Canopy height estimation using drone-based RGB images

Valluvan, Aravind Bharathi; Raj, Rahul; Pingale, Rohit; Adinarayana, J.

doi:10.1016/j.atech.2022.100145

Cited by 7 publications

(7 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While RGB sensors delivered quality data, integrating a hyperspectral sensor, as recommended by [34], might furnish a richer geometrical representation vital for enhanced crop detection. The CHM filtering process, pivotal in noise elimination during preprocessing, bolstered the accuracy of our canopy size delineation, aligning with improvements highlighted by [22] and [24]. The selection of a plant height threshold was crucial, requiring precision to avoid omitting vital features while achieving optimal results.…”

Section: Discussionmentioning

confidence: 84%

“…Alternative algorithms have also been explored, revealing ongoing challenges and advancements in agricultural image processing and plant detection [24][25][26][27][28][29]. The presence of noise elements like soil, background, and shadows presents additional challenges in canopy size delineation, prompting the exploration of machine learning algorithms for plant identification tasks [18,[30][31][32].…”

Section: Introductionmentioning

confidence: 99%

“…This research introduces an innovative method that leverages a Canopy Height Model (CHM) and a modified Voronoi diagram for efficient corn canopy detection and delineation, incorporating domain-specific knowledge to enhance accuracy and efficiency in agricultural monitoring and management [22,24]. This approach aims to build upon previous work by filtering out noise and precisely estimating individual corn crop peaks, using corn spectral data to discriminate individual crops from soil and shadows for effective canopy size estimation.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Detection of Individual Crop and Canopy Delineation from UAV Imagery

Dorbu,

Hashemi-Beni

2024

Preprint

View full text Add to dashboard Cite

Precise monitoring of individual crop growth and health status is crucial for precision agriculture practices. However, traditional manual inspection methods are time-consuming, labor-intensive, and often lack the spatial resolution required for detailed analysis. This research addresses the need for efficient and high-resolution crop monitoring by leveraging Unmanned Aerial Vehicle (UAV) imagery and advanced computational techniques. The primary objective was to develop a methodology for precise identification, extraction, and monitoring of individual corn crops throughout their growth cycle. This was achieved by integrating UAV-derived data with image processing, computational geometry, and machine learning techniques. UAV imagery was ac-quired bi-weekly at altitudes of 40m and 70m, capturing the entire growth cycle of a corn crop from planting to harvest. A time-series Canopy Height Model (CHM) was generated by analyzing the differences between the Digital Terrain Model (DTM) and the Digital Surface Model (DSM) derived from the UAV data. Local spatial analysis and image processing techniques were em-ployed to determine the local maximum height of each crop. Subsequently, a Voronoi data model was developed to delineate individual crop canopies, successfully identifying 13,000 out of 13,050 corn crops in the study area. For enhanced accuracy in canopy size delineation, vegetation indices were incorporated into the Voronoi model segmentation, refining the initial canopy area esti-mates by eliminating interference from soil and shadows. The proposed methodology enables precise estimation and monitoring of crop canopy size, height, biomass reduction, lodging, and stunted growth over time, providing valuable insights for precision agriculture practices. This work contributes to the scientific community by demonstrating the potential of integrating UAV technology, computational geometry, and machine learning for accurate and efficient crop mon-itoring at the individual plant level.

show abstract

Section: Discussionmentioning

confidence: 84%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Detection of Individual Crop and Canopy Delineation from UAV Imagery

Dorbu,

Hashemi-Beni

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…When compared with the actual cotton height of around 70-100 cm in the dataset we used, the error margin remains within an acceptable threshold. Moreover, a study by Valluvan et al [50] highlights that the traditional method's accuracy in determining crop height is impacted due to slope variations. Despite using a linear model for ground elevation adjustment, their reported RMSE error for maize crop height remains around 14.17 cm.…”

Section: Discussionmentioning

confidence: 99%

G-DMD: A Gated Recurrent Unit-Based Digital Elevation Model for Crop Height Measurement from Multispectral Drone Images

Wang,

Oishi,

Birch

et al. 2023

Machines

View full text Add to dashboard Cite

Crop height is a vital indicator of growth conditions. Traditional drone image-based crop height measurement methods primarily rely on calculating the difference between the Digital Elevation Model (DEM) and the Digital Terrain Model (DTM). The calculation often needs more ground information, which remains labour-intensive and time-consuming. Moreover, the variations of terrains can further compromise the reliability of these ground models. In response to these challenges, we introduce G-DMD, a novel method based on Gated Recurrent Units (GRUs) using DEM and multispectral drone images to calculate the crop height. Our method enables the model to recognize the relation between crop height, elevation, and growth stages, eliminating reliance on DTM and thereby mitigating the effects of varied terrains. We also introduce a data preparation process to handle the unique DEM and multispectral image. Upon evaluation using a cotton dataset, our G-DMD method demonstrates a notable increase in accuracy for both maximum and average cotton height measurements, achieving a 34% and 72% reduction in Root Mean Square Error (RMSE) when compared with the traditional method. Compared to other combinations of model inputs, using DEM and multispectral drone images together as inputs results in the lowest error for estimating maximum cotton height. This approach demonstrates the potential of integrating deep learning techniques with drone-based remote sensing to achieve a more accurate, labour-efficient, and streamlined crop height assessment across varied terrains.

show abstract

“…A series of different plant phenotyping studies have used colour analysis algorithms to calculate the proportion of green pixels in a given image to either determine plant canopy area or height e.g. (Starý et al 2020;Abutaleb et al 2021;Valluvan et al 2023), or to calculate the proportion of green pixels in a given image of plants e.g. (Liang et al 2017;Li et al 2021).…”

Section: Introductionmentioning

confidence: 99%

Green Index: a widely accessible method to quantify greenness of photosynthetic organisms

Signorelli,

Casaretto,

Millar

2023

Preprint

View full text Add to dashboard Cite

Plant phenotyping involves the quantitative determination of complex plant traits using image analysis. One important parameter is how green plant tissues appear to the observer, which is indicative of their health and developmental stage. Various formulas have been developed to quantify this by calculating leaf greenness scores. We have developed a revised formula called "Green Index" (GI) devised out of the need to quantitatively assess how the apparent greenness of seedlings changes during de-etiolation. The GI calculation is simple, uses widely available RGB values of pixels in images as input, and does not require commercial software platforms or advanced computational skills. In this study we describe the conception of the GI formula, compare it with other widely used greenness formulas, and test its wider application in plant phenotyping using the open source free software platform RawTherapee. We demonstrate the utility of the GI in addressing common issues encountered in assessing plant biology experiments, underscoring its potential as a reliable and accessible tool. Finally, we explore the correlation between GI and chlorophyll content, assess its reliance on different types of photography, and summarizes the key steps for its effective utilization.

show abstract

Canopy height estimation using drone-based RGB images

Cited by 7 publications

References 21 publications

Detection of Individual Crop and Canopy Delineation from UAV Imagery

Detection of Individual Crop and Canopy Delineation from UAV Imagery

G-DMD: A Gated Recurrent Unit-Based Digital Elevation Model for Crop Height Measurement from Multispectral Drone Images

Green Index: a widely accessible method to quantify greenness of photosynthetic organisms

Contact Info

Product

Resources

About