16AGRITECHCAT5: Feasibility of a Hyper Spectral Crop Camera (HCC) for agriculture optimisation

Abstract

Low cost Hyperspectral Crop Camera (HCC). A consortium from a broad range of disciplines have come together to develop a revolutionary low cost crop camera that could potentially allow farmers to improve crop yield, use less fertiliser, use less pesticide and spot pests and diseases earlier. The project will be led and coordinated by Wideblue Limited - a developer and manufacturer of specialist cameras. The project will also call on the skills of the the James Hutton Institutes expertise in crop nutrition and monitoring, the University of Strathclyde's Hyperspectral Imaging Centre, the University of the West of Scotland's Institute of Thin Films, Sensors and Imaging and Galloway & MacLeod's intelligent agriculture division.

Summary

Farmers and horticulturists face varying difficulties that require experience and knowledge of
their fields and crops, gained over many years. These difficulties include, but are not limited
to: uneven growth/yield of their fields; inexact and estimated fertiliser application; uneven
irrigation and local variations in pests/diseases/weeds. Additionally, the optimum harvest
timing is still speculated and often inexact. Faced with numerous variables, farmers cannot
avoid high variations in costs and crop yields from year to year. Tools to assist farmers to
optimise e.g. fertiliser & water applications or early detection of disease will provide a useful
diagnostic and management capability for optimum control of crop growth. Currently,
solutions for these challenges do exist, however, current systems are large, heavy, not
portable and as such are not readily deployable. They are also prohibitively expensive -
typically £10,000 - £150,000 each - and are generally only suitable for use in airborne or
satellite imaging applications or laboratory analysis. In effect, the current solutions available
for the aforementioned agricultural challenges are limited to large scale farming and/ or high
value crops. In these expensive systems, a spectrometer scan or image of the crop is taken at
visible and/or infrared wavelengths with analysis showing spectral image signature changes
relating to crop growth conditions. The signatures of interest varies from plant to plant and
from cause to cause. The "colour" of a crop (visible and IR) also changes as it approaches
maturity, with spectrometer scans providing scientific information for informed management
decisions in relation to crop hydration, fertiliser application, disease progression and
harvesting. Hyperspectral Imaging (HSI) can capture these changes: HSI systems capture a
large number of images of the scene, each at a different wavelength within some range
determined by the sensor technology, to produce a so called hyperspetral data cube in which
each pixel in the spatial domain contains a spectral profile of the object observed. For our
application, this spectral information can be analysed to make decisions about the
diagnostics/management of challenges in maximising crop yield. The proposed
Hyperspectral Crop Camera (HCC) will be: low-cost, compact & portable, simple in
operation and robust. A camera housing will contain the, sensor, battery and electronics to
produce one small simple lightweight device. This device would be suitable for handheld use
or potentially mountable in a low cost drone for local airborne analysis. HSI technology in
farming and agriculture which can cost anything from £10k - £150k. Application of HCC can
allow a farmer and/ or agriculturists to: - Save water by providing optimised or localised
irrigation - Timely identify areas of pests/diseases/weeds for early intervention - Optimise
use of fertiliser - Determine optimum harvest time and help increase crop yield - Improve
evenness of crop yield across field area - Reduced man hours, manually surveying fields etc -
Reduce need for technical agronomy training/knowledge

Farmers face varying difficulties that require vast experience and knowledge gained over years in the field. These difficulties include, but are not limited to: uneven growth/yield of their fields; inexact and estimated fertiliser application; uneven irrigation, local variations in pests/diseases/weeds, and speculative optimum harvest time.
To solve these challenges, spectrometer scans/images of the crop, are taken at visible and/or IR wavelengths, showing spectral profiles containing information on crop growth and hydration, fertiliser application, disease detection and harvesting. These information are extracted through analysis of spectral signature changes. This requires a very powerful spectrometer and the current spectral imaging systems are cumbersome, not readily deployable and very expensive - typically £10,000 - £150,000 each - and generally only suitable for use in airborne or satellite imaging applications or laboratory analysis.
The proposed Hyperspectral Crop Camera (HCC) will provide a cheaper alternative by replacing the expensive spectrometer through Hyperspectral Imaging (HSI): a camera housing containing the optics (a novel LVF`s developed and fabricated in the UK, off the shelf CMOS / IR sensors, off the shelf optics), filter, sensor, battery and electronics to produce a small simple lightweight device. A library of established crop information will also be included in HCC software: data showing spectral "signature" data for plant stress responses to nutrient deficiency, over/under use of irrigation, pests, diseases etc. The new system will be low-cost, robust, compact, portable and simple to operate; and would be suitable for handheld use or potentially mountable in a drone for local airborne analysis.
Upon success, estimated cost of manufacture of such a camera is £200 in batches of 10,000 - 50,000 each commanding a purchase price of £500 - vastly reducing costs.

The main beneficiaries of the proposed research will be the agricultural industry and environmental research, with a wider range of potential beneficiaries who will discover ways to apply the outputs of the work. The design and operation of this system will be targeted at agricultural systems, and will be tested using agricultural field trials for its ability to detect disease, drought symptoms and nutritional deficiencies in crops. For the agricultural industry, detection of disease and other problems with crop condition often occurs when it is too late to resolve the situation, usually with the resulting loss of all or a major part of the crop. A portable, hand-held and robust monitoring device capable of detection of specific crop problems would enable much more rapid detection, with associated economic savings for the grower. For academics research, the proposed work would provide a tool to allow much more detailed and rapid crop monitoring than before as part of experiments, and also to monitor vegetation condition in the field for ecological surveys. The overall impact of the proposed work will be felt through improved agricultural productivity and food security through the rapid detection of disease and monitoring of crop conditions, and will enable researchers to improve their experimental data capture. Both of these aspects will result in more resilient agricultural systems.
BBSRC Reference: