Development of a 3D image acquisition system and image processing algorithms for the characterization of the ejection parameters of fertilizer granules

The characterization of the fertilizer centrifugal spreading has become an important agriculture scientific issue in order to help farmers having a higher fertilization precision hence higher production efficiency. The ejected fertilizer grains are comparable to projectiles; hence, by using a ballistic flight model, predicting the spread pattern on the ground relies on an estimation of the trajectories and velocities of ejected grains. To estimate those parameters two approaches were proposed. First a two-steps zero mean normalized cross-correlation based algorithm for motion estimation was used to determine the displacement of the grains in the 2D images. The efficiency of this algorithm was evaluated by the mean of a grain images’ simulator. The results showed a high accuracy with an error of less than 0.2 pixels for 90% of the estimated velocities. However, the vertical ejection angle cannot be determined. This limits the use of the technique to spreaders equipped with flat disks where the trajectories of the grains will mostly be in a horizontal plane. This restriction was handled by the second approach. It is based on a 3D stereovision imaging system. A region based stereo matching algorithm with uniqueness and ordering constraints was introduced. It was validated using a grains’ stereo images simulator. 90% of the disparities were estimated with errors less than 2 pixels (around 1%). Moreover a 3D motion estimation algorithm was developed. It is based on an improvement of the previous 2D motion estimation algorithm combined with the estimated 3D coordinates. The efficiency of the whole system was approved via a comparison of its results and a real distribution obtained from a developed cylindrical collector