Ground-based Hyperspectral Imaging Research Articles

Hybrid Segmentation – Artificial Neural Network Classification of High Resolution Hyperspectral Imagery for Site-Specific Herbicide Management in Agriculture

Site-Specific Herbicide Management (SSHM) in Precision Agriculture (PA) requires weed detection in crop fields for directed herbicide application instead of spraying entire fields. This has significant economic and environmental advantages for improved agricultural practices that are essential given forecast increases in global population and food production needs. In this study, a new hybrid segmentation - Artificial Neural Network (HS-ANN) method was compared to standard Maximum Likelihood Classification (MLC) for improving crop/weed species discrimination in SSHM/PA. Very high spatial resolution (1.25 mm) ground-based hyperspectral image data were acquired over field plots of canola, pea, and wheat crops seeded with two weed species (redroot pigweed, wild oat) in southern Alberta, Canada. The very high spatial and spectral resolution image data required development of a simple yet efficient vegetation index (Modified Chlorophyll Absorption in Reflectance Index (MCARI)) threshold segmentation to separate vegetation from soil for classification. The HSANN consistently outperformed MLC in both single date and multi-temporal classifications. Higher class accuracies were obtained with multi-temporally trained ANNs (84 to 92 percent overall), with improvements up to 31 percent over MLC. With advancements in imaging technology and computer processing speed, this HS-ANN method may constitute a viable farm option for real-time detection and mapping of weed species for SSHM in agriculture.

A ground-based hyperspectral imaging system for characterizing vegetation spectral features

A cropping system is usually characterized by continuous spatio-temporal vegetation variability. Vegetation variability can be detected by changes in several vegetation parameters defined according to purpose. Estimation of these vegetation parameters has been made possible by calculating various vegetation indices (VIs), usually by ratioing, differencing, ratioing differences and sums, or by forming linear combinations of spectral band data. Spectrometers or sensors have been used to acquire visible and infrared spectral properties of vegetation. This paper presents a ground-based hyperspectral imaging system for characterizing vegetation spectral features. The hyperspectral sensor used was a ground-based line sensor, ImSpector (V10-12-102), with a nominal spectral resolution of 1.5–2 nm and a wavelength range of 360–1010 nm. A graphical user interface (GUI) was developed in a MATLAB environment to aid in processing and analysis of acquired multidimensional spectral image data. Issues that arise when applying the imaging system to a particular field include acquiring hyperspectral images, selecting appropriate vegetation features or VIs, and quantifying the selected vegetation features or indices with the GUI developed. Vegetation features extracted by the proposed imaging system contribute not only to monitoring vegetation variability in crop systems, but also provide a potential source of relevant variables that can be used to estimate various vegetation parameters. A study that was set up to investigate the alternate bearing phenomenon of citrus trees illustrates the basic elements of the proposed approach.