People Detection in RGB-D Data

People detection is a key issue for robots and intelligent systems sharing a space with people. Previous works have used cameras and 2D or 3D range finders for this task. In this paper, we present a novel people detection approach for RGB-D data. We take inspiration from the Histogram of Oriented Gradients (HOG) detector and from the depth characteristics of the Kinect RGB-D sensor to design a robust method to detect people in dense depth data, called Histogram of Oriented Depths (HOD). HOD locally encodes the direction of depth changes and relies on an depth- informed scale-space search that leads to a 3-fold acceleration of the detection process. We then pro- pose Combo-HOD, a RGB-D detector that combines HOD and HOG responses. The experiments include a comprehensive comparison with several alternative detection approaches including visual HOG, several variants of HOD, a geometric person detector for 3D point clouds, and an Haar-based AdaBoost detector. The results demonstrate the robustness of HOD and Combo-HOD on a real-world data set collected in a populated indoor environment.