• Journal of the Korea Society of Computer and Information
• /
• v.18 no.11
• /
• pp.77-86
• /
• 2013

In this paper, we propose a fast video retargeting method which preserves the contents of a video and converts the image size. Since the conventional Seam Carving which is the well-known content-aware image retargeting technique uses the dynamic programming method, the repetitive update procedure of the accumulation energy is absolutely needed to obtain seam. The energy update procedure cannot avoid the processing time delay because of many operations by the image full-searching. By applying the proposed method, frames which have similar features in video are classified into a scene, and the first frame of a scene is resized by the modified Seam Carving where multiple seams are extracted from candidate seams to reduce the repetitive update procedure. After resizing the first frame of a scene, all continuous frames of the same scene are resized with reference to the seam information stored in the previous frame without the calculation of the accumulation energy. Therefore, although the fast processing is possible with reducing complexity and without analyzing all frames of scene, the quality of an image can be analogously maintained with an existing method. The experimental results show that the proposed method can preserve the contents of an image and can be practically applied to retarget the image on real time.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.1085-1088
• /
• 1999

This paper presents a method for soccer scene analysis and coordinate transformation from scene to ground model using a priori knowledge. First, the ground and spectator regions are separated, and various objects are extracted from the separated ground region. Second, an affine model is used for mapping the object positions on the soccer image into the position on the ground model. Problems regarding holes arising from mapping processing are solved using inverse mapping instead of a usual interpolation method. Experiments are performed on a PC using about 100 RGB images acquired at 240＊640 resolution and 3∼5 frames per second.

• Proceedings of the IEEK Conference
• /
• 2007.07a
• /
• pp.233-234
• /
• 2007

It is needed many images with different exposure to acquire high dynamic range (HDR) image of a scene using digital still camera. This paper proposed to acquire HDR image with small error using reduced number of image. Proposed method takes two pictures with different exposure and estimates dynamic range of scene using information two images, and takes three pictures with calculated proper exposure to acquire HDR image.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.605-608
• /
• 1999

In this paper, we proposed several scene analysis algorithms. These algorithms using image difference and histogram operate on the sequence of DC coefficient which is extracted from Motion JPEG or MPEG without full-frame decompression. Since DC sequence has the most information of full frame while it has reduced data. Experimental results show less than 1/64 of full frame analysing complexity and exactly analyze scene changes and extract key frames.

• Journal of Institute of Control, Robotics and Systems
• /
• v.10 no.5
• /
• pp.415-420
• /
• 2004

We present a new algorithm for the calibration of a camera and the recovery of 3D scene structure up to a scale from image sequences using known angles between lines in the scene. Traditional method for calibration using scene constraints requires various scene constraints due to the stratified approach. Proposed method requires only one type of scene constraint of known angle and also it directly recovers metric structure up to an unknown scale from projective structure. Specifically, we recover the matrix that is the homography between the projective structure and the Euclidean structure using angles. Since this matrix is a unique one in the given set of image sequences, we can easily deal with the problem of varying intrinsic parameters of the camera. Experimental results on the synthetic and real images demonstrate the feasibility of the proposed algorithm.

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10b
• /
• pp.277-282
• /
• 1993

In understanding concepts, there are two aspects; image and language. The point discussed in this paper is things fundamental in finding proper relations between objects in a scene to represent the meaning of the that whole scene properly through experiencing in image and language. It is assumed that one of the objects in a scene has letters as objects inside its contour. As the present system can deal with both figures and letters in a scene, the above assumption makes it easy for the system to infer the context of a scene. Several personal computers on the LAN network are used and they process items in parallel.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 1999.11a
• /
• pp.239-243
• /
• 1999

Mosaic image involves the information of 2D images about objects and background. In this paper, we describe how to construct the information from the mosaic image. We propose the animation method through which it efficiently changes a camera angle from a 2D scene to a 3D scene after it presumes a 3D scene in an assigned place in based on the information of 2D image.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.11 no.4
• /
• pp.107-115
• /
• 2008

Accurate extraction of traversable region is a critical issue for autonomous navigation of unmanned ground vehicle(UGV). This paper introduces enhanced extraction of traversable region by combining scene clustering with 3D world modeling using CCD(Charge-Coupled Device)/IR(Infra Red) image. Scene clustering is developed with K-means algorithm based on CCD and IR image. 3D world modeling is developed by fusing CCD and IR stereo image. Enhanced extraction of traversable regions is obtained by combining feature of extraction with a clustering method and a geometric characteristic of terrain derived by 3D world modeling.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.33 no.1 s.108
• /
• pp.33-48
• /
• 2005

The purpose of this study was to discover the landscape visual image of the slope scene and their harmony with surrounding sceneries. This research utilized the basic study tool of psycho-physics and processed the case study of ten types of slope construction scene along the highway. The analysis was performed by the data obtained from the questionnaires and the photos for the slope construction scene. The questionnaires for analysis the image of the slope construction scene and their harmony with surrounding sceneries were designed using semantic differential scale and 5 point Likert-scale. The major findings were as follows. 1. At the part of the visual preferences analysis, the slope revegetation methods showed high level of preferences generally than on the slope structure methods. While the slope revegetation methods were estimated friendly, continuity, harmonious, soft, light and wide, the slope revegetation methods were estimated unstable, female, static, simple, omnipresent, appeared as policeman of weak inclination. Also the slope structure methods were estimated stable, manly, complicated, steep and healthy but rough, unharmonious, unfamiliar and heavy. 2. Psychological factors, related to the satisfaction for the slope revegetation methods were composed of three factors, aesthetic, individuality and physical character. And the slope structure methods were composed of five factors, aesthetic, individuality, stability, physical character, and complexity. 3. At the part of harmony with surrounding landscapes, the slope revegetation methods were evaluated highly but the slope structure methods received the lowest evaluation. Also the harmony analysis with surrounding view on the slope revegetation methods showed degree of high more than average in all texture, form, color and scale but the slope structure methods showed degree of fewer than average degree in form, scale, color and texture.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.6 no.6
• /
• pp.951-957
• /
• 2002

When retrieving voluminous capacity of video image data, it is necessary to provide synopsized frame lists of video image data for indexing and replaying at the exact point where the user want to retrieve. We apply Mean Squared Error method to extract certain pixel value from diagonal direction of a frame. The RGB value of a pixel extracted from each frame is saved in a matrix form, and this frame is retrievedas a scene change point if the compared value of two points met the certain condition. Also implement the algorithm and provide a way to seize entire structure of video image and the point of scene changes. finally, we analyze and prove that our method has better performance compared with the others.