scispace - formally typeset
Search or ask a question
Author

Jae-Ho Yun

Bio: Jae-Ho Yun is an academic researcher from Sogang University. The author has contributed to research in topics: Scale-invariant feature transform & Image processing. The author has an hindex of 3, co-authored 4 publications receiving 38 citations.

Papers
More filters
Book ChapterDOI
18 Sep 2006
TL;DR: The proposed frame rate up-conversion method can provide detailed and improved interpolated images without block artifact, and experimental results with three sets of ultrasound image sequences show the effectiveness of the proposed interpolation method.
Abstract: In this paper, we present an optical flow based frame rate up-conversion method for ultrasound images. The conventional mechanical scan method for multi-planar images has a slow frame rate, thus frame interpolation is desirable for smooth display. In the proposed frame rate up-conversion method, several new interpolated frames are inserted between two input frames, giving smooth renditions to human eyes. We employ a window-based optical flow based method to find accurate motion estimates for frame interpolation. Consequently, the proposed method can provide detailed and improved interpolated images without block artifact. Experimental results with three sets of ultrasound image sequences show the effectiveness of the proposed interpolation method.

16 citations

Journal Article
TL;DR: In this article, a self-calibration strategy to estimate camera intrinsic and extrinsic parameters using the scale-invariant feature transform (SIFT) was proposed, where the accuracy of the estimated parameters depends on how reliably a set of image correspondences is established.
Abstract: In this paper, we present a self-calibration strategy to estimate camera intrinsic and extrinsic parameters using the scale-invariant feature transform (SIFT). The accuracy of the estimated parameters depends on how reliably a set of image correspondences is established. The SIFT employed in the self-calibration algorithms plays an important role in accurate estimation of camera parameters, because of its robustness to changes in viewing conditions. Under the assumption that the camera intrinsic parameters are constant, experimental results show that the SIFT-based approach using two images yields more competitive results than the existing Harris comer detector-based approach using two images.

12 citations

Book ChapterDOI
06 Nov 2006
TL;DR: Under the assumption that the camera intrinsic parameters are constant, experimental results show that the SIFT-based approach using two images yields more competitive results than the existing Harris corner detector- based approach usingTwo images.
Abstract: In this paper, we present a self-calibration strategy to estimate camera intrinsic and extrinsic parameters using the scale-invariant feature transform (SIFT). The accuracy of the estimated parameters depends on how reliably a set of image correspondences is established. The SIFT employed in the self-calibration algorithms plays an important role in accurate estimation of camera parameters, because of its robustness to changes in viewing conditions. Under the assumption that the camera intrinsic parameters are constant, experimental results show that the SIFT-based approach using two images yields more competitive results than the existing Harris corner detector-based approach using two images.

11 citations

Journal ArticleDOI
TL;DR: Experimental comparisons with the images synthesized using the actual three -dimensional scene structure and camera poses show that the proposed method effectively describes scene changes by viewpoint movements without estimation of 3 -D and camera information.
Abstract: This paper presents an uncalibrated v iew synthesis method using piecewise planar regions that are extracted from a given set of image pairsthrough planar segmentation. Our work concentrates on a view synthesis method that does not needestimation of camera parameters and scene structure. Forour goal, we simply assume that images of real world are composed of piecewise planar regions. Then, we perform view synthesis simply with planar regions and homographiesbetween them. Here, for accurate extraction of planar homographies and piecewise pla nar regions in images, the proposed method employs iterative homography estimation and color segmentation -based planar region extraction. The proposed method synthesizes the virtual view image using a set of planar regions as well as a set of corresponding homographies. Experimental comparisons with the images synthesized using the actual three -dimensional (3-D) scene structure and camera poses show that the proposed method effectively describes scene changes by viewpoint movements without estimation of 3 -D and camera information.

Cited by
More filters
Journal ArticleDOI
TL;DR: An automated stereo vision-based method, as an alternative and inexpensive solution, to producing a sparse Euclidean 3D point cloud of an infrastructure scene utilizing two video streams captured by a set of two calibrated cameras.

