An RGB-D camera-based object symmetry axis detection method, relating to the field of image processing, said method comprising: acquiring three-dimensional point cloud data of an image of a target object in a natural scene; according to a color difference threshold segmentation method, identifying, from the three-dimensional point cloud data, target point cloud data corresponding to a point cloud in an area where the target object is located; establishing a spherical coordinate system by taking the center of mass of the target point cloud data as a center; selecting n2 candidate symmetry planes using a spherical coordinate system segmentation method; and according to the n2 candidate symmetry planes, calculating a symmetry axis of the target point cloud data, i.e. the symmetry axis of the target object. The method achieves the three-dimensional reconstruction of a target object RGB-D image and point cloud filtering, finally, the detection of the symmetry axis of the target object is achieved by means of a grading system; when the method is applied to the field of fruit picking, the symmetry axis of a fruit can be accurately found on the basis of a fruit image taken in a natural scene, improving the automatic fruit picking efficiency.
展开▼