Image Mosaicing and Super-resolutionThe Distinguished Dissertation Series is published on behalf of the Conference of Professors and Heads of Computing and the British Computer Society, who annually select the best British PhD dissertations in computer science for publication. The dissertations are selected on behalf of the CPHC by a panel of eight academics. Each dissertation chosen makes a noteworthy contribution to the subject and reaches a high standard of exposition, placing all results clearly in the context of computer science as a whole. In this way computer scientists with significantly different interests are able to grasp the essentials - or even find a means of entry - to an unfamiliar research topic. This book investigates how information contained in multiple, overlapping images of a scene may be combined to produce images of superior quality. This offers possibilities such as noise reduction, extended field of view, blur removal, increased spatial resolution and improved dynamic range. Potential applications cover fields as diverse as forensic video restoration, remote sensing, video compression and digital video editing. The book covers two aspects that have attracted particular attention in recent years: image mosaicing, whereby multiple images are aligned to produce a large composite; and super-resolution, which permits restoration at an increased resolution of poor quality video sequences by modelling and removing imaging degradations including noise, blur and spacial-sampling. It contains a comprehensive coverage and analysis of existing techniques, and describes in detail novel, powerful and automatic algorithms (based on a robust, statistical framework) for applying mosaicing and super-resolution. The algorithms may be implemented directly from the descriptions given here. A particular feature of the techniques is that it is not necessary to know the camera parameters (such as position and focal length) in order to apply them. Throughout the book, examples are given on real image sequences, covering a variety of applications including: the separation of latent marks in forensic images; the automatic creation of 360 panoramic mosaics; and super-resolution restoration of various scenes, text, and faces in lw-quality video. |
Contents
I | 1 |
II | 4 |
III | 5 |
V | 7 |
VI | 9 |
VII | 10 |
IX | 12 |
XI | 13 |
LVIII | 91 |
LIX | 92 |
LX | 93 |
LXI | 96 |
LXII | 101 |
LXIII | 105 |
LXIV | 106 |
LXV | 110 |
XII | 14 |
XIII | 17 |
XIV | 18 |
XV | 20 |
XVII | 21 |
XIX | 22 |
XX | 26 |
XXIII | 34 |
XXIV | 36 |
XXVI | 36 |
XXVII | 38 |
XXIX | 40 |
XXX | 43 |
XXXI | 45 |
XXXII | 47 |
XXXIII | 48 |
XXXV | 50 |
XXXVI | 53 |
XXXVII | 54 |
XXXVIII | 55 |
XL | 59 |
XLI | 62 |
XLII | 64 |
XLIII | 66 |
XLIV | 69 |
XLV | 71 |
XLVI | 72 |
XLVII | 73 |
XLVIII | 74 |
XLIX | 77 |
LII | 78 |
LIII | 79 |
LIV | 82 |
LV | 83 |
LVI | 84 |
LVII | 90 |
LXVII | 111 |
LXIX | 119 |
LXXI | 120 |
LXXII | 122 |
LXXIV | 123 |
LXXV | 131 |
LXXVIII | 132 |
LXXIX | 133 |
LXXX | 134 |
LXXXI | 136 |
LXXXII | 140 |
LXXXIII | 141 |
LXXXV | 142 |
LXXXVI | 150 |
LXXXVII | 158 |
LXXXVIII | 161 |
XC | 163 |
XCII | 164 |
XCIII | 165 |
XCIV | 169 |
XCV | 170 |
XCVI | 171 |
XCVII | 175 |
XCVIII | 182 |
XCIX | 183 |
CII | 184 |
CIII | 185 |
CIV | 186 |
CV | 188 |
CVI | 189 |
CVII | 190 |
CVIII | 193 |
CIX | 195 |
CXI | 197 |
211 | |
Other editions - View all
Common terms and phrases
3x zoom affine transformation algorithm applied arg max average image blur captured centre Chapter components computed convergence corresponding cross-validation described difference image equation example face-space favg feature-based filter fountain and th Gaussian geometric global GMRF gradient descent grey-levels hence HMRF prior homography image gradient image model image mosaicing image noise image registration input images intensity interest points IS-MAP iterations Levenberg-Marquardt algorithm lifeless ocean linear low-res low-resolution images low-resolution pixel MAP estimators matrix maximum likelihood minimizes ML estimator mosaic N-view matching number of images obtained Opsf optic optimization pair of images parameters photometric photometric registration pixel-zoom pixels planar manifold Plate point-spread function position on profile pre-image point problem quadratic RANSAC reconstruction error rendered image residual RMS error robust scene Section shown in Figure shows solution spatial steepest descent sub-space super-pixels super-resolution estimate super-resolution image synthetic images tion two-view Var(eavg variance warped Wiener filter zoom ratio
Popular passages
Page 203 - M. Irani, P. Anandan, J. Bergen, R. Kumar, and S. Hsu. Efficient representations of video sequences and their applications.
Page 204 - M. Irani, B. Rousso, and S. Peleg. Computing occluding and transparent motions.
Page 204 - Video orbits of the projective group: A new perspective on image mosaicing," MIT Media Lab Perceptual Computing Section Technical Report No.
Page 204 - Virtual bellows: constructing high quality stills from video,
Page 205 - S. Peleg, D. Keren, and L. Schweitzer, "Improving image resolution using subpixel motion", Pattern Recognition Letters 5 (3), pp.