning multispectral imagery YOLOv5 |
| title | Deep Learning-Based Pine Nematode Trees’ Identification Using Multispectral and Visible UAV Imagery |
| title_full | Deep Learning-Based Pine Nematode Trees’ Identification Using Multispectral and Visible UAV Imagery |
| title_fullStr | Deep Learning-Based Pine Nematode Trees’ Identification Using Multispectral and Visible UAV Imagery |
| title_full_unstemmed | Deep Learning-Based Pine Nematode Trees’ Identification Using Multispectral and Visible UAV Imagery |
| title_short | Deep Learning-Based Pine Nematode Trees’ Identification Using Multispectral and Visible UAV Imagery |
| title_sort | deep learning based pine nematode trees identification using multispectral and visible uav imagery |
| topic | pine wood nematode disease deep learning multispectral imagery YOLOv5 |
| url | https://www.mdpi.com/2504-446X/7/3/183 |
| work_keys_str_mv | AT bingxiqin deeplearningbasedpinenematodetreesidentificationusingmultispectralandvisibleuavimagery AT fenggangsun deeplearningbasedpinenematodetreesidentificationusingmultispectralandvisibleuavimagery AT weixingshen deeplearningbasedpinenematodetreesidentificationusingmultispectralandvisibleuavimagery AT bindong deeplearningbasedpinenematodetreesidentificationusingmultispectralandvisibleuavimagery AT shenchengma deeplearningbasedpinenematodetreesidentificationusingmultispectralandvisibleuavimagery AT xinyuhuo deeplearningbasedpinenematodetreesidentificationusingmultispectralandvisibleuavimagery AT penglan deeplearningbasedpinenematodetreesidentificationusingmultispectralandvisibleuavimagery |