Fast Object Detection for Human-Robot Interaction Control

This paper proposes a fast object detection algorithm based on structural light analysis, which is used to detect and recognize human gesture and pose and then to conclude the respective commands for human-robot interaction control. The RGB camera and the infrared light module aim to do distance estimation of a body or several bodies. The module not only provides image perception but also objective skeleton detection. In which, a laser source in the infrared light module emits invisible infrared light which passes through a filter and is scattered into a semi-random but constant pattern of small dots which is projected onto the environment in front of the sensor. The reflected pattern is then detected by an infrared camera and analyzed for depth estimation. Since the depth of object is a key parameter for pose recognition, one can estimate the distance to each dot and then get depth information by calculation of distance between emitter and receiver. In this paper, the human poses are estimated and analyzed by the proposed scheme, and then the resultant data concluded by the fuzzy decision making system are used to launch respective robotic motions. The experimental results demonstrate the feasibility of the proposed system.