期刊
COMPUTERS AND ELECTRONICS IN AGRICULTURE
卷 184, 期 -, 页码 -出版社
ELSEVIER SCI LTD
DOI: 10.1016/j.compag.2021.106107
关键词
Mask R-CNN; Fruit reconstruction; Branch reconstruction; RGB-D; Guava harvesting robot
资金
- Science and Technology Planning Project of Guangdong Province, China [2019A050510035]
- Key Field R&D Program Project of Guangdong Province, China [2019B020223003]
- Science and Technology Research Program of Chongqing Municipal Education Commission [KJQN201901308]
This study presents a method for obstacle avoidance path planning of robots through fruit and branch detection and three-dimensional reconstruction. The tiny Mask R-CNN is used to detect guava fruits and branches, which are then reconstructed using 3D spheres and 3D cylindrical segments. The results show effective reconstruction of fruits and branches for planning obstacle avoidance paths for harvesting robots.
In unstructured environments, harvesting robots may collide with disorderly growing branches, thus reducing the success rate of harvesting. This study introduces a fruit and branch detection and three-dimensional (3D) reconstruction method for obstacle avoidance path planning of robots. A new architecture for instance segmentation was developed by replacing the backbone of Mask R-CNN with a tiny network, referred to as ?tiny Mask R-CNN?. The tiny Mask R-CNN was trained with a small number of images and used to detect guava fruits and branches. Each detected fruit and branch were converted into a 3D point cloud. It was then hypothesized that guava fruits could be represented by 3D spheres and irregular branches can be approximated by a finite number of 3D cylindrical segments. Based on the proposed hypothesis, a random sample consensus-based sphere fitting method and a principal component analysis-based cylindrical segment fitting method were investigated to reconstruct the fruits and branches from the point clouds. A guava dataset with 304 RGB-D images was collected from the fields and used to validate the developed method. The results showed that the detection F1 score of the tiny Mask R-CNN was 0.518; the F1 score for fruit reconstruction was approximately 0.851 and 0.833 under the 2D- and 3D-fruit metrics, respectively; and the F1 score for branch reconstruction was approximately 0.394 and 0.415 under the 2D- and 3D-branch metrics, respectively. These results confirm that the proposed method can effectively reconstruct the fruits and branches and can, therefore, be used to plan an obstacle avoidance path for harvesting robots.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据