• ETRI Journal
• /
• v.33 no.4
• /
• pp.506-516
• /
• 2011

In this paper, we develop a registration method to eliminate the geometric inconsistency between the stereo-images and light detection and ranging (LIDAR) data obtained by an airborne multisensor system. This method consists of three steps: registration primitive extraction, correspondence establishment, and exterior orientation parameter (EOP) adjustment. As the primitives, we employ object points and linked edges from the stereo-images and planar patches and intersection edges from the LIDAR data. After extracting these primitives, we establish the correspondence between them, being classified into vertical and horizontal groups. These corresponding pairs are simultaneously incorporated as stochastic constraints into aerial triangulation based on the bundle block adjustment. Finally, the EOPs of the images are adjusted to minimize the inconsistency. The results from the application of our method to real data demonstrate that the inconsistency between both data sets is significantly reduced from the range of 0.5 m to 2 m to less than 0.05 m. Hence, the results show that the proposed method is useful for the data fusion of aerial images and LIDAR data.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.04a
• /
• pp.904-907
• /
• 2014

In this work we present a robust and fast approach to estimate 3D vehicle pose that can provide results under a specific traffic surveillance conditions. Such limitations are expressed by single fixed CCTV camera that is located relatively high above the ground, its pitch axes is parallel to the reference plane and the camera focus assumed to be known. The benefit of our framework that it does not require prior training, camera calibration and does not heavily rely on 3D model shape as most common technics do. Also it deals with a bad shape condition of the objects as we focused on low resolution surveillance scenes. Pose estimation task is presented as PnP problem to solve it we use well known "POSIT" algorithm [1]. In order to use this algorithm at least 4 non coplanar point's correspondence is required. To find such we propose a set of techniques based on model and scene geometry. Our framework can be applied in real time video sequence. Results for estimated vehicle pose are shown in real image scene.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.4
• /
• pp.309-314
• /
• 2015

In this study, an embedded ranging system based on a laser structured light image is developed. The distance measurement by the structured light image processing has efficient computation because the burdensome correspondence problem is avoidable. In order to achieve robustness against environmental illumination noise and real-time laser structured light image processing, a bandpass optical filter is adopted in this study. The proposed ranging system has an embedded image processor performing the whole image processing and distance measurement, and so reduces the computational burden in the main control system. A system calibration algorithm is presented to compensate for the lens distortion.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10b
• /
• pp.1758-1763
• /
• 1991

This paper describes a new method to determine the 3D-shape of objects consisting of specular planar surfaces. This method exploits a light source which is made of a diffuse plane with a grid pattern encoded in an M-sequence and uses a single image of the light source reflected by the objects to acquiring orientations and positions of the surfaces of the objects. When grid lines of the light source are reflected by a specular planar surface and perspectively projected on an image plane, a set of lines vanishing at a point are obtained on the image plane. The orientation of the specular planar surface is determined by using the vanishing point, and the position is determined by using the correspondence between lines on the image and lines on the light source, which is obtained by employing a characteristic regularity of the M-sequence. Before the vanishing points are calculated, the lines on the image are classified and correlated with the surfaces of objects by using slopes and positions of the lines and the regularity of the M-sequence. This method requires only a single image.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.24 no.12
• /
• pp.122-130
• /
• 2010

This paper presents an active ranging system based on laser structured-light image. The structured-light image processing is computationally efficient in comparison with the conventional stereo image processing, since the burdensome correspondence problem is avoidable. In order to achieve robustness against environmental illumination noise, an efficient image processing algorithm, i.e., integration of difference images with structured-light modulation is proposed. Distance equation from the measured structured light pixel distance and system parameter calibration are addressed in this paper. Experiments and analysis are carried out to verify performance of the proposed ranging system.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.12 no.4
• /
• pp.524-531
• /
• 2009

In this paper, we propose an automatic image registration method for multi-sensor image fusion such as visible and infrared images. The registration is achieved by finding corresponding feature points in both input images. In general, the global statistical correlation is not guaranteed between multi-sensor images, which bring out difficulties on the image registration for multi-sensor images. To cope with this problem, mutual information is adopted to measure correspondence of features and to select faithful points. An update algorithm for projective transform is also proposed. Experimental results show that the proposed method provides robust and accurate registration results.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.1887-1890
• /
• 2003

This paper presents a three-dimensional (3D) head pose estimation algorithm using the stereo image. Given a pair of stereo image, we automatically extract several important facial feature points using the disparity map, the gabor filter and the canny edge detector. To detect the facial feature region , we propose a region dividing method using the disparity map. On the indoor head & shoulder stereo image, a face region has a larger disparity than a background. So we separate a face region from a background by a divergence of disparity. To estimate 3D head pose, we propose a 2D-3D Error Compensated-SVD (EC-SVD) algorithm. We estimate the 3D coordinates of the facial features using the correspondence of a stereo image. We can estimate the head pose of an input image using Error Compensated-SVD (EC-SVD) method. Experimental results show that the proposed method is capable of estimating pose accurately.

