Smart Vision & and Sensing

Professor, Robotics Laboratory
Department of System Cybernetics, 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.

Fast Color-Histogram-Based Target Tracking

In this study, we introduces a high-speed vision system that can be applied to color-histogram-based tracking at 2000 fps by hardware implementing an improved CamShift algorithm. In the improved CamShift algorithm, the size, position, and orientation of a color-patterned object to be tracked in an image can be simultaneously extracted using only the hardware implementation of a color histogram circuit module for calculating moment features of binary images quantized by 16 hue-based color bins.


By hardware-implementing color histogram circuit modules on a high-speed vision platform, IDP Express, the improved CamShift algorithm enables color histogram-based tracking at 2000 fps for 512×511 pixel images in real time. By installing our tracking system on a two-axis mechanical active vision system, we demonstrate the effectiveness of 2000 fps color-histogram-based tracking by performing several experiments of color-patterned objects, which are always tracked in the camera views even when they move rapidly under complicated backgrounds.
tracking of a rotating color-pattern WMV movie(0.9M)
tracking of a rotating color-pattern
tracking of a human hand WMV movie(4.3M)
tracking of a human hand