Mathematical aspects of distortion calibration for digital cameras

Abstract

Nowadays, most human processes are automated by means of computerization. This process has not spared the automotive industry. The latest developments in this field give promise that in the near future, cars will be completely autonomous. However, before that, there is an urgent need to address a number of issues, such as increasing the angle of view for greater coverage of the road with minimal space curvature. It is known that when the angle of view increases, so does the distortion (a mismatch in geometric similarity between an object and its image). This mismatch significantly reduces the accuracy of recognition algorithms. To solve this problem, this paper proposes a calibration method for cameras. The paper deals with mathematical aspects of distortion and the method of calibration of automobile chambers, and calibration errors. The method of static calibration without the use of points at infinity using static templates is proposed. A conventional camera has a small field of view (about 80 degrees). Such angle of view does not provide full scanning of the space; as a result, some of the necessary information remains outside the field of view, which is crucial for automotive industry because road signs, pedestrians, traffic lights might be missed. Therefore, in case of car cameras, the angle of view is increased by introducing distortion aberration. In this case, the field of view increases, yet the geometric similarity between the object and its image is affected. This, in turn, can affect the accuracy of computer vision algorithms. In order to keep the field of view angle large and the similarity between the subject and the object, it is necessary to calibrate the camera. In this paper, a calibration method for wide-angle car cameras is proposed and considered.