Efficient dead pine tree detecting method in the Forest damaged by pine wood nematode (<i>Bursaphelenchus xylophilus</i>) through utilizing unmanned aerial vehicles and deep learning-based object detection techniques

Lim, Wontaek; Choi, Kwanghun; Cho, Wonhee; Chang, Byungwoo; Ko, Dongwook W.

doi:10.1080/21580103.2022.2048900

Cited by 10 publications

(7 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, the default hyperparameters could have been suitable for the task, in which case further optimization would not have had a significant effect on the results. In the referred studies [13,15,16], the researchers have not mentioned hyperparameter optimization; results of this study did not reveal any concerns regarding the use of default hyperparameters.…”

Section: Evaluation Of Model Trainingmentioning

confidence: 69%

“…Comparison of Faster Region-based Convolutional Neural Network (Faster R-CNN) and YOLOv3 showed the methods had similar precision, but the YOLO-based models had a smaller size and faster processing speed [15]. Recent studies have implemented YOLOv3 for object detection with a focus on minimizing the omission error [16], a lightweight improved YOLOv4-Tiny based method suitable for edge computing [17], and an enhanced version of YOLOv4 providing more efficient model optimization and an improved accuracy [18].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Estimating Tree Health Decline Caused by Ips typographus L. from UAS RGB Images Using a Deep One-Stage Object Detection Neural Network

et al. 2022

View full text Add to dashboard Cite

Various biotic and abiotic stresses are causing decline in forest health globally. Presently, one of the major biotic stress agents in Europe is the European spruce bark beetle (Ips typographus L.) which is increasingly causing widespread tree mortality in northern latitudes as a consequence of the warming climate. Remote sensing using unoccupied aerial systems (UAS) together with evolving machine learning techniques provide a powerful tool for fast-response monitoring of forest health. The aim of this study was to investigate the performance of a deep one-stage object detection neural network in the detection of damage by I. typographus in Norway spruce trees using UAS RGB images. A Scaled-YOLOv4 (You Only Look Once) network was implemented and trained for tree health analysis. Datasets for model training were collected during 2013–2020 from three different areas, using four different RGB cameras, and under varying weather conditions. Different model training options were evaluated, including two different symptom rules, different partitions of the dataset, fine-tuning, and hyperparameter optimization. Our study showed that the network was able to detect and classify spruce trees that had visually separable crown symptoms, but it failed to separate spruce trees with stem symptoms and a green crown from healthy spruce trees. For the best model, the overall F-score was 89%, and the F-scores for the healthy, infested, and dead trees were 90%, 79%, and 98%, respectively. The method adapted well to the diverse dataset, and the processing results with different options were consistent. The results indicated that the proposed method could enable implementation of low-cost tools for management of I. typographus outbreaks.

show abstract

Section: Evaluation Of Model Trainingmentioning

confidence: 69%

Section: Introductionmentioning

confidence: 99%

Estimating Tree Health Decline Caused by Ips typographus L. from UAS RGB Images Using a Deep One-Stage Object Detection Neural Network

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In this study, data augmentation was performed on the individual tree samples to increase the number of training samples. The data augmentation methods include rotation and brightening, such as rotating the image clockwise by 90 • , counterclockwise by 90 • , 180 • and brightening by 50% [45][46][47][48]. After data augmentation, the number of sample datasets was increased to five times.…”

Section: Data Augmentationmentioning

confidence: 99%

Tree Species Classification in Subtropical Natural Forests Using High-Resolution UAV RGB and SuperView-1 Multispectral Imageries Based on Deep Learning Network Approaches: A Case Study within the Baima Snow Mountain National Nature Reserve, China

