• Journal of Navigation and Port Research
• /
• v.32 no.5
• /
• pp.355-361
• /
• 2008

Stereo matching is one of the most active research areas in computer vision. In this paper, we propose a stereo matching scheme using genetic algorithm for object depth recognition. The proposed approach considers the matching environment as an optimization problem and finds the optimal solution by using an evolutionary strategy. Accordingly, genetic operators are adapted for the circumstances of stereo matching. An individual is a disparity set. Horizontal pixel line of image is considered as a chromosome. A cost function is composed of certain constraints which are commonly used in stereo matching. Since the cost function consists of intensity, similarity and disparity smoothness, the matching process is considered at the same time in each generation. The LoG(Laplacian of Gaussian) edge is extracted and used in the determination of the chromosome. We validate our approach with experimental results on stereo images.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.22 no.11
• /
• pp.2543-2551
• /
• 1997

This paper proposes a compression technique of image data, a variable length PN code and channel models which are required in CDMA communication system. It also analyzes their performances. Original images is compressed by 2-D DCT and its coefficients are quantized by optimal quantizer at compression rate 0.84bit/pel. Channel model 1 and 2 which are composed of 5 and 4 channels respectively are employed to be used in CDMA. Such a situation forces us to empoly variable length PN code, such as Chebyshev map for spread spectrum system. When average PN code length of model 1 and 2 is 44.4 and 26.7 chips respectively, the received image through these models under Gaussian noise with variance 1.75 is visually of the same quality as the transmitting image. Thus, the model 2 appears to be better in channel efficiency, comparing with channel model 1 and channel model which uses fixed length PN code.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.26 no.7
• /
• pp.157-165
• /
• 1989

To recover three dimensional information in Shape from Texture, the distorting effects of projection must be distinguished from properties of the texture on which the distortion acts. In this paper, we show an approximated maximum likelihood estimation method in which we find surface orientation of the visible surface (hemisphere) in gaussian sphere using local analysis of the texture. In addition, assuming that an orthogonal projection and a circle is an image formation system and a texel (texture element) respectively, we drive the surface orientation from the distribution of variation by means of orthogonal projection of a tangent direction which exists regularly in the arc length of a circle. We present the orientation parameters of textured surface with slant and tilt in gradient space, and also the surface normal of the resulted surface orientationas as needle map. This algorithm is applied to geographic contour (artificially generated chejudo) and synthetic texture.

• Transactions on Control, Automation and Systems Engineering
• /
• v.3 no.4
• /
• pp.283-288
• /
• 2001

In this paper, we proposed a method for extracting facial characteristics of human being in an image. Given a pair of gray level sample images taken with and without human being, the face of human being is segmented from the image. Noise in the input images is removed with the help of Gaussian filters. Edge maps are found of the two input images. The binary edge differential image is obtained from the difference of the two input edge maps. A mask for face detection is made from the process of erosion followed by dilation on the resulting binary edge differential image. This mask is used to extract the human being from the two input image sequences. Features of face are extracted from the segmented image. An effective recognition system using the discrete wave let transform (DWT) is used for recognition. For extracting the facial features, such as eyebrows, eyes, nose and mouth, edge detector is applied on the segmented face image. The area of eye and the center of face are found from horizontal and vertical components of the edge map of the segmented image. other facial features are obtained from edge information of the image. The characteristic vectors are extrated from DWT of the segmented face image. These characteristic vectors are normalized between +1 and -1, and are used as input vectors for the neural network. Simulation results show recognition rate of 100% on the learned system, and about 92% on the test images.

• The Bulletin of The Korean Astronomical Society
• /
• v.35 no.1
• /
• pp.28.2-28.2
• /
• 2010

We have investigated seven Extreme-Ultraviolet (EUV) bright points in the active region (AR 10926) on 2006 December 2 by the EUV imaging spectrometer (EIS) onboard Hinode spacecraft. We determined their Doppler velocities and non-thermal velocities from 15 EUV spectral lines (log T=4.7-7.2) by fitting each line profile to a Gaussian function. We present the Doppler velocity map as a function of temperature which corresponds to a different height. As a result, these active region bright points show two different types of characteristics. Type 1 bright point shows a systematic increase of Doppler velocity from -68 km/s (blue shift) at log T=4.7 to 27 km/s (red shift) at log T=6.7, while type 2 bright points have Doppler velocities in the range of -20 km/s and 20 km/s. Using MDI magnetograms, we found that only type 1 bright point was associated with the canceling magnetic feature at the rate of $2.4{\times}10^{18}$ Mx/hour. When assuming that these bright points are caused by magnetic reconnection and the Doppler shift indicates reconnection out flow, the pattern of the Doppler shift implies that type 1 bright point should be related to low atmosphere magnetic reconnection. We also determined electron densities from line ratio as well as temperatures from emission measure loci using CHIANTI atomic database. The electron densities of all bright points are comparable to typical values of active regions (log Ne=9.9-10.4). For the temperature analysis, the emission loci plots indicate that these bright points should not be isothermal though background is isothermal. The DEM analysis also show that while the background has a single peak distribution (isothermal), the EUV bright points, double peak distributions.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.47 no.4
• /
• pp.47-54
• /
• 2010

