Estimation of Bacterial Pustule on Soybean Using Crane-Mounted Hyperspectral Sensor Data

Abstract

This paper investigates adequate selection of hyperspectral components for estimating the degree of soybean bacterial pustule infection. According to a filed report,the higher the disease damage level is,the less the yield is expected.Based on highresolution hyperspectral images for different levels of damaged soybean fields,we have investigated the relationship between the soybean weight averaged for 100 seeds and the hyperspectral changes.In order to estimate the degree of damages from the hyperspctral data,we have tested 3 methods:(i) Estimation using reflectance of a single band based on a linear regression analysis.The RMSE was 2.0g.(ii)Estimation using normalized vegetation indices also based on a linear regression analysis.The RMSE was 2.1g.(iii) Estimation using neural network(NN)of a single-layer perceptron which has input nodes corresponding to the hyperspectral bands and a single output node.The RMSE was 1.5g,for estimating 100 seeds weight ranged over 16.7g to 22.7g.This paper indicates that NN is the most accurate among three methods to estimate the degree of soybean bacterial pustule infection.

Continuous Monitoring of Visible and Near-Infrared Band Reflectance from a Rice Paddy for Determining Nitrogen Uptake Using Digital Cameras

“…Ground-based acquisition of spectral images may partly resolve the problem since it should simultaneously collect the spatial distribution of the widespread target. For relatively simple and cost-effective ground observations, a high spatial-and spectral-resolution imaging system using line sensors has been developed for intensive surveys (Kosaka et al, 2007), but it requires a crane for scanning above the targeted object. On the other hand, handy video cameras or digital cameras have been used for assessing crop leaf nitrogen and/or chlorophyll content (Nakatani and Kawashima, 1994;Kawashima and Nakatani, 1998;Matsuda et al, 2003;Jia et al, 2004;Ku et al, 2004;Casadesus et al, 2007;Takemine et al, 2007) and for analyzing plant cover or phenology of vegetation (Purcell, 2000;Zhou and Robson, 2001;Richardson et al, 2007;Ishihara et al, 2008).…”

Daytime and Nighttime Field Spectral Imagery of Ripening Paddy Rice for Determining Leaf Greenness and 1000-Grain Weight

“…They measured paddy fields in order to show the spectral responses from the panicles and leaves separately. Additionally, it has been found that disease and weather hazard damages on crops were detectable with these spectral images (Kosaka et al, 2007;Minekawa et al, 2007). Imaging spectrometry makes it possible to collect spectral information not only from the overall canopy but also from a part of an organ such as a panicle or even a spikelet.…”