On the design and implementation of a dual fisheye camera-based surveillance vision system

Abstract

Image processing and computer vision have been a focus of researchers for decades in various application domains. This research is continuously rising with the rise of Artificial Intelligence in the fourth industrial revolution. One of the important digital image processing applications is to produce panorama images. The wide range of view a panorama image provides can be used in a variety range of applications which may include surveillance applications and remote robot operations. A panorama image is a combination of several individual natural looking images into a composite one to provide a wide field of view that may reach 360 degrees horizontally without any distortion. Wide-angle lenses provide a wide field of view, but using them alone does not necessarily make a panorama image. In this work the design and implementation of a wide-angle stereo vision system that suites many real-time applications is proposed. The system makes use of two wide-angle fisheye cameras where each camera covers around 170 degrees field of view. The horizontal angle between the cameras is 140 degrees. The cameras acquire the instantaneous overlapping images continuously and transmits them to a base station via a communication link. The base station calibrates, corrects, correlates and stitches the non-overlapping corrected images to a composite one. The resultant final image covers 310 degrees field of view. The system is of low computational complexity compared with previously implemented systems. It is tested on a laptop and on a standalone embedded computing device. The processing speed for the panorama image stitching including the correction of the fisheye barrel distortion on the laptop computer and the embedded computer is 11 fps, and 6 fps, respectively.