ABSTRACT
Image composition for GoPro videos captured in the presence of significant camera motion is a manual and time consuming process. Existing techniques typically fail to automate this process due to the wide-capture field of view and high camera motion of such videos. The proposed method seeks to solve these problems by developing an image registration algorithm for fisheye images without expensive pixel warping or loss of field of view. Background subtraction is performed to extract moving foreground objects, which are noise corrected and then layered on a reference image to build the final composite. The results show marked improvements in accuracy and efficiency for automating image composition.
Supplemental Material
Available for Download
Supplemental files.
- Bouwmans, T., El Baf, F., and Vachon, B. 2008. Background modeling using mixture of gaussians for foreground detection-a survey. Recent Patents on Computer Science 1, 3, 219--237.Google ScholarCross Ref
- Matt, 2013. The galaxy s4: A life companion. http://www.samsung.com/uk/discover/mobile/galaxy-s4-a-life-companion/, June. Accessed on March, 1 2016.Google Scholar
- Sobral, A., and Vacavant, A. 2014. A comprehensive review of background subtraction algorithms evaluated with synthetic and real videos. Computer Vision and Image Understanding 122, 4--21.Google Scholar
- Sunkavalli K. Joshi N. Kang S. B. Cohen M. F. and Pfister, H. 2012. Video snapshots: Creating high-quality images from video clips. Visualization and Computer Graphics, IEEE Transactions on 18, 11, 1868--1879. Google ScholarDigital Library
- Szeliski, R. 2006. Image alignment and stitching: A tutorial. Foundations and Trends® in Computer Graphics and Vision 2, 1, 1--104. Google ScholarDigital Library
- Umeyama, S. 1991. Least-squares estimation of transformation parameters between two point patterns. IEEE Transactions on Pattern Analysis & Machine Intelligence, 4, 376--380. Google ScholarDigital Library
- Xiong, Y., and Turkowski, K. 1997. Creating image-based vr using a self-calibrating fisheye lens. In Computer Vision and Pattern Recognition, 1997. Proceedings., 1997 IEEE Computer Society Conference on, IEEE, 237--243. Google ScholarDigital Library
Index Terms
- Motion compensated automatic image compositing for GoPro videos
Recommendations
True motion-compensated de-interlacing algorithm
This paper presents a true motion-compensated de-interlacing (TMCD) algorithm based on a fast true motion estimation scheme. The fast true motion estimation scheme, designated as a variable block size true motion estimation for a translated motion model ...
A motion compensated de-interlacing algorithm for motive object capture
ICDHM'07: Proceedings of the 1st international conference on Digital human modelingA motion compensated de-interlacing algorithm is proposed to recover the defects of interlaced video frame for capturing motion object. In this algorithm, two anti-noise background fields are formed by analyzing the temporal correlation of pixels ...
Video de-interlacing by adaptive 4-field global/local motion compensated approach
A de-interlacing algorithm using adaptive 4-field global/local motion compensated approach is presented. It consists of block-based directional edge interpolation, same-parity 4-field motion detection, global/local motion estimation and compensation. ...
Comments