scholarly journals A Deep Learning-Based Generalized System for Detecting Pine Wilt Disease Using RGB-Based UAV Images

2021 ◽  
Vol 14 (1) ◽  
pp. 150
Author(s):  
Jie You ◽  
Ruirui Zhang ◽  
Joonwhoan Lee
Keyword(s):  
Real World ◽  
Early Stage ◽  
Pine Wilt Disease ◽  
Wilt Disease ◽  
Image Resolution ◽  
Test Time ◽  
Detection Model ◽  
Pine Wilt ◽  
Pine Trees ◽  
Uav Images

Pine wilt is a devastating disease that typically kills affected pine trees within a few months. In this paper, we confront the problem of detecting pine wilt disease. In the image samples that have been used for pine wilt disease detection, there is high ambiguity due to poor image resolution and the presence of “disease-like” objects. We therefore created a new dataset using large-sized orthophotographs collected from 32 cities, 167 regions, and 6121 pine wilt disease hotspots in South Korea. In our system, pine wilt disease was detected in two stages: n the first stage, the disease and hard negative samples were collected using a convolutional neural network. Because the diseased areas varied in size and color, and as the disease manifests differently from the early stage to the late stage, hard negative samples were further categorized into six different classes to simplify the complexity of the dataset. Then, in the second stage, we used an object detection model to localize the disease and “disease-like” hard negative samples. We used several image augmentation methods to boost system performance and avoid overfitting. The test process was divided into two phases: a patch-based test and a real-world test. During the patch-based test, we used the test-time augmentation method to obtain the average prediction of our system across multiple augmented samples of data, and the prediction results showed a mean average precision of 89.44% in five-fold cross validation, thus representing an increase of around 5% over the alternative system. In the real-world test, we collected 10 orthophotographs in various resolutions and areas, and our system successfully detected 711 out of 730 potential disease spots.

scholarly journals Early detection of pine wilt disease in Pinus tabuliformis in North China using a field portable spectrometer and UAV-based hyperspectral imagery

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Run Yu ◽  
Lili Ren ◽  
Youqing Luo
Keyword(s):  
Early Stage ◽  
Vegetation Indices ◽  
Pine Wilt Disease ◽  
Wilt Disease ◽  
Pinus Tabulaeformis ◽  
Pine Tree ◽  
Preventative Measures ◽  
Pine Wilt ◽  
Pine Trees ◽  
Airborne Vehicle

Abstract Background Pine wilt disease (PWD) is a major ecological concern in China that has caused severe damage to millions of Chinese pines (Pinus tabulaeformis). To control the spread of PWD, it is necessary to develop an effective approach to detect its presence in the early stage of infection. One potential solution is the use of Unmanned Airborne Vehicle (UAV) based hyperspectral images (HIs). UAV-based HIs have high spatial and spectral resolution and can gather data rapidly, potentially enabling the effective monitoring of large forests. Despite this, few studies examine the feasibility of HI data use in assessing the stage and severity of PWD infection in Chinese pine. Method To fill this gap, we used a Random Forest (RF) algorithm to estimate the stage of PWD infection of trees sampled using UAV-based HI data and ground-based data (data directly collected from trees in the field). We compared relative accuracy of each of these data collection methods. We built our RF model using vegetation indices (VIs), red edge parameters (REPs), moisture indices (MIs), and their combination. Results We report several key results. For ground data, the model that combined all parameters (OA: 80.17%, Kappa: 0.73) performed better than VIs (OA: 75.21%, Kappa: 0.66), REPs (OA: 79.34%, Kappa: 0.67), and MIs (OA: 74.38%, Kappa: 0.65) in predicting the PWD stage of individual pine tree infection. REPs had the highest accuracy (OA: 80.33%, Kappa: 0.58) in distinguishing trees at the early stage of PWD from healthy trees. UAV-based HI data yielded similar results: the model combined VIs, REPs and MIs (OA: 74.38%, Kappa: 0.66) exhibited the highest accuracy in estimating the PWD stage of sampled trees, and REPs performed best in distinguishing healthy trees from trees at early stage of PWD (OA: 71.67%, Kappa: 0.40). Conclusion Overall, our results confirm the validity of using HI data to identify pine trees infected with PWD in its early stage, although its accuracy must be improved before widespread use is practical. We also show UAV-based data PWD classifications are less accurate but comparable to those of ground-based data. We believe that these results can be used to improve preventative measures in the control of PWD.