86 citations

Journal ArticleDOI
TL;DR: In this article, a multi-view fire localization framework is proposed, which merges the single-view detection results of the multiple cameras by homographic projection onto multiple horizontal and vertical planes, which slice the scene.

31 citations

Patent
25 Sep 2009
TL;DR: In this paper, motion information generated by comparing one or more clinical volume data may be used in a variety of applications, such as the generation of interpolated volume data at a time point somewhere between two received instance of volume data.
Abstract: Motion information generated by comparing one or more clinical volume data may be used in a variety of applications. Examples of applications described herein include 1) generation of interpolated volume data at a time point somewhere between two received instance of volume data; 2) propagation of geometric information from one instance of volume data to another based on the motion information; and 3) adjustment of volume data to fix one or more features at a same location in a series of rendered instances of volume data. Combinations of these effects may also be implemented.

29 citations

Journal ArticleDOI
TL;DR: A novel framework that optimizes TSR enhancement of echocardiographic images by utilizing temporal information and sparse representation and does not require training of low-resolution and high-resolution dictionaries.
Abstract: A challenging issue for echocardiographic image interpretation is the accurate analysis of small transient motions of myocardium and valves during real-time visualization. A higher frame rate video may reduce this difficulty, and temporal super resolution (TSR) is useful for illustrating the fast-moving structures. In this paper, we introduce a novel framework that optimizes TSR enhancement of echocardiographic images by utilizing temporal information and sparse representation. The goal of this method is to increase the frame rate of echocardiographic videos, and therefore enable more accurate analyses of moving structures. For the proposed method, we first derived temporal information by extracting intensity variation time curves (IVTCs) assessed for each pixel. We then designed both low-resolution and high-resolution overcomplete dictionaries based on prior knowledge of the temporal signals and a set of prespecified known functions. The IVTCs can then be described as linear combinations of a few prototype atoms in the low-resolution dictionary. We used the Bayesian compressive sensing (BCS) sparse recovery algorithm to find the sparse coefficients of the signals. We extracted the sparse coefficients and the corresponding active atoms in the low-resolution dictionary to construct new sparse coefficients corresponding to the high-resolution dictionary. Using the estimated atoms and the high-resolution dictionary, a new IVTC with more samples was constructed. Finally, by placing the new IVTC signals in the original IVTC positions, we were able to reconstruct the original echocardiography video with more frames. The proposed method does not require training of low-resolution and high-resolution dictionaries, nor does it require motion estimation; it does not blur fast-moving objects, and does not have blocking artifacts

24 citations

Dissertation
01 Jan 2011
TL;DR: In this paper, the authors focus on multimodale verwerking van visuele, infrarood and time-of-flight videobeelden, which result in significant improvements in real-time detectie.
Abstract: In dit proefschrift worden verschillende aspecten van een intelligent videogebaseerd branddetectiesysteem onderzocht. In een eerste luik ligt de nadruk op de multimodale verwerking van visuele, infrarood en time-of-flight videobeelden, die de louter visuele detectie verbetert. Om de verwerkingskost zo minimaal mogelijk te houden, met het oog op real-time detectie, is er voor elk van het type sensoren een set ’low-cost’ brandkarakteristieken geselecteerd die vuur en vlammen uniek beschrijven. Door het samenvoegen van de verschillende typen informatie kunnen het aantal gemiste detecties en valse alarmen worden gereduceerd, wat resulteert in een significante verbetering van videogebaseerde branddetectie. Om de multimodale detectieresultaten te kunnen combineren, dienen de multimodale beelden wel geregistreerd (~gealigneerd) te zijn. Het tweede luik van dit proefschrift focust zich hoofdzakelijk op dit samenvoegen van multimodale data en behandelt een nieuwe silhouet gebaseerde registratiemethode. In het derde en tevens laatste luik van dit proefschrift worden methodes voorgesteld om videogebaseerde brandanalyse, en in een latere fase ook brandmodellering, uit te voeren. Elk van de voorgestelde technieken voor multimodale detectie en multi-view lokalisatie zijn uitvoerig getest in de praktijk. Zo werden onder andere succesvolle testen uitgevoerd voor de vroegtijdige detectie van wagenbranden in ondergrondse parkeergarages.

21 citations