We propose a smart human-computer interface replacing conventional mouse interface. The interface is able to control cursor and command action with only hand performing without object. Four finger motions(left click, right click, hold, drag) for command action are enough to express all mouse function. Also we materialize cursor movement control using image processing. The measure what we use for inference is entropy of EMG signal, gaussian modeling and maximum likelihood estimation. In image processing for cursor control, we use color recognition to get the center point of finger tip from marker, and map the point onto cursor. Accuracy of finger movement inference is over 95% and cursor control works naturally without delay. we materialize whole system to check its performance and utility.

• Korean Journal of Optics and Photonics
• /
• v.25 no.5
• /
• pp.273-278
• /
• 2014

We present an algorithm for surface reconstruction from the second-derivative data for free-form aspherics, which uses a subaperture scanning system that measures the local surface profile and determines the three second-derivative values at those local sampling points across the free-form surface. The three second-derivative data were integrated to get a map of x- and y-slopes, which went through a second Southwell integration step to reconstruct the surface profile. A synthetic free-form surface 200 mm in diameter was simulated. The simulation results show that the reconstruction error is 19 nm RMS residual difference. Finally, the sensitivity to noise is diagnosed for second-derivative Gaussian random noise with a signal to noise ratio (SNR) of 16, the simulation results proving that the suggested method is robust to noise.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.3
• /
• pp.353-360
• /
• 2012

This paper describes a SLAM method which estimates landmark locations and robot pose simultaneously. The particle filter can deal with nonlinearity of robot motion as well as the non Gaussian property of robot motion uncertainty and sensor error. The state to be estimated includes the locations of landmarks in addition to the robot pose. In the experiment, four beacons which transmit ultrasonic signal are used as landmarks. The robot receives the ultrasonic signals from the beacons and detects the distance to them. The method uses rang scanning sensor to build geometric feature of the environment. Since robot location and heading are estimated by the particle filter, the scanned range data can be converted to the geometric map. The performance of the method is compared with that of the deadreckoning and trilateration.

• Korean Journal of Remote Sensing
• /
• v.24 no.5
• /
• pp.483-496
• /
• 2008

Qualified ground control points (GCPs) are required to construct a digital elevation model (DEM) from a pushbroom stereo pair. An inverse geolocation algorithm for extracting GCPs from ERS SAR data and the SRTM DEM was recently developed. However, not all GCPs established by this method are accurate enough for direct application to the geometric correction of pushbroom images such as SPOT, IRS, etc, and thus a method for selecting and removing inaccurate points from the sets of GCPs is needed. In this study, we propose a method for evaluating GCP accuracy and winnowing sets of GCPs through orientation modeling of pushbroom image and validate performance of this method using SPOT stereo pair of Daejon City. It has been found that the statistical distribution of GCP positional errors is approximately Gaussian without bias, and that the residual errors estimated by orientation modeling have a linear relationship with the positional errors. Inaccurate GCPs have large positional errors and can be iteratively eliminated by thresholding the residual errors. Forty-one GCPs were initially extracted for the test, with mean the positional error values of 25.6m, 2.5m and -6.1m in the X-, Y- and Z-directions, respectively, and standard deviations of 62.4m, 37.6m and 15.0m. Twenty-one GCPs were eliminated by the proposed method, resulting in the standard deviations of the positional errors of the 20 final GCPs being reduced to 13.9m, 8.5m and 7.5m in the X-, Y- and Z-directions, respectively. Orientation modeling of the SPOT stereo pair was performed using the 20 GCPs, and the model was checked against 15 map-based points. The root mean square errors (RMSEs) of the model were 10.4m, 7.1m and 12.1m in X-, Y- and Z-directions, respectively. A SPOT DEM with a 20m ground resolution was successfully constructed using a automatic matching procedure.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.21 no.6
• /
• pp.171-181
• /
• 2011

Proposed in this paper is the intelligent video surveillance system to effectively detect multiple loitering objects even that disappear from the out of camera's field of view and later return to a target zone. After the background and foreground are segmented using Gaussian mixture model and shadows are removed, the objects returning to the target zone is recognized using the chromaticity histogram and the duration of loitering is preserved. For more accurate measurement of the loitering behavior, the camera calibration is also applied to map the image plane to the real-world ground. Hence, the loitering behavior can be detected by considering the time duration of the object's existence in the real-world space. The experiment was performed using loitering video and all of the loitering behaviors are accurately detected.