Auto-directed video stabilization with robust L1 optimal camera paths

By Matthias Grundmann, Vivek Kwatra, Irfan Essa. Computer Vision and Pattern Recognition, 2011

394 citations recorded by the source corpus.

We present a novel algorithm for automatically applying constrainable, L1-optimal camera paths to generate stabilized videos by removing undesired motions. Our goal is to compute camera paths that are composed of constant, linear and parabolic segments mimicking the camera motions employed by professional cinematographers. To this end, our algorithm is based on a linear programming framework to minimize the first, second, and third derivatives of the resulting camera path. Our method allows for video stabilization beyond the conventional filtering of camera paths that only suppresses high frequency jitter. We incorporate additional constraints on the path of the camera directly in our algorithm, allowing for stabilized and retargeted videos. Our approach accomplishes this without the need of user interaction or costly 3D reconstruction of the scene, and works as a post-process for videos from any camera or from an online source.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/49941c788b9dd8a639b33b4208b32a740b8c7bf8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Movement Pattern Histogram for Action Recognition and Retrieval (2014, methodology): “To minimize the effect of camera motion we can apply a video stabilization technique such as [7] before computing dense optical flow.”
Video magnification in presence of large motions (2015, methodology): “In the special case of camera motion, it might be possible to apply video stabilization as a preprocess to remove the undesirable large handshake, e.g. [8, 3, 9, 10], before magniﬁcation.”
PSyCo: Manifold Span Reduction for Super Resolution (2016, methodology): “Homographies are widely used in several applications involving multiple cameras or camera motion [8, 11], and they have been also used recently in SR [12] in order to increase the number of relevant patches in the NN search.”