Dejan Seatovic

Centrifugal fertilizer spreaders are by far the most commonly used granular fertilizer spreader type in Europe. Their spread pattern however is error-prone, potentially leading to an undesired distribution of particles in the field and losses out of the field, which is often caused by poor calibration of the spreader for the specific fertilizer used. Due to the large environmental impact of fertilizer use, it is important to optimize the spreading process and minimize these errors. Spreader calibrations can be performed by using collection trays to determine the (field) spread pattern, but this is very time-consuming and expensive for the farmer and hence not common practice. Therefore, we developed an innovative multi-camera system to predict the spread pattern in a fast and accurate way, independent of the spreader configuration. Using high-speed stereovision, ejection parameters of particles leaving the spreader vanes were determined relative to a coordinate system associated with the spreader. The landing positions and subsequent spread patterns were determined using a ballistic model incorporating the effect of tractor motion and wind. Experiments were conducted with a commercial spreader and showed a high repeatability. The results were transformed to one spatial dimension to enable comparison with transverse spread patterns determined in the field and showed similar results.

This paper considers theoretical prerequisites for a sensor or sensor system that provides data for reliable single plant detection. The goal of the paper is to close the gap between state of the art sensor technology and the theoretical “ideal” sensor to fulfill one and only purpose: providing single plant detection data in cluttered and disordered environments. Through analysis of artificial leaf forms, the paper determines expectations of the sensor spatial resolution and its maximum noise level, and is supported by the results of a theoretical primer on predefined (artificial) shape analysis. Each shape is analyzed by elliptic Fourier descriptor invariants obtained from the shape boundary, which allow translation, rotation and scale invariant of each object. This paper analyzes the statistical significance of each descriptor and its separability from other features. Finally an approximation formula developed here can be used to compute required resolution of such sensor for the plant detection.