Hema S.N. Duddu

Hema S.N. Duddu

Auto-generated profile, based on publicly available information

Hema S.N. Duddu

Agriculture and Agri‐Food Canada 107 Science Place Saskatoon SK Canada

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2022 in The Plant Phenome Journal
Verified
Journal Article
Open access
Thuan HaThuan Ha
Thuan Ha
HDHema Duddu
Hema Duddu
Albert VandenbergAlbert Vandenberg
Albert Vandenberg
SSSteve Shirtliffe
Steve Shirtliffe
Advances in high‐throughput platforms such as UAVs (unoccupied aerial vehicles) facilitate rapid image‐based phenotypic data acquisition. However, existing plot‐level data extraction methods are unreliable if field plots differ in size and spacing, as often occurs in early‐generation plant breeding trials. To overcome the limitations of conventional plot extraction techniques, a combinational approach with both field‐map information and image classification techniques can be used to optimize plot extraction. The objective of this study was to develop a plot boundary extraction workflow for irregularly sized and spaced field plots from UAV imagery using plot spacing data and vegetation index‐based classifiers. An herbicide screening experiment consisting of three replications of 780 lentil (Lens culinaris Medik.) populations was foliar sprayed with saflufenacil. Aerial image acquisition was conducted during the peak vegetation stage using a RedEdge multispectral camera. A semi‐automatic workflow was compiled in eCognition software to extract lentil plot boundaries. Normalized difference vegetation index (NDVI) was calculated to locate the plots with vegetation and those with low NDVI or no vegetation, and pixel resizing based on plot size and orientation was used to draw the plot boundary. The extraction results showed a precise estimation of plot boundary for all the plots with a wide range of herbicide damage, including the plots with complete loss of vegetation. By using a simple convolutional filter (line filter), image thresholding, and pixel resizing, this approach avoided the use of complex algorithm‐based methodologies. Results suggest that this workflow can be extended to a wide range of phenotyping studies.

1 September 2019
Verified
Conference Paper
Closed access
Keshav D SinghKeshav D Singh
Keshav D Singh
SSSteve J. Shirtliffe
Steve J. Shirtliffe
HDHema S.N. Duddu
Hema S.N. Duddu
The UAV-based hyperspectral imaging (HSI) has been extensively used in various agriculture applications. The data calibration and pre-processing techniques have been widely studied in the remote sensing research. However, it was ignored that the most important factor affecting the results accuracy is the quality of the spectral data. To acquire such high spectral quality, the bi-directional reflection should be optimally adjusted during the data processing according to radiative transfer equation (RTE) based Hapke’s model. In this study, we quantitatively analyzed the relationship of bi-directional reflectance (BRDF) correction on two crop (Canola and Wheat) varieties in the context of hyperspectral data robustness. The simulated dataset based on the radiative transfer parameters are used to evaluate the influence of source-sensor geometry, light illumination, and scattering on data quality and it’s ability on data correction using proposed spectral similarity measures (SID-SAM score). The RTE-based BRDF optimization method (Hapke model) is proposed for improving the hyperspectral data quality after comparing with the uncorrected datasets. Simulated results shows that the optimization have significantly improved the data quality and increased the signal accuracy. Hence, the bi-directional reflectance correction would definitely have advantages on the hyperspectral data analysis to improve classification results.