A peduncle detection method of tomato for autonomous harvesting

For automating the harvesting of bunches of tomatoes in a greenhouse, the end-effector needs to reach the exact cutting point and adaptively adjust the pose of peduncles. In this paper, a method is proposed for peduncle cutting point localization and pose estimation. Images captured in real time at a fixed long-distance are detected using the YOLOv4-Tiny detector with a precision of 92.7% and a detection speed of 0.0091 s per frame, then the YOLACT + + Network with mAP of 73.1 and a time speed of 0.109 s per frame is used to segment the close-up distance. The segmented peduncle mask is fitted to the curve using least squares and three key points on the curve are found. Finally, a geometric model is established to estimate the pose of the peduncle with an average error of 4.98 degrees in yaw angle and 4.75 degrees in pitch angle over the 30 sets of tests.

Automated summary

In this paper, a method is proposed for automated harvesting of greenhouse tomato bunches by localizing the cut points and estimating the poses of peduncles with high accuracy. The process involves real-time image detection using YOLOv4-Tiny, segmenting with YOLACT++, fitting the peduncle mask to a curve, and establishing a geometric model for pose estimation. The average errors of yaw and pitch angles in tests were 4.98 degrees and 4.75 degrees, respectively.