Using OpenCV for distance determinationIn “Distance Determination for an Automobile Environment using Inverse Perspective Mapping in OpenCV,” S.Tuohy, D.O’Cualain, E. Jones, and M.Glavin at the College of Engineering and Informatics National University of Ireland describe a novel real-time distance determination OpenCV algorithm using an image sensor in an automobile environment. The system uses a forward facing camera placed within the vehicle.
Because it is difficult to determine distances to objects in front of the vehicle with any degree of certainty because of a non linear relationship between the height of an object in a forward facing image and its distance from the camera, they make use of Inverse Perspective Mapping (IPM).
Using IPM, they describe how to 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 and results in a high performance, low overhead system that could be implemented on a low power embedded device in an automotive environment.
Log-in or register for a free account to get unlimited articles and full access to EDN.