scholarly journals The Microbiome of Endophytic, Wood Colonizing Bacteria from Pine Trees as Affected by Pine Wilt Disease

2017 ◽  
Vol 7 (1) ◽  
Author(s):  
Diogo Neves Proença ◽  
Romeu Francisco ◽  
Susanne Kublik ◽  
Anne Schöler ◽  
Gisle Vestergaard ◽  
...  
Keyword(s):  
Pine Wilt Disease ◽  
Wilt Disease ◽  
Pine Wilt ◽  
Pine Trees

Volatile compounds in pine stands suffering from pine wilt disease: qualitative and quantitative evaluation

Nematology ◽  
2006 ◽  
Vol 8 (6) ◽  
pp. 869-879 ◽  
Author(s):  
Kazuyoshi Futai ◽  
Natsumi Kanzaki ◽  
Yuko Takeuchi
Keyword(s):  
Volatile Compounds ◽  
Pine Wilt Disease ◽  
Bursaphelenchus Xylophilus ◽  
Wilt Disease ◽  
Economic Damage ◽  
Qualitative And Quantitative ◽  
Pine Wilt ◽  
Pine Trees ◽  
Quantitative Properties ◽  
Pine Stands

AbstractPine wilt disease causes ecological and economic damage in Japanese pine forests in spite of intensive effort to protect them from the pine wood nematode, Bursaphelenchus xylophilus. Pine trees infected with B. xylophilus emit a characteristic bouquet of volatile compounds bioactive to the vector beetle of the nematode, Monochamus alternatus, and potentially affecting symptom development inside the trees. To investigate the qualitative and quantitative properties of volatile compounds in the field, we profiled the volatile emissions in two Japanese black pine stands, one naturally suffering from pine wilt disease and the other artificially inoculated with B. xylophilus. In both pine stands, the emission of some terpenoids from the infected trees such as (−)-α-pinene, began to increase in summer, overlapping the oviposition season of the vector beetle, but peaked in the summer and autumn. These data suggest that the beetles may not necessarily depend on the tremendous quantity of volatiles alone when they search for suitable trees on which to oviposit.

Effects of spring-killed pine trees on the epidemics of pine wilt disease

2012 ◽  
Vol 47 (4) ◽  
pp. 311-318 ◽  
Author(s):  
Katsumi Togashi ◽  
Katsunori Nakamura ◽  
Shota Jikumaru
Keyword(s):  
Pine Wilt Disease ◽  
Wilt Disease ◽  
Pine Wilt ◽  
Pine Trees

scholarly journals The specialization of Esteya vermicola hyphae in infection to Bursaphelenchus xylophilus and its colonization of pine tree

2020 ◽  
Author(s):  
Hai-Hua Wang ◽  
Can Yin ◽  
Jie Gao ◽  
Ran Tao ◽  
Piao-Piao Dai ◽  
...  
Keyword(s):  
Pine Wilt Disease ◽  
Bursaphelenchus Xylophilus ◽  
Wilt Disease ◽  
Fungal Colonization ◽  
Pinewood Nematode ◽  
Pine Tree ◽  
Pine Wilt ◽  
Pine Trees ◽  
Colonization Patterns ◽  
Esteya Vermicola

