Research Progress on the Early Monitoring of Pine Wilt Disease Using Hyperspectral Techniques

Wu, Wei; Zhang, Zhenbang; Zheng, Longjiang; Han, Chongyang; Wang, Xiaoming; Xu, Jian; Wang, Xinrong

doi:10.3390/s20133729

Cited by 42 publications

(20 citation statements)

References 94 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…All these results clearly show the practicability of PWD detection by spectral imaging and non-imaging, as further confirmed by the extensive review by Wu et al (2020).…”

Section: Pine Wilt Diseasesupporting

confidence: 71%

See 1 more Smart Citation

Spectroscopic detection of forest diseases: a review (1970–2020)

Cotrozzi

2021

J. For. Res.

View full text Add to dashboard Cite

Sustainable forest management is essential to confront the detrimental impacts of diseases on forest ecosystems. This review highlights the potential of vegetation spectroscopy in improving the feasibility of assessing forest disturbances induced by diseases in a timely and cost-effective manner. The basic concepts of vegetation spectroscopy and its application in phytopathology are first outlined then the literature on the topic is discussed. Using several optical sensors from leaf to landscape-level, a number of forest diseases characterized by variable pathogenic processes have been detected, identified and quantified in many country sites worldwide. Overall, these reviewed studies have pointed out the green and red regions of the visible spectrum, the red-edge and the early near-infrared as the spectral regions most sensitive to the disease development as they are mostly related to chlorophyll changes and symptom development. Late disease conditions particularly affect the shortwave-infrared region, mostly related to water content. This review also highlights some major issues to be addressed such as the need to explore other major forest diseases and geographic areas, to further develop hyperspectral sensors for early detection and discrimination of forest disturbances, to improve devices for remote sensing, to implement long-term monitoring, and to advance algorithms for exploitation of spectral data. Achieving of these goals will enhance the capability of vegetation spectroscopy in early detection of forest stress and in managing forest diseases.

show abstract

“…All these results clearly show the practicability of PWD detection by spectral imaging and non-imaging, as further confirmed by the extensive review by Wu et al (2020).…”

Section: Pine Wilt Diseasesupporting

confidence: 71%

“…Trees affected by PWD cease resin secretion and needles gradually become yellowish. Finally, the needles turn brown and the plant dies (Wu et al 2020).…”

Section: Pine Wilt Diseasementioning

confidence: 99%

Spectroscopic detection of forest diseases: a review (1970–2020)

Cotrozzi

2021

J. For. Res.

View full text Add to dashboard Cite

show abstract

“…Após avaliação in loco, ortomosaico gerado a partir de imagens RGB e análise dos dados hiperespectrais, os resultados indicam que a distribuição das arvores sintomáticas foi a mesma nas três metodologias, porém mais fácil de se atingir, e com maior acurácia, com o sensoriamento hiperespectral (QIN et al, 2016). Em uma revisão mais recente sobre este mesmo assunto, são abordadas ainda outras maneiras de se adquirir e de se processar esses dados, por exemplo, com sensores acoplados a RPAs (WU et al, 2020).…”

Section: Sensores Hiperespectraisunclassified

Monitoramento Fitossanitário Utilizando Sensoriamento Remoto: Avanços e Desafios

Barros

Rosalen²,

Filho

et al. 2021

Rev. Bras. Cartogr.

View full text Add to dashboard Cite

Problemas fitossanitários, como doenças, pragas e plantas daninhas, que competem com as plantas cultivadas por recursos e, consequentemente, prejudicam seu pleno desenvolvimento, são responsáveis por perdas significativas no setor agrícola, ano após ano. Portanto, conhecer o status sanitário da lavoura é um fator crucial no planejamento de ações de manejo, além de embasar políticas públicas de investimento e de proteção, a serem adotadas, com o objetivo de prevenir perdas produtivas e de assegurar a segurança alimentar da nação. Quando expostas a esses problemas, as plantas ativam respostas de defesa, cujos mecanismos moleculares são muito complexos. Nos estágios iniciais de um ataque de pragas ou de uma doença, embora os sintomas ainda não sejam visíveis no dossel, as plantas reagem com diferentes mecanismos fisiológicos, tais como a redução da taxa de fotossíntese, que induz a um aumento da fluorescência e da emissão de calor. Dessa forma, plantas estressadas produzem uma assinatura espectral que difere da assinatura de uma planta saudável. Dentro do Sensoriamento Remoto, inúmeras pesquisas têm estudado a relação entre diferentes problemas fitossanitários com a resposta espectral registrada em sensores multi ou hiperespectrais (sejam imageadores ou não imageadores, ativos ou passivos e embarcados em plataformas terrestres, aéreas ou orbitais). Nesse contexto, o objetivo desta revisão é descrever o estado da arte da tecnologia de Sensoriamento Remoto aplicada a aspectos fitossanitários de lavouras, nos níveis de coleta de dados terrestre, aéreo e orbital, envolvendo diferentes modalidades de sensores.

show abstract

“…Research on early identification or warning of PWD has been mainly focused on selecting the characteristic spectrum band, which is the band sensitive to PWD [10,11]. Although many studies have attempted to determine effective selection using ground high-spectral cameras or spectrometers, the complexity of the PWD spread still hinders early warning [12].…”

Section: Introductionmentioning

confidence: 99%

Evaluation of Deep Learning Segmentation Models for Detection of Pine Wilt Disease in Unmanned Aerial Vehicle Images

et al. 2021

View full text Add to dashboard Cite

Pine wilt disease (PWD) is a serious threat to pine forests. Combining unmanned aerial vehicle (UAV) images and deep learning (DL) techniques to identify infected pines is the most efficient method to determine the potential spread of PWD over a large area. In particular, image segmentation using DL obtains the detailed shape and size of infected pines to assess the disease’s degree of damage. However, the performance of such segmentation models has not been thoroughly studied. We used a fixed-wing UAV to collect images from a pine forest in Laoshan, Qingdao, China, and conducted a ground survey to collect samples of infected pines and construct prior knowledge to interpret the images. Then, training and test sets were annotated on selected images, and we obtained 2352 samples of infected pines annotated over different backgrounds. Finally, high-performance DL models (e.g., fully convolutional networks for semantic segmentation, DeepLabv3+, and PSPNet) were trained and evaluated. The results demonstrated that focal loss provided a higher accuracy and a finer boundary than Dice loss, with the average intersection over union (IoU) for all models increasing from 0.656 to 0.701. From the evaluated models, DeepLLabv3+ achieved the highest IoU and an F1 score of 0.720 and 0.832, respectively. Also, an atrous spatial pyramid pooling module encoded multiscale context information, and the encoder–decoder architecture recovered location/spatial information, being the best architecture for segmenting trees infected by the PWD. Furthermore, segmentation accuracy did not improve as the depth of the backbone network increased, and neither ResNet34 nor ResNet50 was the appropriate backbone for most segmentation models.

show abstract

Research Progress on the Early Monitoring of Pine Wilt Disease Using Hyperspectral Techniques

Cited by 42 publications

References 94 publications

Spectroscopic detection of forest diseases: a review (1970–2020)

Spectroscopic detection of forest diseases: a review (1970–2020)

Monitoramento Fitossanitário Utilizando Sensoriamento Remoto: Avanços e Desafios

Evaluation of Deep Learning Segmentation Models for Detection of Pine Wilt Disease in Unmanned Aerial Vehicle Images

Contact Info

Product

Resources

About