Pre-harvest Sugarcane Yield Estimation Using UAV-Based RGB Images and Ground Observation

Som-ard, Jaturong; Hossain, Mohammad Dalower; Ninsawat, Sarawut; Veerachitt, Vorraveerukorn

doi:10.1007/s12355-018-0601-7

Cited by 42 publications

(21 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Recently, Som-ard et al (2018 ) reported a successful (more than 90% accuracy) forecasting model for pre-harvest sugarcane yield determination using UAV-acquired RGB color images coupled with ground information data. The high spatial resolution of the UAV image and the advanced image classification of object-based image analysis (OBIA) with a gray-level co-occurrence matrix demonstrated the significant potential for the prediction of sugarcane yield before harvest, which will be beneficial to sugarcane farmers and related industries.…”

Section: Introductionmentioning

confidence: 99%

Recent Advances in Sugarcane Genomics, Physiology, and Phenomics for Superior Agronomic Traits

et al. 2022

View full text Add to dashboard Cite

Advances in sugarcane breeding have contributed significantly to improvements in agronomic traits and crop yield. However, the growing global demand for sugar and biofuel in the context of climate change requires further improvements in cane and sugar yields. Attempts to achieve the desired rates of genetic gain in sugarcane by conventional breeding means are difficult as many agronomic traits are genetically complex and polygenic, with each gene exerting small effects. Unlike those of many other crops, the sugarcane genome is highly heterozygous due to its autopolyploid nature, which further hinders the development of a comprehensive genetic map. Despite these limitations, many superior agronomic traits/genes for higher cane yield, sugar production, and disease/pest resistance have been identified through the mapping of quantitative trait loci, genome-wide association studies, and transcriptome approaches. Improvements in traits controlled by one or two loci are relatively easy to achieve; however, this is not the case for traits governed by many genes. Many desirable phenotypic traits are controlled by quantitative trait nucleotides (QTNs) with small and variable effects. Assembling these desired QTNs by conventional breeding methods is time consuming and inefficient due to genetic drift. However, recent developments in genomics selection (GS) have allowed sugarcane researchers to select and accumulate desirable alleles imparting superior traits as GS is based on genomic estimated breeding values, which substantially increases the selection efficiency and genetic gain in sugarcane breeding programs. Next-generation sequencing techniques coupled with genome-editing technologies have provided new vistas in harnessing the sugarcane genome to look for desirable agronomic traits such as erect canopy, leaf angle, prolonged greening, high biomass, deep root system, and the non-flowering nature of the crop. Many desirable cane-yielding traits, such as single cane weight, numbers of tillers, numbers of millable canes, as well as cane quality traits, such as sucrose and sugar yield, have been explored using these recent biotechnological tools. This review will focus on the recent advances in sugarcane genomics related to genetic gain and the identification of favorable alleles for superior agronomic traits for further utilization in sugarcane breeding programs.

show abstract

Section: Introductionmentioning

confidence: 99%

Recent Advances in Sugarcane Genomics, Physiology, and Phenomics for Superior Agronomic Traits

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Moreover, owing to the use of high-resolution data with high spectral variety between pixels, which often results in oversampling, the approach of OBIA of clustering pixels into objects is more effective than that of the pixel-based method [57] in processing high-resolution images requiring terrace damage extraction. The recent studies have also proven that OBIA and UAV data can be successfully applied in many fields, such as building safety [58][59][60][61], crop production [62,63], landslide movement [64,65], and artificial terrace mapping [52,66].…”

Section: Introductionmentioning

confidence: 99%

OBIA-Based Extraction of Artificial Terrace Damages in the Loess Plateau of China from UAV Photogrammetry

