Automatic apple recognition based on the fusion of color and 3D feature for robotic fruit picking

- A color based region growing segmentation method was applied to extract the independent point cloud of apple, branches and leaves from the scene.
- We proposed an improved 3D descriptor which is composed by color feature and 3D geometric feature to describe apples, branches and leaves from point cloud data.
- We proposed an automatic recognition method based on genetic algorithm optimized SVM to recognize three classes of data.
- We discussed the feasibility of using the proposed method to estimate the blocking of apples.

Accurate apple recognition is a vital step in the operation of robotic fruit picking. To improve robot recognition ability and perception in three-dimensional (3D) space, an automatic recognition method was proposed to achieve apple recognition from point cloud data. First, an improved 3D descriptor (Color-FPFH) with the fusion of color features and 3D geometry features was extracted from the preprocessed point clouds. Then, a classification category was subdivided into apple, branch, and leaf to provide the system with a more comprehensive perception capability. A classifier based on the support vector machine, optimized using a genetic algorithm, was trained by the three data classes. Finally, the results of recognition and lateral comparison were obtained by comparison with the different 3D descriptors and other classic classifiers. The results showed that the proposed method exhibited better performance. In addition, the feasibility of estimating the occurrence of blocking using proposed method was discussed.