GENERIC OBJECT RECOGNITION BASED ON FEATURE FUSION IN ROBOT PERCEPTION
Xinde Li, Chaomin Luo, Jean Dezert, Yingzi Tan · International Journal of Robotics and Automation · 2016
A new generic object recognition (GOR) method for robot perception is proposed in this paper, based on multi-feature fusion of two-dimensional (2D) and 3D scale invariant feature transform descriptors drawn from 2D images and 3D point clouds.