If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

Real-time Corn Grain Measurement Device Using Stereo Vision

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan www.asabe.org

Citation:  2019 ASABE Annual International Meeting  1900422.(doi:10.13031/aim.201900422)
Authors:   Matthew Benjamin Rogers, Robert Clark Stevens
Keywords:   Computer vision, grain filling, ROS, stereo camera, stereo vision.

Abstract. A real-time grain volume and grain depth level measuring device is developed for corn grain flowing into a plastic tote. Additionally, the vision system detects when the tote is in the correct position for grain filling using color targets that were placed on the tote. A Carnegie Robotics Multisense S21 stereo camera is the primary instrument used to measure the grain flow. Robot Operating System, Python with OpenCV, and Ubuntu were the primary software packages that were utilized. Dry corn grain was poured via an electric auger, with the stereo camera measurement device continuously operating and displaying real-time volume and depth measurements on a computer screen. The volume and grain level measurement systems were tested and showed promising results, with depth being accurate within an inch when the target depth is .18 meters. However, the volume algorithm can be improved as shown by a 39% difference between target volume and measured volume when filling a volume of .021 cubic meters. Grain volume and depth measurement methods from this paper can be applied to other areas, such as anything that requires a specific amount of grain volume poured into it.

(Download PDF)    (Export to EndNotes)