Multi-Scale, Categorical Object Detection and Pose Estimation using Hough Forest in RGB-D Images

Classification and localization of objects enables a robot to plan and execute tasks in unstructured environments. Much work on the detection and pose estimation of objects in the robotics context focused on object instances. We propose here a novel approach that detects object classes and finds the canonical pose of the detected objects in RGB-D images using Hough forests. In Hough forests each random decision tree maps local image patch to one of its leaves through a cascade of binary decisions over a patch appearance, where each leaf casts probabilistic Hough vote in Hough space encoded in object location, scale and orientation. We propose depth and surfel pair-feature as an additional appearance channels to introduce scale, shape and geometric information about the object. Moreover, we exploit depth at various stages of the processing pipeline to handle variable scale efficiently. Since obtaining large amounts of annotated training data is a cumbersome process, we use training data captured on a turn-table setup. Although the training examples from this domain do not include clutter, occlusions or varying background situations. Hence, we propose a simple but effective approach to render training images from turn-table dataset which shows the same statistical distribution in image properties as natural scenes. We evaluate our approach on publicly available RGB-D object recognition benchmark datasets and demonstrate good performance in varying background and view poses, clutter, and occlusions.