White cap detection device
A device for analyzing a grain sample including a light source, an image sensor, and a controller. The light source is configured for illuminating the grain sample. The image sensor is configured for capturing images of the grain sample. The controller is coupled to the image sensor and is configured for receiving the images of the grain sample therefrom and for analyzing the images to detect at least one material other than grain in the grain sample. The light source is configured for illuminating the grain sample with a local light spot having a size that is smaller than a width of an average wheat kernel. The image analysis and the detection of material other than grain may, at least partly, be performed using trained neural networks and other artificial intelligence algorithms.
1. A device for analyzing a grain sample, the device comprising
a light source configured for illuminating the grain sample with a local light spot having a size that is smaller than a width of an average wheat kernel;
an image sensor configured for capturing at least one image of the grain sample illuminated by the local light spot having a size that is smaller than a width of an average wheat kernel, and
a controller coupled to the image sensor, the controller configured for:
receiving the at least one image of the grain sample illuminated by the local light spot having a size that is smaller than a width of an average wheat kernel from the image sensor; and
analyzing the at least one image to detect at least one material other than grain in the grain sample.
2. The device as claimed in claim 1 , wherein the local light spot has a diameter that is smaller than about 5 mm.
3. The device as claimed in claim 1 , wherein the light source comprises a laser source.
4. The device as claimed in claim 1 , wherein the light source is further configured for illuminating the grain sample with a plurality of local light spots having a size that is smaller than a width of an average wheat kernel.
5. The device as claimed in claim 4 , wherein the plurality of local light spots is arranged along an at least substantially straight line.
6. The device as claimed in claim 4 , wherein the plurality of local light spots is arranged in a grid pattern.
7. The device as claimed in claim 1 , wherein the light source is further configured for moving the local light spot relative to the grain sample.
8. The device as claimed in claim 1 , wherein the light source is further configured for illuminating the grain sample with a wide light spot having a size that is larger than multiple times a length of an average wheat kernel.
9. The device as claimed in claim 8 , wherein the wide light spot has a diameter of at least 5 cm.
10. A combine harvester comprising the device for analyzing a grain sample as claimed in claim 1 .
11. The combine harvester as claimed in claim 10 , further comprising a clean grain elevator for transporting cleaned grain towards a grain tank, the device for analyzing a grain sample being arranged to capture images of grain in the clean grain elevator or in a bypass section thereof.
12. A method for analyzing a grain sample using a device as claimed in claim 1 , the method comprising steps of:
using the light source to illuminate the grain sample with the local light spot,
using the image sensor for capturing the at least one image of the grain sample,
analyzing the at least one captured image to determine a reflection profile of the local light spot at the grain sample, and
detecting, based on the determined reflection profile, a material other than grain in the grain sample.
13. The method as claimed in claim 12 , further comprising classifying, based on the determined reflection, a type of material other than grain.
14. The method as claimed in claim 13 , wherein the type of material other than grain is empty chaff particle or white cap.
15. The method as claimed in claim 14 , further comprising using the light source to illuminate the grain sample with a wide light spot having a size that is larger than multiple times a length of an average wheat kernel.
16. The method as claimed in claim 15 , wherein trained neural networks or other artificial intelligence algorithms are used to detect the material other than grain in the grain sample.