Multiframe Super-Resolution Reconstruction of Small Moving Objects

Eekeren, Adam W. M. van; Schutte, Klamer; Vliet, Lucas J. van

doi:10.1109/tip.2010.2068210

Cited by 46 publications

(23 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They, hence, may face the problem of selfocclusions especially in the case of non-rigidly moving objects. This difficulty arises in depth videos, but also for 2-D sequences [21,22,23,24]. Most of the methods in the literature are limited due to strong assumptions on the shape and number of moving objects.…”

Section: Sr For Dynamic Scenesmentioning

confidence: 99%

Enhancement of dynamic depth scenes by upsampling for precise super-resolution (UP-SR)

Ismaeil

Aouada

Mirbach

et al. 2016

Computer Vision and Image Understanding

View full text Add to dashboard Cite

Multi-frame super-resolution is the process of recovering a high resolution image or video from a set of captured low resolution images. Super-resolution approaches have been largely explored in 2-D imaging. However, their extension to depth videos is not straightforward due to the textureless nature of depth data, and to their high frequency contents coupled with fast motion artifacts. Recently, few attempts have been introduced where only the super-resolution of static depth scenes has been addressed. In this work, we propose to enhance the resolution of dynamic depth videos with non-rigidly moving objects. The proposed approach is based on a new data model that uses densely upsampled, and cumulatively registered versions of the observed low resolution depth frames. We show the impact of upsampling in increasing the sub-pixel accuracy and reducing the rounding error of the motion vectors. Furthermore, with the proposed cumulative motion estimation, a high registration accuracy is achieved between non-successive upsampled frames with relative large motions. A statistical performance analysis is derived in terms of mean square error explaining the effect of the number of observed frames and the effect of the super-resolution factor at a given noise level. We evaluate the accuracy of the proposed algorithm theoretically and experimentally as function of the SR factor, and the level of contaminations with noise. Experimental results on both real and synthetic data show the effectiveness of the proposed algorithm on dynamic depth videos as compared to state-of-art methods.

show abstract

Section: Sr For Dynamic Scenesmentioning

confidence: 99%

Enhancement of dynamic depth scenes by upsampling for precise super-resolution (UP-SR)

Ismaeil

Aouada

Mirbach

et al. 2016

Computer Vision and Image Understanding

View full text Add to dashboard Cite

show abstract

“…The novelty of the first method is that the seismic data and well logs are integrated with a stratigraphic model constructed with quantitative knowledge of the reservoir architecture. The innovation of the second method lies in its goal to adopt a 'super-resolution' technique that favors sparse solutions for the clinoform characterization (Van Eekeren et al, 2008). Both inversion methods are not fully 2D, but…”

Section: Research Objectivesmentioning

confidence: 99%

“…Recently, Van Eekeren et al (2008) introduced a method for multiframe super-resolution (SR) reconstruction of small moving objects…”

Section: Super Resolution Reconstruction Of Small Moving Objectsmentioning

confidence: 99%

“…To be able to apply the Levenberg-Marquardt method in combination with an L 1 -norm we use the hyperbolic norm ( • H ) introduced by Van Eekeren et al (2008). This norm is defined as…”

Section: Hyperbolic Normmentioning

confidence: 99%

“…To enforce a sparse solution we adopted a method by Van Eekeren et al (2008) that was successfully applied to obtain 'super-resolution'…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations