A Simulation Method of Specific Fish-Eye Imaging System Based on Image Postprocessing

Abstract

In order to enable the implementation of the computer vision-based perception techniques in the physical-based simulation environment, visual sensors need to be simulated physically. Among others, fish-eye cameras are commonly used visual sensors to provide an omni-directional field of view. The existing methods cannot simulate the output of a specific real fish-eye imaging system. In this paper, we present a postprocessing fish-eye imaging system simulation method. According to the stereographic projection model, a mapping is established between the ideal fish-eye image and a cube-map rendered by the graphic engine. The distortion of the real camera is measured and added to the ideal image, in order to simulate the output of a specific camera. Experimental result shows that our simulation method can give output close enough to the image captured by a specific fish-eye camera. The practicality of our method is validated in an actual application of vehicle omniview system.

Keywords

• Sensor simulation
• Intelligent vehicle system
• Fish-eye camera
• Camera calibration
• Stereographic projection model