• Journal of Broadcast Engineering
• /
• v.19 no.1
• /
• pp.56-63
• /
• 2014

This paper deals with a binarization for plate number recognition. The binarization process converts an image into a binary image and plays an important role for automatically recognizing plate number. The rear license plate has often a shadowed image which causes erroneous binarized image due to non-uniform illumination. In this paper, a binarization method is proposed in which the shadow line is detected in a rear plate with a shadow. And then the histogram matching is conducted for the two image separated by the shadow line. After histogram matching, two images are joined and finally Otsu method is applied for the binarization. In the experiment, the proposed algorithm shows robust performance compared to the conventional method in the presence of estimation error in the shadow line.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.5
• /
• pp.1690-1710
• /
• 2014

In this paper, we propose the rapid implementation of a 3-dimensional (3D) facial reconstruction from a single frontal face image and introduce a design for its application on a mobile device. The proposed system can effectively reconstruct human faces in 3D using an approach robust to lighting conditions, and a fast method based on a Canonical Correlation Analysis (CCA) algorithm to estimate the depth. The reconstruction system is built by first creating 3D facial mapping from a personal identity vector of a face image. This mapping is then applied to real-world images captured with a built-in camera on a mobile device to form the corresponding 3D depth information. Finally, the facial texture from the face image is extracted and added to the reconstruction results. Experiments with an Android phone show that the implementation of this system as an Android application performs well. The advantage of the proposed method is an easy 3D reconstruction of almost all facial images captured in the real world with a fast computation. This has been clearly demonstrated in the Android application, which requires only a short time to reconstruct the 3D depth map.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.40 no.4
• /
• pp.201-209
• /
• 2007

Line transect sampling in a sighting survey is one of most widely used methods for assessing animal abundance. This study applied distance data, collected from three sighting surveys using line transects for finless porpoise that were conducted in 2004 and 2005 off the west coast of Korea, to four models (hazard-rate, uniform, half-normal and exponential) that can use a variety of detection functions, g (x). The hazard-rate model, a derived model for the detection function, should have a shoulder condition chosen using the AIC (Akaike Information Criterion), as the most suitable model. However, it did not describe a shoulder shape for the value of g(x) near the track tine and underestimated g (x), just as the exponential model did. The hazard-rate model showed a bias toward overestimating the densities of finless porpoises with a higher coefficient of variation (CV) than the other models did. The uniform model underestimated the densities of finless porpoise but had the lowest CV. The half-normal model described a detection function with a shape similar to that of the uniform model. The half-normal model was robust for finless porpoise data and should be able to avoid density underestimation. The estimated abundance of finless porpoise was 3,602 individuals (95% CI=1,251-10,371) inshore in 2005 and 33,045 individuals (95% CI=24,274-44,985) offshore in 2004.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.2
• /
• pp.10-23
• /
• 2009

The fundamental matrix and key frame selection are one of the most important techniques to recover full 3D reconstruction of objects from turntable sequences. This paper proposes a new algorithm that estimates a robust fundamental matrix for camera calibration from uncalibrated images taken under turn-table motion. Single axis turntable motion can be described in terms of its fixed entities. This provides new algorithms for computing the fundamental matrix. From the projective properties of the conics and fundamental matrix the Euclidean 3D coordinates of a point are obtained from geometric locus of the image points trajectories. Experimental results on real and virtual image sequences demonstrate good object reconstructions.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.6
• /
• pp.746-753
• /
• 2008

In this paper, we introduce the improved control method are communicated between a master and a slave robot in the teleoperation systems. When the master and slave robots are located in different places, time delay is unavoidable under the network environment and it is well known that the system can become unstable when even a small time delay exists in the communication channel. The time delay may cause instability in teleoperation systems especially if those systems include haptic feedback. This paper presents a control scheme based on the estimator with virtual master model in teleoperation systems over the network. As the behavior of virtual model is tracking the one of master model, the operator can control real master robot by manipulating the virtual robot. And LQG/LTR scheme was adopted for the compensation of un-modeled dynamics. The approach is based on virtual master model, which has been implemented on a robot over the network. Its performance is verified by the computer simulation and the experiment.

