Abstract: A method and arrangement for calibrating stereo cameras. A first image from a first camera is received, and a second image is received from a second camera, the first image and the second image comprise an overlap. One or more candidate points of the first image and of the second image are determined in the overlap. The candidate points of the first image are matched with the candidate points of the second image and pairs of corresponding candidate points are determined. A homography of the first camera is calculated based on the pairs of corresponding candidate points and a homography of the second camera is calculated based on the pairs of corresponding candidate points. The first camera and the second camera are calibrated by adjusting an intrinsic parameter or an extrinsic parameter of each respective camera, based on the calculated homography of each respective camera.

Abstract: A method and arrangement for calibrating stereo cameras in a vehicle is disclosed. A first image from a first camera is received, and a second image is received from a second camera, the first image and the second image comprise an overlap. One or more candidate points of the first image and of the second image are determined in the overlap. The candidate points of the first image are matched with the candidate points of the second image and pairs of corresponding candidate points are determined. A homography of the first camera is calculated based on the pairs of corresponding candidate points and a homography of the second camera is calculated based on the pairs of corresponding candidate points. The first camera and the second camera are calibrated by adjusting an intrinsic parameter or an extrinsic parameter of each respective camera, based on the calculated homography of each respective camera.

Abstract: A method for tracking objects in a scene being viewed by a sequence of digital images comprises: separating a region of interest in the digital images into a plurality of spatially smaller, overlapping modules, and defining a hidden Markov model for each module. The method further comprises observing detections of positions of possible objects at different times, considering a set of states at a point of time (t1) such that the set of states comprises a state having a global optimum probability, and backtracking through the sequence of digital images for each hidden Markov model to shrink the set of states that are possible for earlier parts of the sequence of digital images, such that a single optimal state is found for an earlier point of time (t2<t1), whereby tracks of detected objects through the scene are determined up to the earlier point of time (t2).