• Asia Marketing Journal
• /
• v.13 no.4
• /
• pp.29-54
• /
• 2012

Recently, as film has been admitted as the artistic merit and higher value-added business, the past studies on film have been lively carried on various fields. Especially, the film business is thought to be value-added business and has explored the causes of influencing spectators. However, there are no researches enough to explain what induces the choice and diffusion of the film. The film is not only hedonic products but also typical example of experiential products. So how to process film formation plays important roles in explaining the procedures of forming preference on the film and the movies spread more widely. But the great part of study of films has been concentrated on exploring hedonic factors of influencing spectator's choice. Until now there is not enough study for the relationship between experiential information processing and film preference. To explain film's preference, our study focuses on preference fluency and processing fluency that can provide an insight for our question about the relationship. In this article, to explain the procedures of processing experiential information and forming preference on the film, our study focuses on finding the relationship between film's processing fluency and film's preference fluency and explores the factors that affect film's processing fluency. To achieve the goal of this study, we distinguish factors of film's conceptual fluency from factors of film's perceptual fluency and explore the paths from the factors to film's preference fluency. The factors which have effects on perceptual fluency are hypothesized to be distinction of image expression, distinction of sound expression, correspondence between actors' image and their role. The factors which have effect on conceptual fluency are supposed to be well-organized story, suitability of lines expression. The experiments in which students were sampled at 'C' university were conducted in 2010 (december). Data collection was proceeded through questionnaires. We test the hypothesized model by using structural equation modeling(Amos 17.0). The fit indices for the model are as follows : x²=416.266(df=213, p=0.00), GFI=0.855, AGFI=0.812, RMSEA =0.069, IFI=O.925, CFI=0.920, TLI=0.905. According to the guidelines, there is evidence that our measurement model fits data. The results of empirical study are as follows. The path from film's perceptual fluency to film's preference fluency is supported(estimate: 0.223, C.R: 2.641). The path from film's conceptual fluency to film's preference fluency is supported(estimate: 0.397, C.R: 4.863). The path from distinction of image expression to film's perceptual fluency is not supported(estimate: 0.113, C.R: 1.665). The path from distinction of sound expression to film's perceptual fluency is supported (estimate: 0.190, C.R: 2.042). The path from correspondence between actors' image and their role to film's perceptual fluency is supported(estimate: 0.686, C.R: 5.566). The path from well-organized story to film's conceptual fluency is supported(estimate: 0.396, C.R: 4.023). The path from suitability of lines expression to film's conceptual fluency is supported(estimate: 0.536, C.R: 5.441). Concludingly, our study explored the influencing factors of film's processing fluency inducing film's Preference fluency. First, film's perceptual fluency and film's conceptual fluency have positive effects on film's preference fluency. Second, distinction of image expression is not significant on film's perceptual fluency, but distinction of sound expression and image's correspondence of actors' image and their role have positive effects on film's perceptual fluency. Lastly, well-organized story and suitability of lines expression have positive effects on film's conceptual fluency.

• Radiation Oncology Journal
• /
• v.35 no.2
• /
• pp.101-111
• /
• 2017

The number of imaging data sets has significantly increased during radiation treatment after introducing a diverse range of advanced techniques into the field of radiation oncology. As a consequence, there have been many studies proposing meaningful applications of imaging data set use. These applications commonly require a method to align the data sets at a reference. Deformable image registration (DIR) is a process which satisfies this requirement by locally registering image data sets into a reference image set. DIR identifies the spatial correspondence in order to minimize the differences between two or among multiple sets of images. This article describes clinical applications, validation, and algorithms of DIR techniques. Applications of DIR in radiation treatment include dose accumulation, mathematical modeling, automatic segmentation, and functional imaging. Validation methods discussed are based on anatomical landmarks, physical phantoms, digital phantoms, and per application purpose. DIR algorithms are also briefly reviewed with respect to two algorithmic components: similarity index and deformation models.

• Journal of Information Display
• /
• v.5 no.4
• /
• pp.31-37
• /
• 2004

In this paper, an effective method for reconstruction of stereoscopic image pair through the regularized adaptive disparity estimation is proposed. Although the conventional adaptive disparity window matching can sharply improve the PSNR of a reconstructed stereo image, but there still exist some problems of overlapping between the matching windows and disallocation of the matching windows, because the size of the matching window tend to changes adaptively in accordance with the magnitude of the feature values. In the proposed method, the problems relating to the conventional adaptive disparity estimation scheme can be solved and the predicted stereo image can be more effectively reconstructed by regularizing the extimated disparity vector with the neighboring disparity vectors. From the experimental results, it is found that the proposed algorithm show improvements the PSNR of the reconstructed right image by about 2.36${\sim}$2.76 dB, on average, compared with that of conventional algorithms.