Multi-Spectral Imaging for Weed Identification in Herbicides Testing

A new methodology to help to improve the efficiency of herbicide assessment is explained. It consists of an automatic tool to quantify the percentage of weeds and plants of interest (sunflowers) that are present in a given area. Images of the crop field taken from Sequoia camera were used. Firstly, the quality of the images of each band is improved. Later, the resulting multispectral images are classified into several classes (soil, sunflower and weed) through a novel algorithm implemented in e-Cognition software. Obtained results of the proposed classifications have been compared with two deep learning-based segmentation methods (U-Net and FPN).

Automated summary

A new methodology for improving herbicide assessment efficiency is presented, which involves an automatic tool to quantify the percentage of weeds and sunflowers in a given area. Images captured by the Sequoia camera are used, and the quality of each band's images is enhanced. The resulting multispectral images are then classified into soil, sunflower, and weed categories using a novel algorithm implemented in e-Cognition software. The classification results are compared with two deep learning-based segmentation methods (U-Net and FPN).