Imaging systems, specifically stereo rig, are lately being more widely used in several domains. Several steps are necessary in stereovision: camera calibration, image acquisition, image rectification, image matching and depth determination.

The main part of the stereo computing is the image matching. Image matching is the determination of the correspondence between pixels of the stereo right and left image. If the matching is accurate the depth calculation will be as well. However image matching is a very difficult task. Its accuracy depends on several factors such as image resolution, noises, texture …

In a previous work, we showed the feasibility of using stereovision to characterize of the fertilizer centrifugal spreading process and to control the spreading fertilizer distribution pattern on the ground. Fertilizer grains are similar and the grain images are poor according to texture aspect. Therefore the accuracy of stereo matching algorithm in literature can’t be used as a reference for a stereo images of fertilizer grain.

In order to evaluate stereo matching algorithm applied on grain images we present in this paper a generator of synthetic stereo particle images. Two main steps compose the particle stereo image generator: particle 3d position generator and virtual stereo rig. The particle 3d position generator uses a ballistic flight model and the disc characteristics to simulate the ejection and the displacement of grains. The virtual stereo rig simulates the stereo acquisition system and it generates stereo images, a disparity map and an occlusion map.

Evaluated matching algorithms are applied on the generated stereo images. The obtained results are compared with the disparity and occlusion map to calculate their accuracy.