High Speed Tracking of Moving Objects and Depth Estimation by using Smart Image Sensor and FPGA

Abstract

We have been investigating an integration of sensing and compression in an image sensor. A compression Sensor reduces the number of pixels in the image signal that have to be read out from the sensor, We present a real-time object tracking system by using a compression sensor that has 128×128 pixels and FPGA, By using this system. several moving objects can be extracted and tracked independently at 1200 frames/second. We also describe real-time depth estimation by using a binocular compression sensor. We show some results obtained by the system.