Using the binocular stereo vision system, the branches of citrus trees in natural scene were reconstructed in virtual environment, to help citrus picking robots recognize and evade obstacles in real working scene. During the reconstruction, images were subjected to thinning, pruning, and curve fitting successively. We reduced the computational burden while guaranteeing the model precision. Then, we adopted the principle of modularized modeling and OpenGL for branch reconstruction. It is verified that the method developed in this work provides a route planning criterion and a virtual workplace for the robot's obstacle evading system.
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.