• The KIPS Transactions:PartB
• /
• v.18B no.4
• /
• pp.193-200
• /
• 2011

This paper proposes a low-cost visual analyzer algorithm of human body motion for real-time applications such as human-computer interfacing, virtual reality applications in medicine and telemonitoring of patients. To reduce cost of its use, we design the algorithm to use a single camera. To make the proposed system to be used more conveniently, we avoid from using optical markers. To make the proposed algorithm be convenient for real-time applications, we design it to have a closed-form with high accuracy. To design a closed-form algorithm, we propose an idea that formulates motion of a human body joint as a 2D universal joint model instead of a common 3D spherical joint model, without any kins of approximation. To make the closed-form algorithm has high accuracy, we formulates the estimation process to be an optimization problem. Thus-desined algorithm is applied to each joint of the human body one after another. Through experiments we show that human body motion capturing can be performed in an efficient and robust manner by using our algorithm.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.7 no.6
• /
• pp.1413-1422
• /
• 2012

Adaptive back stepping control technique may provide robust control characteristics under parameter perturbation caused by changing external condition. In order to synthesize a high-precision velocity controller for IPMSM(Interior Permanent Magnet Synchronous Motor) using this method, the period of control loop should be very small. However, because of the resolution of the encoder for speed measurement, control cycle is limited, which makes it difficult to improve the performance of the controller. This paper proposes a velocity controller design method based on nonlinear adaptive back-stepping method to accomplish fast and accurate performance. Here, an EKF(Extended Kalman Filter) method is incorporated for the estimation of the motor speed into the design of a speed controller using adapted back-stepping control technique. The performance of the proposed controller is demonstrated through simulation using PSIM.

• Journal of Digital Contents Society
• /
• v.11 no.4
• /
• pp.597-606
• /
• 2010

This paper describes a real-time camera tracking framework specifically designed to track a monocular camera in an AR workspace. Typically, the Kalman filter is often employed for the camera tracking. In general, however, tracking performances of conventional methods are seriously affected by unpredictable situations such as ambiguity in feature detection, occlusion of features and rapid camera shake. In this paper, a recursive Bayesian sampling framework which is also known as the particle filter is adopted for the camera pose estimation. In our system, the camera state is estimated on the basis of the Gaussian distribution without employing additional uncertainty model and sample weight computation. In addition, the camera state is directly computed based on new sample particles which are distributed according to the true posterior of system state. In order to verify the proposed system, we conduct several experiments for unstable situations in the desktop AR environments.

• The Journal of the Acoustical Society of Korea
• /
• v.34 no.4
• /
• pp.316-320
• /
• 2015

In this paper, the pole filtering concept is applied to the Mel-frequency cepstral coefficient (MFCC) feature vectors in the conventional cepstral mean normalization (CMN) and cepstral mean and variance normalization (CMVN) frameworks. Additionally, performance of the cepstral mean and scale normalization (CMSN), which uses scale normalization instead of variance normalization, is evaluated in speech recognition experiments in noisy environments. Because CMN and CMVN are usually performed on a per-utterance basis, in case of short utterance, they have a problem that reliable estimation of the mean and variance is not guaranteed. However, by applying the pole filtering and scale normalization techniques to the feature normalization process, this problem can be relieved. Experimental results using Aurora 2 database (DB) show that feature normalization method combining the pole-filtering and scale normalization yields the best improvements.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• v.1
• /
• pp.333-335
• /
• 2006

Position of surface objects can be fixed in many ways. The most popular radionavigational systems, including satellite systems, make possible obtaining nearly continuous and very precise ship's position. However, under the water application of radionavigational systems is impossible. Underwater navigation requires other tools and solutions then these encountered in surface and air navigation. In underwater environment vehicles and submarines, operate that have to possess alternative navigational systems. Underwater vehicles, in order to perform their tasks require accurate information about their own, current position. At present, they are equipped with inertial navigational systems (INS). Accuracy of INS is very high but in relatively short periods. Position error is directly proportional to time of working of the system. The basic feature of INS is its autonomy and passivity. This characteristic mainly decides that INS is broadly used on submarines and other underwater vehicles. However, due to previously mentioned shortcoming i.e. gradually increasing position error, periodical calibration of the system is necessary. The simplest calibration method is surface or nearly surface application of GPS system. Another solution, which does not require interruption of performed task and emergence on the surface, is application of comparative navigation technique. Information about surrounding environment of the ship, obtained e.g. by means sonic depth finder or board sonar, and comparing it with accessible pattern can be used in order to fix ship's position. The article presents a structure and a description of working of underwater vehicle navigation system simulator. The simulator works on the basis of comparative navigation methods which exploit in turn digital images of echograms and sonograms. The additional option of the simulator is ability to robust estimation of measurements. One can do it in order to increase accuracy of position fixed with comparative navigation methods application. The simulator can be a basis to build future underwater navigation system.