Motion Estimation for Fisheye Video With an Application to Temporal Resolution Enhancement

Surveying wide areas with only one camera is a typical scenario in surveillance and automotive applications. Ultra wide-angle fisheye cameras employed to that end produce video data with characteristics that differ significantly from conventional rectilinear imagery as obtained by perspective pinhole cameras. Those characteristics are not considered in typical image and video processing algorithms such as motion estimation, where translation is assumed to be the predominant kind of motion. This contribution introduces an adapted technique for use in block-based motion estimation that takes into the account the projection function of fisheye cameras and thus compensates for the non-perspective properties of fisheye videos. By including suitable projections, the translational motion model that would otherwise only hold for perspective material is exploited, leading to improved motion estimation results without altering the source material. In addition, we discuss extensions that allow for a better prediction of the peripheral image areas, where motion estimation falters due to spatial constraints, and further include calibration information to account for lens properties deviating from the theoretical function. Simulations and experiments are conducted on synthetic as well as real-world fisheye video sequences that are part of a data set created in the context of this paper. Average synthetic and real-world gains of 1.45 and 1.51 dB in luminance PSNR are achieved compared against conventional block matching. Furthermore, the proposed fisheye motion estimation method is successfully applied to motion compensated temporal resolution enhancement, where average gains amount to 0.79 and 0.76 dB.

[1]  Shahram Shirani,et al.  Frame Rate Upconversion Using Optical Flow and Patch-Based Reconstruction , 2016, IEEE Transactions on Circuits and Systems for Video Technology.

[2]  J. Yamaguchi,et al.  Human tracking using fisheye images , 2007, SICE Annual Conference 2007.

[3]  André Kaup,et al.  Coding of distortion-corrected fisheye video sequences using H.265/HEVC , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[4]  Bernhard Schölkopf,et al.  Online Video Deblurring via Dynamic Temporal Blending Network , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[5]  Gangolf Hirtz,et al.  A fast approach for omnidirectional surveillance with multiple virtual perspective views , 2013, Eurocon 2013.

[6]  André Kaup,et al.  Disparity estimation for fisheye images with an application to intermediate view synthesis , 2017, 2017 IEEE 19th International Workshop on Multimedia Signal Processing (MMSP).

[7]  André Kaup,et al.  Temporal error concealment for fisheye video sequences based on equisolid re-projection , 2015, 2015 23rd European Signal Processing Conference (EUSIPCO).

[8]  Michael R. Frater,et al.  A cell-loss concealment technique for MPEG-2 coded video , 2000, IEEE Trans. Circuits Syst. Video Technol..

[9]  Shao-Yi Chien,et al.  Algorithm and Architecture Design of Multirate Frame Rate Up-conversion for Ultra-HD LCD Systems , 2017, IEEE Transactions on Circuits and Systems for Video Technology.

[10]  Iain E. G. Richardson,et al.  The H.264 Advanced Video Compression Standard , 2010 .

[11]  Dan Levi,et al.  Vision-based pedestrian detection for rear-view cameras , 2014, 2014 IEEE Intelligent Vehicles Symposium Proceedings.

[12]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[13]  André Kaup,et al.  Multi-image super-resolution for fisheye video sequences using subpixel motion estimation based on calibrated re-projection , 2016, 2016 24th European Signal Processing Conference (EUSIPCO).

[14]  Whoi-Yul Kim,et al.  Lane detection system with around view monitoring for intelligent vehicle , 2013, 2013 International SoC Design Conference (ISOCC).

[15]  Liam Kilmartin,et al.  A Blind-Zone Detection Method Using a Rear-Mounted Fisheye Camera With Combination of Vehicle Detection Methods , 2016, IEEE Transactions on Intelligent Transportation Systems.

[16]  Gary J. Sullivan,et al.  Overview of the High Efficiency Video Coding (HEVC) Standard , 2012, IEEE Transactions on Circuits and Systems for Video Technology.

[17]  Nayoung Kim,et al.  Bi-directional deformable block-based motion estimation for frame rate-up conversion of 360-degree videos , 2017 .

[18]  Miska M. Hannuksela,et al.  Fisheye video coding using elastic motion compensated reference frames , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[19]  Madhukar Budagavi,et al.  Motion estimation and compensation for fisheye warped video , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[20]  Olivier D. Faugeras,et al.  Automatic calibration and removal of distortion from scenes of structured environments , 1995, Optics & Photonics.

[21]  Roland Siegwart,et al.  A Toolbox for Easily Calibrating Omnidirectional Cameras , 2006, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[22]  Juho Kannala,et al.  A generic camera model and calibration method for conventional, wide-angle, and fish-eye lenses , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  Yanjun Li,et al.  Joint Adaptive Sparsity and Low-Rankness on the Fly: An Online Tensor Reconstruction Scheme for Video Denoising , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[24]  André Kaup,et al.  A hybrid motion estimation technique for fisheye video sequences based on equisolid re-projection , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[25]  Edward Jones,et al.  Wide-angle camera technology for automotive applications: a review , 2009 .

[26]  André Kaup,et al.  Motion estimation for fisheye video sequences combining perspective projection with camera calibration information , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[27]  Clemens Rabe,et al.  6D Vision Goes Fisheye for Intersection Assistance , 2008, 2008 Canadian Conference on Computer and Robot Vision.

[28]  Ajay Luthra,et al.  Overview of the H.264/AVC video coding standard , 2003, IEEE Trans. Circuits Syst. Video Technol..

[29]  Jong Beom Ra,et al.  Frame Rate Up Conversion Based on Variational Image Fusion , 2014, IEEE Transactions on Image Processing.

[30]  Myung Hoon Sunwoo,et al.  New Frame Rate Up-Conversion Algorithms With Low Computational Complexity , 2014, IEEE Transactions on Circuits and Systems for Video Technology.

[31]  Kenro Miyamoto,et al.  Fish Eye Lens , 1964 .

[32]  Moon Gi Kang,et al.  Super-resolution image reconstruction: a technical overview , 2003, IEEE Signal Process. Mag..

[33]  Taejeong Kim,et al.  MAP-Based Motion Refinement Algorithm for Block-Based Motion-Compensated Frame Interpolation , 2016, IEEE Transactions on Circuits and Systems for Video Technology.