AbstractPine wilt disease (PWD) caused by the nematode Bursaphelenchus xylophilus is a serious problem on pines, and there is currently no effective control strategy for this disease. Although the endoparasitic fungus Esteya vermicola showed great effectiveness in controlling pine wilt disease, the colonization patterns of the host pine tree xylem by this fungus are unknown. To investigate the colonization patterns of pine xylem by this fungus, the species Pinus koraiensis grown in a greenhouse was used as an experimental host tree. The fungal colonization of healthy and wilting pine trees by E. vermicola was quantified using PCR with a TaqMan probe, and a green fluorescence protein (GFP) transformant was used for visualization. The results reported a specific infection approach used by E. vermicola to infect B. xylophilus and specialized fungal parasitic cells in PWN infection. In addition, the inoculated blastospores of E. vermicola germinated and grew inside of healthy pine xylem, although the growth rate was slow. Moreover, E. vermicola extended into the pine xylem following spray inoculation of wounded pine seedling stems, and a significant increase in fungal quantity was observed in response to B. xylophilus invasion. An accelerated extension of E. vermicola colonization was shown in PWN-infected wilting pine trees, due to the immigration of fungal-infected PWNs. Our results provide helpful knowledge about the extension rate of this fungus in healthy and wilting PWN-susceptible pine trees in the biological control of PWD and will contribute to the development of a management method for PWD control in the field.Author summaryPine wilt disease, caused by Bursaphelenchus xylophilus, has infected most pine forests in Asian and European forests and led to enormous losses of forest ecosystem and economy. Esteya vermicola is a bio-control fungus against pinewood nematode, showed excellent control efficient to pine wilt disease in both of greenhouse experiments and field tests. Although this bio-control agent was well known for the management of pine wilt disease, the infection mechanism of fungal infection and colonization of host pine tree are less understand. Here, we use GFP-tagged mutant to investigate the fungal infection to pinewood nematode; additionally, the temporal and spatial dynamics of E. vermicola colonize to pine tree were determined by the TaqMan real-time PCR quantification, as well as the response to pinewood nematode invasion. We found a specific infection approach used by E. vermicola to infect B. xylophilus and specialized fungal parasitic cells in PWN infection. In addition, the fungal germination and extension inside of pine tree xylem after inoculation were revealed. In addition, the quantity of E. vermicola increased as response to pinewood nematode invasion was reported. Our study provides two novel technologies for the visualization and detection of E. vermicola for the future investigations of fungal colonization and its parasitism against pinewood nematode, and the mechanisms of the bio-control process.

scholarly journals Assessment of the PCR technique for identification of Bursaphelenchus mucronatus Mamiya & Enda 1979, B. xylophilus Steiner & Buhrer 1934 (Nickle 1970) and B. fraudulentus Rühm 1956 (Nematoda, Aphelenchoididae) in crude extract of nematodes isolated from wood

2021 ◽  
Vol 61 (4) ◽  
pp. 346-351
Keyword(s):  
Pine Wilt Disease ◽  
Bursaphelenchus Xylophilus ◽  
Wilt Disease ◽  
Coniferous Forests ◽  
Pine Wood Nematode ◽  
Direct Examination ◽  
Pine Wood ◽  
Pine Wilt ◽  
Detection And Identification ◽  
Pine Trees

The pine wood nematode, Bursaphelenchus xylophilus Steiner & Buhrer 1934 (Nickle 1970) is the major causative agent of the pine wilt disease which has become devastating to Asian and European coniferous forests. These regions are also naturally occupied by two other native but nonpathogenic species, i.e. B. mucronatus Mamiya & Enda 1979 and B. fraudulentus Rühm 1956 which are closely related to the invasive B. xylophilus. Moreover, all these three species can colonize pine trees, and potentially be extracted from the same wood samples. Due to the cosmopolitan character and wide genetic variation within- and between existing populations the taxonomic distinction of these species based exclusively on their morphology is difficult or, almost impossible. The present quarantine regulations related to B. xylophilus require the most credible and simple methods which could allow for a possibly earliest detection and precise identification of this species in wood shipments and conifer forests stands. The main objectives of the presently reported research were to simplify the presently available procedures for possibly fast and precise detection and identification of B. xylophilus examined in the background of the remaining Bursaphelenchus species of the xylophilus group and other bacterio- and mycetophagous nematodes naturally present in the pine wood samples. The developed method is based on a direct examination of the crude nematode extract from wood samples and subsequent use of PCR technique with earlier designed specific reaction starters amplifying ITS1–28S rDNA regions.

