JOURNAL of the JAPANESE SOCIETY of AGRICULTURAL MACHINERY

Show abstractHide abstract

An intelligent agricultural worker assistance system that can track worker positions and behavior patterns and comprehend workflow presents a potential method of facilitating workload reduction and improving work efficiency. In this study, we developed an image processing system capable of simultaneously detecting both the position and posture of a worker on a route by combining a single pan-tilt-zoom camera, an original working uniform marked with four different red-blue combinative colors and two types of particle filters that permit detection of the color markers on the working uniform. In our experiments, we determined that the proposed system could detect the position of a worker that was walking, turning and moving his arms from standing and sitting postures on a monitored route in a field with a resolution of approximately 1 m and a sensing range of approximately 38 m. The system could also detect, with no exceptions, eight separate worker postures. The results of these experiments indicate that our developed system could be used for tracking worker positions and behavior patterns in real time.

View full abstract

Download PDF (10658K)

An autonomous rice combine harvester was developed utilizing a commercially available rice combine harvester, by integrating the ability to work autonomously using position and azimuth data from RTK-GPS and azimuth sensors, respectively. The autonomous rice combine harvester was equipped with unitized sensing devices and control actuators; while a CAN bus was used as the communication standard. In the test field (100 × 30 m), the accuracy of work on the ridge side and headland were RMS 0.04 m and RMS 0.08 m, respectively. The capacity of work was 18.7 ha/h; which included manned harvesting and discharging of harvested grain.

View full abstract

The purpose of this study was the elucidation of the growth characteristics of the potato. We simultaneously measured changes in stem diameter and growth of potato tuber.
We improved the old equipment that measures the perimeter of the tuber with the new equipment. A potentiometer was used to measure the changes in the diameter of the stem.
We continuously measured the relationship based on enlargement time, period, rate and volume of potato tuber and stem diameter change (information on the ground) by this system.

View full abstract

This study investigated the potential for autonomous harvesting of strawberries cultivated in a hanging-type elevated substrate.
Investigation of degree of overlap between inside and outside revealed that approximately 90% of mature fruits are located at the front and can be detected by an inside inspection. Harvesting tests were conducted using an inside-approach harvesting robot that can travel beneath a hanging bench and pick fruits on both sides using a single manipulator. The success rates for detecting and for picking were 68.7% and 50.6% for var. Benihoppe, and 75.0% and 63.0% for var. Amaotome. Our investigation of degree of overlap and harvesting tests demonstrated that the improved visibility of mature fruits from inside led to significantly enhanced picking performance.

View full abstract

Register with J-STAGE for free!