MobileRGBD, an open benchmark corpus for mobile RGB-D related algorithms

Since the commercialization of low cost RGB-D sensors, like the Kinect, more and more indoor robots have been equipped with this kind of sensors to perform tasks as people tracking or gesture recognition. Nevertheless, as far as we know from the literature, studies do not consider the limits of the sensors in term of motion speed, position of the sensor on the robot, etc. In this work, we propose to provide a corpus dedicated to low level RGB-D algorithms benchmarking. Originality of our approach is the use of dummies in order to play static users in the environment. This idea let us vary other variables that can impact algorithm performance: linear/angular speed of the robot, trajectory of the robot, RGB-D sensor height and vertical angle of view, number and relative position of dummies and furniture position. This paper first describes the experimental platform used to perform the acquisitions and the environment setup required to reproduce the dataset. Then, a precise description of all available data is given. We will see that, as this corpus contains a lot of configurations, it will allow researchers to investigate how these variables impact the results of their algorithms.