Detection of nitrogen stress on winter wheat by multispectral machine vision

Hand-held sensors (SPAD meter, N-Tester, …) used for detecting the leaves nitrogen concentration (Nc) present several drawbacks. The nitrogen concentration is gained by an indirect way through the chlorophyll concentration and the leaves have to be fixed in a defined position for the measurements. These drawbacks could be overcome by an imaging device that measures the canopy reflectance. Hence, the objective of the paper is to analyse the potential of multispectral imaging for detecting nitrogen concentration.
The tests were carried out on parcels submitted to nitrogen inputs varying from 0 to 180 kg N.ha-1. Reference Nc measurements were obtained by the Kjeldahl method and a Hydro N-Tester (Yara). The developed imaging system comprised a CMOS camera and a set of 22 interference filters ranging from 450 to 950 nm mounted on a wheel steered by a stepper motor. The image acquisition and the motor rotation were controlled by a program written in C++. The crop was imaged vertically at one meter height. The raw images presented 1280×1024 pixels covering an area of approximately 0.25 m² and were recorded with a 12-bit luminance resolution. To deal with the natural irradiance variability of the scene, a white reference was used and the integration time was automatically adjusted for each image. The image treatment included the segmentation of Photosynthetically Active Leaves (PAL) by using Bayes theorem and the computation of the mean PAL reflectance after correction of background and illumination fluctuations. Nc was estimated on the basis of the 22 filters by the Partial Least Square (PLS) method and by four filters selected by the Best Subset Selection (BSS) method.
In comparison with the Kjeldahl method, the estimation of Nc by means of the Hydro N-Tester, the PLS method and the BSS method (filters 600-80, 950-100, 650-40 and 450-80 nm) gave determination coefficients equal to 0.53, 0.63, and 0.62, respectively. This indicated that the full multi-spectral approach gave significantly better Nc estimation than a portable device and suggested that a camera equipped with four filters would give similar results.