Fang

Zhu

et al. 2021

IJGI

View full text Add to dashboard Cite

Terraces, which are typical artificial landforms found around world, are of great importance for agricultural production and soil and water conservation. However, due to the lack of maintenance, terrace damages often occur and affect the local flow process, which will influence soil erosion. Automatic high-accuracy mapping of terrace damages is the basis of monitoring and related studies. Researchers have achieved artificial terrace damage mapping mainly via manual field investigation, but an automatic method is still lacking. In this study, given the success of high-resolution unmanned aerial vehicle (UAV) photogrammetry and object-based image analysis (OBIA) for image processing tasks, an integrated framework based on OBIA and UAV photogrammetry is proposed for terrace damage mapping. The Pujiawa terrace in the Loess Plateau of China was selected as the study area. Firstly, the segmentation process was optimised by considering the spectral features and the terrains and corresponding textures obtained from high-resolution images and digital surface models. The feature selection was implemented via correlation analysis, and the optimised segmentation parameter was achieved using the estimation of scale parameter algorithm. Then, a supervised k-nearest neighbourhood classifier was used to identify the terrace damages in the segmented objects, and additional geometric features at the object level were considered for classification. The comparison with the ground truth, as delineated by the image and field survey, showed that proposed classification can be adequately performed. The F-measures of extraction on three terrace damages were 92.07% (terrace sinkhole), 81.95% (ridge sinkhole), and 85.17% (collapse), and the Kappa coefficient was 85.34%. Finally, the potential application and spatial distribution of the terrace damages in this study were determined. We believe that this work can provide a credible framework for mapping terrace damages in the Loess Plateau of China.

show abstract

“…La estimación del rendimiento de algunos cultivos, así como el análisis de su variabilidad espacial y temporal, se puede realizar mediante el uso de diferentes herramientas geoespaciales, como por ejemplo, las imágenes satelitales, apoyadas en técnicas fotogramétricas (Shunling 2004, Marcos et al 2016, Som-ard et al 2018. Al utilizar esas herramientas se pretende facilitar el monitoreo espacial y temporal de las plantaciones para tener así, una respuesta rápida y oportuna, en procura de tomar las mejores decisiones (Oshunsanya y Aliku 2016).…”

Section: Introductionunclassified

Estimación de rendimiento en el cultivo de caña de azúcar (Saccharum officinarum) a partir de fotogrametría con vehículos aéreos no tripulados (VANT)

Montes

Henríquez

Rodríguez

et al. 2021

RAC

View full text Add to dashboard Cite

Introducción. La estimación previa de variables de rendimiento en plantaciones de caña de azúcar (Saccharum officinarum), es importante para adaptar prácticas de manejo y aumentar la competitividad en la agroindustria azucarera costarricense. Objetivo. El objetivo de este estudio fue realizar estimaciones de variables de rendimiento en el cultivo de la caña de azúcar, por medio de la integración de fotografías aéreas, métodos fotogramétricos y determinaciones de campo. Materiales y métodos. Se utilizó un lote de una hectárea de caña de azúcar, propiedad de la cooperativa CoopeCañita R.L. (Turrialba, Costa Rica), con 5 años de producción y sembrado con la variedad B76-256. La evolución espacio-temporal del crecimiento del cultivo se midió de mayo a noviembre del 2017, por medio de 6 vuelos con un VANT, el cual portaba una cámara fotográfica CoolPix A de 16,2 megapíxeles. Se realizó el procesamiento fotogramétrico y se obtuvieron los Modelos Digitales de Superficie (DSM). Estas variables permitieron estimar la altura y el volumen del cultivo. Las estimaciones se correlacionaron con diferentes variables de rendimiento como toneladas métricas de caña por hectárea (TMH), rendimiento de kilogramos de azúcar por tonelada (RKA), total de kilogramos de azúcar (TKA), total de kilogramos de miel (TKM) y rendimiento de kilogramos de miel (RKM) de la zafra 2017-2018. Resultados. La relación entre las TMH obtenidas en campo y las estimadas a partir del modelo de regresión lineal creado con la altura del cultivo fue de un R2 de 0,83. El error absoluto de la estimación de rendimiento, a partir de altura de planta, fue de 3,7 ton.ha-1, el error residual estándar de 6,3 ton.ha-1 y el RMSE de 5,63 ton.ha-1. Conclusión. Según los resultados, la mejor fecha para la estimación TMH fue aproximadamente 3 meses antes de cosecha. No se encontró relación entre las estimaciones fotogramétricas y la variable RKA.

show abstract

Pre-harvest Sugarcane Yield Estimation Using UAV-Based RGB Images and Ground Observation

Cited by 42 publications

References 40 publications

Recent Advances in Sugarcane Genomics, Physiology, and Phenomics for Superior Agronomic Traits

Recent Advances in Sugarcane Genomics, Physiology, and Phenomics for Superior Agronomic Traits

OBIA-Based Extraction of Artificial Terrace Damages in the Loess Plateau of China from UAV Photogrammetry

Estimación de rendimiento en el cultivo de caña de azúcar (Saccharum officinarum) a partir de fotogrametría con vehículos aéreos no tripulados (VANT)

Contact Info

Product

Resources

About