Distance determination for an automobile environment using inverse perspective mapping in OpenCV

This paper presents a novel real-time distance determination algorithm using an image sensor for use in an automobile environment. The system uses a forward facing camera placed within the vehicle. From a single forward facing image, it is difficult to determine distances to objects in front of the vehicle with any degree of certainty. There is a non linear relationship between the height of an object in a forward facing image and its distance from the camera. This paper presents a method which uses Inverse Perspective Mapping (IPM) to overcome this problem. Using IPM, we can transform the forward facing image to a top-down "bird's eye" view, in which there is a linear relationship between distances in the image and in the real world. The algorithm is implemented in the C language using the OpenCV libraries. Implementation in OpenCV leads to a high performance, low overhead system that could be implemented on a low power embedded device in an automotive environment.