First record of the genus Bursaphelenchus Fuchs, 1937 in Thailand and description of B. thailandae sp. n. (Nematoda: Parasitaphelenchidae)

Nematology ◽  
2002 ◽  
Vol 4 (7) ◽  
pp. 853-863 ◽  
Author(s):  
Helen Braasch ◽  
Rainulf Braasch-Bidasak
Keyword(s):  
Pine Wilt Disease ◽  
First Record ◽  
Wilt Disease ◽  
The Other ◽  
Mountainous Region ◽  
Morphometric Data ◽  
Lateral Field ◽  
Pine Wilt ◽  
Pine Trees ◽  
Phytosanitary Measures

AbstractWood samples were taken from pine trees in the mountainous region between Pai and Maehongson in northern Thailand. Four species of Bursaphelenchus were recovered from the samples: Bursaphelenchus hylobianum, B. mucronatus, B. aberrans and B. thailandae sp. n. Bursaphelenchus thailandae sp. n. is most similar to B. sychnus but also shows similarities with B. ruehmi, B. hunanensis and B. steineri. It has a relatively small stylet lacking distinct basal knobs and a lateral field with four lines. The female has more or less protruding vulval lips and a slim, conoid, tail. The relatively small and delicate spicules show a distinctive darker sector and lack a cucullus. The male tail has a very small terminal 'bursa'. Bursaphelenchus thailandae sp. n. is tentatively included in the B. fungivorus -group of the genus Bursaphelenchus. Brief notes and morphometric data are given for the other species found. The record of B. mucronatus indicates that conditions for the establishment of the closely related B. xylophilus (the cause of pine wilt disease) may be suitable in Thailand and strict phytosanitary measures are therefore advisable.

scholarly journals Dispersal Patterns of Pine Wilt Disease in the Early Stage of Its Invasion in South Korea

Forests ◽  
2017 ◽  
Vol 8 (11) ◽  
pp. 411 ◽  
Author(s):  
Won Il Choi ◽  
Hye Jung Song ◽  
Dong Soo Kim ◽  
Dae-Sung Lee ◽  
Cha-Young Lee ◽  
...  
Keyword(s):  
South Korea ◽  
Early Stage ◽  
Pine Wilt Disease ◽  
Wilt Disease ◽  
Dispersal Patterns ◽  
Pine Wilt

scholarly journals Three-Dimensional Convolutional Neural Network Model for Early Detection of Pine Wilt Disease Using UAV-Based Hyperspectral Images

2021 ◽  
Vol 13 (20) ◽  
pp. 4065
Author(s):  
Run Yu ◽  
Youqing Luo ◽  
Haonan Li ◽  
Liyuan Yang ◽  
Huaguo Huang ◽  
...  
Keyword(s):  
Neural Network ◽  
Early Detection ◽  
Convolutional Neural Network ◽  
Three Dimensional ◽  
Pine Wilt Disease ◽  
Wilt Disease ◽  
Hyperspectral Images ◽  
Pine Wilt ◽  
Pine Trees ◽  
3D Cnn

As one of the most devastating disasters to pine forests, pine wilt disease (PWD) has caused tremendous ecological and economic losses in China. An effective way to prevent large-scale PWD outbreaks is to detect and remove the damaged pine trees at the early stage of PWD infection. However, early infected pine trees do not show obvious changes in morphology or color in the visible wavelength range, making early detection of PWD tricky. Unmanned aerial vehicle (UAV)-based hyperspectral imagery (HI) has great potential for early detection of PWD. However, the commonly used methods, such as the two-dimensional convolutional neural network (2D-CNN), fail to simultaneously extract and fully utilize the spatial and spectral information, whereas the three-dimensional convolutional neural network (3D-CNN) is able to collect this information from raw hyperspectral data. In this paper, we applied the residual block to 3D-CNN and constructed a 3D-Res CNN model, the performance of which was then compared with that of 3D-CNN, 2D-CNN, and 2D-Res CNN in identifying PWD-infected pine trees from the hyperspectral images. The 3D-Res CNN model outperformed the other models, achieving an overall accuracy (OA) of 88.11% and an accuracy of 72.86% for detecting early infected pine trees (EIPs). Using only 20% of the training samples, the OA and EIP accuracy of 3D-Res CNN can still achieve 81.06% and 51.97%, which is superior to the state-of-the-art method in the early detection of PWD based on hyperspectral images. Collectively, 3D-Res CNN was more accurate and effective in early detection of PWD. In conclusion, 3D-Res CNN is proposed for early detection of PWD in this paper, making the prediction and control of PWD more accurate and effective. This model can also be applied to detect pine trees damaged by other diseases or insect pests in the forest.

Sign in / Sign up

Export Citation Format

Share Document