Smart Vision & Robotic Sensing

Professor, Robotics Laboratory
Smart Innovation Program, Graduate School of Advanced Science and Engineering
Hiroshima University
>> Research Contents
In order to establish high-speed robot senses that are much faster than human senses, we are conducting research and development of information systems and devices that can achieve real-time image processing at 1000 frames/s or greater. As well as integrated algorithms to accelerate sensor information processing, we are also studying new sensing methodologies based on vibration and flow dynamics; they are too fast for humans to sense.

GPU-Based High-Frame-Rate Face Tracking

face tracking This study propose a high-speed vision system that can be applied to real-time face tracking at 500 fps using GPU acceleration of a boosting-based face tracking algorithm. By assuming a small image displacement between frames, which is a property of high-frame-rate (HFR) vision, we develop an improved boosting-based face tracking algorithm for fast face tracking by enhancing the Viola-Jones face detector. In the improved algorithm, the size and position of a face pattern to be tracked in an image can be efficiently extracted by reducing the number of window searches for Haar-like features and by combining skin color extraction with Haar classifiers. The improved boosting-based face tracking algorithm is implemented on a GPU-based high-speed vision platform, and face tracking can be executed in real time at 500 fps for an 8-bit color image of 512×512 pixels. In order to verify the effectiveness of the developed face tracking system, we install it on a two-axis mechanical active vision system and perform several experiments for tracking face patterns.

MPEG movie (9.6M) human face tracking using a 2-DOF active vision Human face tracking using a 2-DOF active vision
(MPEG movie (9.6M))