Automatic extrinsic camera parameters calibration using convolutional neural networks

Abstract

Camera calibration is essential for accurate computer vision, and automatic calibration of some extrinsic parameters is needed in case the camera is placed on a mobile platform. The pitch and yaw angles, which are the most likely ones to change as the vehicle moves, can be inferred from the image coordinates of the vanishing point (VP). In this paper we present an artificial neural network approach for detecting the vanishing point position in road traffic scenarios. The network is trained using 2500 images which are first automatically annotated using a classical vanishing point detection algorithm, and then manually validated. The training and test datasets are made publicly available. The trained network was tested on more than 250 images not previously seen by the network, locating the VP accurately in more than 90% of the cases.