Use of Unmanned Aerial Vehicle Imagery and Deep Learning UNet to Extract Rice Lodging

Zhao, Xin; Yuan, Yitong; Song, Mengdie; Ding, Yang; Lin, Fenfang; Liang, Dong; Zhang, Dongyan

doi:10.3390/s19183859

Cited by 110 publications

(54 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2009; Rango et al, 2006;Sankey et al, 2019;Zhao et al, 2019), whereas spaceborne and manned airborne images are too coarse in spatial resolution. This was particularly important in our study because the cottonwood trees were only 6 years old and represent small canopies <5 m in canopy diameter and height.…”

Section: Uav Thermal Remote Sensingmentioning

confidence: 99%

UAV thermal image detects genetic trait differences among populations and genotypes of Fremont cottonwood (Populus fremontii, Salicaceae)

Sankey

Blasini

Koepke

et al. 2020

Remote Sens Ecol Conserv

View full text Add to dashboard Cite

Many plants are becoming increasingly maladapted to their environments due to changing climate and environmental conditions. It is, therefore, important to quantitatively evaluate what species, populations, and genotypes will survive in projected climate change scenarios and the implications this can have for associated biodiversity. We evaluate unmanned aerial vehicle (UAV)‐based high‐resolution thermal images for differentiating populations and genotypes in Fremont cottonwood (Populus fremontii S. Wats.), a foundation tree species that supports high levels of biodiversity and associated processes in riparian ecosystems. Specifically, we compare UAV thermal image‐derived tree canopy temperatures among 16 different populations and 10 replicated genotypes within two of the populations of Fremont cottonwood trees sourced from a broad environmental gradient and growing together in a common garden in central Arizona, USA. The UAV image‐derived tree canopy temperatures ranged 30°C–42°C resulting in a high overall accuracy of 85% in tree canopy classification. Our results indicate that the UAV thermal image‐derived mean tree canopy temperatures were significantly different among most of the 16 populations (P < 0.001). Within a warm‐adapted Sonoran Desert population and a cooler High Plateau population, the UAV thermal image‐derived tree canopy temperatures were also significantly different among many genotypes (P < 0.001). Furthermore, the UAV thermal image‐derived tree canopy temperatures were significantly correlated with tree canopy cover (R2 = 0.73; P‐value < 0.001) and varied with locations across the garden. Our findings have important implications for characterizing intraspecific genetic diversity in long‐lived forest trees like Fremont cottonwood and inferences for understanding ecosystem processes and guiding restoration efforts. We suggest that UAV thermal images can be used to rapidly scale laboratory‐ and plot‐based genetics research up to the landscape level. Ecological restoration efforts informed by projected climate scenarios can benefit from the UAV‐based genetics findings to identify future climate‐adapted populations and genotypes for potential propagation sources.

show abstract

Section: Uav Thermal Remote Sensingmentioning

confidence: 99%

UAV thermal image detects genetic trait differences among populations and genotypes of Fremont cottonwood (Populus fremontii, Salicaceae)

Sankey

Blasini

Koepke

et al. 2020

Remote Sens Ecol Conserv

View full text Add to dashboard Cite

show abstract

“…The decoder part whereas recovers the image details with upsampling and short connections. Because of the high accuracy on large image segmentation, U-Net has been used in many remote sensing tasks [47][48].…”

Section: B Comparison With Other Methods On Change Detectionmentioning

confidence: 99%

Land Cover Change Detection With VHR Satellite Imagery Based on Multi-Scale SLIC-CNN and SCAE Features

2020

View full text Add to dashboard Cite

“…Using this method, plant height can be modelled and estimated by the principles of the structure from motion photogrammetry, where the difference between digital terrain model (DTM) and digital surface model (DSM) is the average height of plants within the plots [ 99 ]. Quantitative measurement of lodging can be derived from the differences between DSM before and after lodging events, which has been demonstrated in barley [ 131 ], wheat [ 132 ], and rice [ 133 ].…”

Section: Phenomic Characterization and Evaluation Of Genebank Accementioning

confidence: 99%

Genebank Phenomics: A Strategic Approach to Enhance Value and Utilization of Crop Germplasm

Nguyen

Norton

2020

Plants

View full text Add to dashboard Cite

Genetically diverse plant germplasm stored in ex-situ genebanks are excellent resources for breeding new high yielding and sustainable crop varieties to ensure future food security. Novel alleles have been discovered through routine genebank activities such as seed regeneration and characterization, with subsequent utilization providing significant genetic gains and improvements for the selection of favorable traits, including yield, biotic, and abiotic resistance. Although some genebanks have implemented cost-effective genotyping technologies through advances in DNA technology, the adoption of modern phenotyping is lagging. The introduction of advanced phenotyping technologies in recent decades has provided genebank scientists with time and cost-effective screening tools to obtain valuable phenotypic data for more traits on large germplasm collections during routine activities. The utilization of these phenotyping tools, coupled with high-throughput genotyping, will accelerate the use of genetic resources and fast-track the development of more resilient food crops for the future. In this review, we highlight current digital phenotyping methods that can capture traits during annual seed regeneration to enrich genebank phenotypic datasets. Next, we describe strategies for the collection and use of phenotypic data of specific traits for downstream research using high-throughput phenotyping technology. Finally, we examine the challenges and future perspectives of genebank phenomics.

show abstract

Use of Unmanned Aerial Vehicle Imagery and Deep Learning UNet to Extract Rice Lodging

Cited by 110 publications

References 27 publications

UAV thermal image detects genetic trait differences among populations and genotypes of Fremont cottonwood (Populus fremontii, Salicaceae)

UAV thermal image detects genetic trait differences among populations and genotypes of Fremont cottonwood (Populus fremontii, Salicaceae)

Land Cover Change Detection With VHR Satellite Imagery Based on Multi-Scale SLIC-CNN and SCAE Features

Genebank Phenomics: A Strategic Approach to Enhance Value and Utilization of Crop Germplasm

Contact Info

Product

Resources

About