3D Modeling of Dormant Apple Trees
 
Dormant pruning is one of the most essential as well as most costly and labor-intensive operations in specialty crop production. During winter, a large crew of trained seasonal workers has to carefully remove the branches from hundreds of trees using a set of pre-defined rules. The motivation behind automatic pruning is to reduce dependence on the large work-force and the associated huge labor cost currently needed for the job. Automatically applying the pruning rules entails construction of 3D models of the trees in their dormant condition (that is, without foliage) and accurate estimation of the pruning points on the branches. The goal of this project is to create an easy interface with the robotic pruners by building and visualizing accurate 3D models of dormant apple trees.
 
 
 
 
 
 
 
 
 
 
 
 
 
    
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Approach:
We build accurate 3D models of dormant apple trees by reconstructing the trunk and primary branches using a novel semicircle fitting based 3D reconstruction scheme.
 
 
 
Results:
 
 
 
PROJECT TEAM
 
    •    Shayan A. Akbar
    •    Somrita Chattopadhyay
    •    Noha M. Elfiky
    •    Avinash Kak
    •    Donghun Kim
    •    Fangda Li
    •    Henry Medeiros
    •    Johnny Park
    •    Hariharan Seshadri
    •    Jianxin Sun
 
 
 
PUBLICATIONS
 
Henry Medeiros, Donghun Kim, Jianxin Sun, Hariharan Seshadri, Shayan Ali Akbar, Noha M. Elfiky, Johnny Park, “Modeling Dormant Fruit Trees for Agricultural Automation,” Journal of Field Robotics, 2016 (accepted). [pdf]
Shayan A. Akbar, Somrita Chattopadhyay, Noha M. Elfiky, and Avinash Kak, “A Novel Benchmark RGBD Dataset for Dormant Apple Trees and its Application to Automatic Pruning,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Las Vegas, NV, USA, 2016. [pdf]
Fangda Li, Somrita Chattopadhyay, Shayan A. Akbar, Noha M. Elfiky, and Avinash Kak, “A Novel Visualization Tool for Evaluating the Accuracy of 3D Sensing and Reconstruction Algorithms for Automatic Dormant Pruning Applications,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Las Vegas, NV, USA, 2016. [pdf]
Somrita Chattopadhyay, Shayan A. Akbar, Noha M. Elfiky, Henry Medeiros, and Avinash Kak, “Measuring and Modeling Apple Trees using Time-of-Flight Data for Automation of Dormant Pruning Applications,” IEEE Winter Conference on Applications of Computer Vision (WACV), 2016, Lake Placid, NY, USA. [pdf]
Shayan A. Akbar, Noha M. Elfiky, and Avinash Kak, “A Novel Framework for Modeling Dormant Apple Trees using Single Depth Image for Robotic Pruning Application,” International Conference on Robotics and Automation (ICRA) 2016, Stockholm, Sweden. [pdf]
Noha M. Elfiky, Shayan A. Akbar, Jianxin Sun, Johnny Park, and Avinash Kak, “Automation of Dormant Pruning in Specialty Crop Production: An Adaptive Framework for Automatic Reconstruction and Modeling of Apple Trees,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Boston, MA, USA, 2015. [pdf]
PROJECT DESCRIPTION
The USDA Automatic Pruning Project