2023

View full text Add to dashboard Cite

Accurate information on dominant tree species and their spatial distribution in subtropical natural forests are key ecological monitoring factors for accurately characterizing forest biodiversity, depicting the tree competition mechanism and quantitatively evaluating forest ecosystem stability. In this study, the subtropical natural forest in northwest Yunnan province of China was selected as the study area. Firstly, an object-oriented multi-resolution segmentation (MRS) algorithm was used to segment individual tree crowns from the UAV RGB imagery and satellite multispectral imagery in the forests with different densities (low (547 n/ha), middle (753 n/ha) and high (1040 n/ha)), and parameters of the MRS algorithm were tested and optimized for accurately extracting the tree crown and position information of the individual tree. Secondly, the texture metrics of the UAV RGB imagery and the spectral metrics of the satellite multispectral imagery within the individual tree crown were extracted, and the random forest algorithm and three deep learning networks constructed in this study were utilized to classify the five dominant tree species. Finally, we compared and evaluated the performance of the random forest algorithm and three deep learning networks for dominant tree species classification using the field measurement data, and the influence of the number of training samples on the accuracy of dominant tree species classification using deep learning networks was investigated. The results showed that: (1) Stand density had little influence on individual tree segmentation using the object-oriented MRS algorithm. In the forests with different stand densities, the F1 score of individual tree segmentation based on satellite multispectral imagery was 71.3–74.7%, and that based on UAV high-resolution RGB imagery was 75.4–79.2%. (2) The overall accuracy of dominant tree species classification using the light-weight network MobileNetV2 (OA = 71.11–82.22%), residual network ResNet34 (OA = 78.89–91.11%) and dense network DenseNet121 (OA = 81.11–94.44%) was higher than that of the random forest algorithm (OA = 60.00–64.44%), among which DenseNet121 had the highest overall accuracy. Texture metrics improved the overall accuracy of dominant tree species classification. (3) For the three deep learning networks, the changes in overall accuracy of dominant tree species classification influenced by the number of training samples were 2.69–4.28%.

show abstract

“…Pinewood nematode is native to North America and is less harmful to native pine plants. However, after invading Asia and Europe ( Kim et al., 2018 , 2020 ; Lim et al., 2022 ), the PWD has had disastrous effects on pine trees in countries such as Japan, Korea, China, Portugal, and Spain ( Ohsawa and Akiba, 2014 ; Wang and Zhang, 2015 ; Wang et al., 2022 ). Since 1982, when PWD was first discovered in China, the disease has caused the death of hundreds of millions of pine trees, with an annual average of about 27 million dead trees, making it the biggest killer of China’s pinewoods ( Yang et al., 2014 ).…”

Section: Introductionmentioning

confidence: 99%

Pine wilt disease detection algorithm based on improved YOLOv5

Du,

Wu,

Wen

et al. 2024

Front. Plant Sci.

View full text Add to dashboard Cite

Pine wilt disease (PWD) poses a significant threat to forests due to its high infectivity and lethality. The absence of an effective treatment underscores the importance of timely detection and isolation of infected trees for effective prevention and control. While deep learning techniques combined unmanned aerial vehicle (UAV) remote sensing images offer promise for accurate identification of diseased pine trees in their natural environments, they often demand extensive prior professional knowledge and struggle with efficiency. This paper proposes a detection model YOLOv5L-s-SimAM-ASFF, which achieves remarkable precision, maintains a lightweight structure, and facilitates real-time detection of diseased pine trees in UAV RGB images under natural conditions. This is achieved through the integration of the ShuffleNetV2 network, a simple parameter-free attention module known as SimAM, and adaptively spatial feature fusion (ASFF). The model boasts a mean average precision (mAP) of 95.64% and a recall rate of 91.28% in detecting pine wilt diseased trees, while operating at an impressive 95.70 frames per second (FPS). Furthermore, it significantly reduces model size and parameter count compared to the original YOLOv5-Lite. These findings indicate that the proposed model YOLOv5L-s-SimAM-ASFF is most suitable for real-time, high-accuracy, and lightweight detection of PWD-infected trees. This capability is crucial for precise localization and quantification of infected trees, thereby providing valuable guidance for effective management and eradication efforts.

show abstract

Efficient dead pine tree detecting method in the Forest damaged by pine wood nematode (Bursaphelenchus xylophilus) through utilizing unmanned aerial vehicles and deep learning-based object detection techniques

Cited by 10 publications

References 22 publications

Estimating Tree Health Decline Caused by Ips typographus L. from UAS RGB Images Using a Deep One-Stage Object Detection Neural Network

Estimating Tree Health Decline Caused by Ips typographus L. from UAS RGB Images Using a Deep One-Stage Object Detection Neural Network

Tree Species Classification in Subtropical Natural Forests Using High-Resolution UAV RGB and SuperView-1 Multispectral Imageries Based on Deep Learning Network Approaches: A Case Study within the Baima Snow Mountain National Nature Reserve, China

Pine wilt disease detection algorithm based on improved YOLOv5

Contact Info

Product

Resources

About