Pose Estimation of Sweet Pepper through Symmetry Axis Detection.

Qibing Zhu,Ya Guo,Jianwei Qin,Hao Li,Min Huang

doi:10.3390/s18093083

Qibing Zhu, Ya Guo + Show 3 more

Open Access

https://doi.org/10.3390/s18093083

Copy DOI

Abstract

The space pose of fruits is necessary for accurate detachment in automatic harvesting. This study presents a novel pose estimation method for sweet pepper detachment. In this method, the normal to the local plane at each point in the sweet-pepper point cloud was first calculated. The point cloud was separated by a number of candidate planes, and the scores of each plane were then separately calculated using the scoring strategy. The plane with the lowest score was selected as the symmetry plane of the point cloud. The symmetry axis could be finally calculated from the selected symmetry plane, and the pose of sweet pepper in the space was obtained using the symmetry axis. The performance of the proposed method was evaluated by simulated and sweet-pepper cloud dataset tests. In the simulated test, the average angle error between the calculated symmetry and real axes was approximately 6.5°. In the sweet-pepper cloud dataset test, the average error was approximately 7.4° when the peduncle was removed. When the peduncle of sweet pepper was complete, the average error was approximately 6.9°. These results suggested that the proposed method was suitable for pose estimation of sweet peppers and could be adjusted for use with other fruits and vegetables.

Highlights

Fruit harvesting is an important part of the entire production process of fruit farming
The point cloud was separated by u (u > 4, where u is an integer) candidate planes in the spherical coordinate system established with the centroid of the crop
Errors between true and calculated wherethe thecalculated point cloud is rendered in and two Errors between true and calculated symmetry axes, where thecamera point cloud is rendered in the white indicates the real symmetry axis

Summary

Introduction

Fruit harvesting is an important part of the entire production process of fruit farming. Prevalent harvesting methods are still based on high-cost, -intensity, and -risk manual harvesting, in which the labor force employed accounts for 33% to 50% of the total labor force [1]. A total of $21 million was used for personal injury compensation related to manual harvesting between 1996 and 2001 in the USA [3]. Automated harvesting systems must be developed to meet the increasing labor demand, to decrease human risks of injuries in orchards, and to decrease the harvesting cost by saving time, money, and energy to benefit producers and consumers [5]

Objectives

Methods

Results

Discussion

Conclusion