• IEMEK Journal of Embedded Systems and Applications
• /
• v.11 no.3
• /
• pp.163-171
• /
• 2016

Lane detection is a widely researched topic. Although simple road detection is easily achieved by previous methods, lane detection becomes very difficult in several complex cases involving noisy edges. To address this, we use a Convolution neural network (CNN) for image enhancement. CNN is a deep learning method that has been very successfully applied in object detection and recognition. In this paper, we introduce a robust lane detection method based on a CNN combined with random sample consensus (RANSAC) algorithm. Initially, we calculate edges in an image using a hat shaped kernel, then we detect lanes using the CNN combined with the RANSAC. In the training process of the CNN, input data consists of edge images and target data is images that have real white color lanes on an otherwise black background. The CNN structure consists of 8 layers with 3 convolutional layers, 2 subsampling layers and multi-layer perceptron (MLP) of 3 fully-connected layers. Convolutional and subsampling layers are hierarchically arranged to form a deep structure. Our proposed lane detection algorithm successfully eliminates noise lines and was found to perform better than other formal line detection algorithms such as RANSAC

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.1
• /
• pp.169-174
• /
• 2010

This paper explains end-point detection method for better speech recognition rates. The proposed method determines speech and non-speech region with the entropy and the harmonic detection of speech. The end-point detection using entropy on the speech spectral energy has good performance at the high SNR(SNR 15dB) environments. At the low SNR environment(SNR 0dB), however, the threshold level of speech and noise varies, so the precise end-point detection is difficult. Therefore, this paper introduces the end-point detection methods which uses speech spectral entropy and harmonics. Experiment shows better performance than the conventional entropy methods.

• Journal of Digital Contents Society
• /
• v.10 no.4
• /
• pp.597-604
• /
• 2009

For the improvement of license plate recognition system, correct extraction of a license plate region as well as character recognition is important. In this paper, with the analysis and classification of the error patterns in the process of plate region extraction, we tried to improve the extraction of the region using HoG(histogram of gradient) features and Adaboost. The results show that the HoG feature is robust to the noise and various types of the plates, and also is very effective to extract the region failed before.

• Proceedings of the Korea Society for Energy Engineering kosee Conference
• /
• 1997.10a
• /
• pp.17-23
• /
• 1997

A methodology for on-line data reconciliation and optimization has been proposed to minimize the energy cost of a utility system. As industrial data tend to be corrupted by noise or gross error, fast and robust data reconciliation technique is essential for the on-line optimization of utility system. Thus, we propose the hierarchical decomposition approach that can be applicable to on-line data reconciliation and optimization. As this approach divides whole system into several subsystems and removes the nonlinearity of constraint systematically, it handles complexity of system easily and shows good performance in accuracy and computation speed. Through case studies, we prove that this methodology is a good candidate for on-line data reconciliation and optimization.

• Journal of Sensor Science and Technology
• /
• v.27 no.4
• /
• pp.209-215
• /
• 2018

Recent research in animal behavior has shown that gradient information plays an important role in finding food and home. It is also important in optimization of performance because it indicates how the inputs should be adjusted for maximization/minimization of a performance index. We introduce perturbation as an additional input to obtain gradient information. Unlike the typical approach of calculating the gradient from the derivative, the proposed processing is very robust to noise since it is performed as a summation. Experimental results prove the validity of the process of spatial gradient acquisition. Quantitative indices for measuring the effect of the amplitude and the frequency are developed based on linear regression analysis. Drones are very useful for environmental monitoring and an autonomous path planning is required for unstructured environment. Guiding the drone for finding the origin of the interested physical property is done by estimating the gradient of the sensed value and generating the drone trajectories in the direction which maximizes the sensed value. Simulation results show that the proposed method can be successfully applied to identify the source of the physical quantity of interest by utilizing it for path planning of an autonomous drone in 3D environment.

• Journal of Ocean Engineering and Technology
• /
• v.16 no.1
• /
• pp.64-70
• /
• 2002

This paper shows the results of the development of a small size of digital type continuous and intermittent welding auto-carriage based on microprocessor (Intel 80196KC) for welding process with long welding line. The developed welding auto-carriage loads welding torch and tracks welding line. It is an automaton largely used for welding process with a lot of long welding lines such as shipbuilding and structure. Most traditional auto-carriages have been developed based on analog circuit for open loop control. So this analog circuit welding auto-carriage cannon control welding speed. Specially welding auto-carriage for intermittent welding condition is so complicated and has the low precision of control performance in welding distance and non-welding distance. The auto-carriage developed in this paper has the following characteristics: It has not only functions of traditional carriage but also functions such as pseudo-welding process of big iron structures, intermittent welding in order to limit heat for welding thin plates, crater treatment of the final step of welding, acceleration at the initial step of welding and deceleration in the final step of welding. The main control board of auto-carriage, power supply system and DC motor drive wee developed and manufactured. The welding speed and the welding distance of the developed auto-carriage are controlled accurately by feedback control using photo-sensor. Hardware and software robust against the heat and noise produced on the welding process are developed.

• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.9
• /
• pp.956-962
• /
• 2008

This paper is devoted to yarn tension control problem in winding machines. The passive take-up unit is replaced by active one with ADRC(Active Disturbance Rejection Control) and it was compared with the method using conventional PD(Proportional-Derivative) controller. The main part of ADRC is ESO(Extended State Observer) which continuously estimates nonlinearities of the system, such as intrinsic nonlinearity, external disturbance and sensor noise. Then the estimated nonlinearity is used to compensate the real one, thus making controlled system linear. A number of experiments have been conducted in order to verify the performance of the original winding system to the modified one. Experiments have shown improved efficiency of the system with adopting active yarn tension control. Experimental results show that the ADRC achieves a better tension response than PD controller and is robust to parameters variation.

• Structural Monitoring and Maintenance
• /
• v.4 no.4
• /
• pp.301-329
• /
• 2017

Impedance-based damage detection method has been known as an innovative tool with various successful implementations for structural health monitoring of civil structures. To monitor the local critical area of a structure, the impedance-based method utilizes the high-frequency impedance responses sensed by piezoelectric sensors as the local dynamic features. In this paper, current advances and future challenges of the impedance-based structural health monitoring are presented. Firstly, theoretical background of the impedance-based method is outlined. Next, an overview is given to recent advances in the wireless impedance sensor nodes, the interfacial impedance sensing devices, and the temperature-effect compensation algorithms. Various research works on these topics are reviewed to share up-to-date information on research activities and implementations of the impedance-based technique. Finally, future research challenges of the technique are discussed including the applicability of wireless sensing technology, the predetermination of effective frequency bands, the sensing region of impedance responses, the robust compensation of noise and temperature effects, the quantification of damage severity, and long-term durability of sensors.

• Smart Structures and Systems
• /
• v.19 no.4
• /
• pp.393-402
• /
• 2017

Many vibration-based global damage detection methods attempt to extract modal parameters from vibration signals as the main structural features to detect damage. The local flexibility method is one promising method that requires only the first few fundamental modes to detect not only the location but also the extent of damage. Generally, the mode shapes in the lateral degree of freedom are extracted from lateral vibration signals and then used to detect damage for a beam structure. In this study, a new approach which employs the mode shapes in the rotary degree of freedom obtained from the macro-strain vibration signals to detect damage of a beam structure is proposed. In order to facilitate the application of mode shapes in the rotary degree of freedom for beam structures, the local flexibility method is modified and utilized. The proposed rotary approach is verified by numerical and experimental studies of simply supported beams. The results illustrate potential feasibility of the proposed new idea. Compared to the method that uses lateral measurements, the proposed rotary approach seems more robust to noise in the numerical cases considered. The sensor configuration could also be more flexible and customized for a beam structure. Primarily, the proposed approach seems more sensitive to damage when the damage is close to the supports of simply supported beams.

• Journal of Computing Science and Engineering
• /
• v.8 no.2
• /
• pp.119-128
• /
• 2014

The appearance of retinal blood vessels is an important diagnostic indicator of serious disease, such as hypertension, diabetes, cardiovascular disease, and stroke. Automatic segmentation of the retinal vasculature is a primary step towards automatic assessment of the retinal blood vessel features. This paper presents an automated method for the enhancement and segmentation of blood vessels in fundus images. To decrease the influence of the optic disk, and emphasize the vessels for each retinal image, a multidirectional morphological top-hat transform with rotating structuring elements is first applied to the background homogenized retinal image. Then, an improved multiscale line detector is presented to produce a vessel response image, and yield the retinal blood vessel tree for each retinal image. Since different line detectors at varying scales have different line responses in the multiscale detector, the line detectors with longer length produce more vessel responses than the ones with shorter length; the improved multiscale detector combines all the responses at different scales by setting different weights for each scale. The methodology is evaluated on two publicly available databases, DRIVE and STARE. Experimental results demonstrate an excellent performance that approximates the average accuracy of a human observer. Moreover, the method is simple, fast, and robust to noise, so it is suitable for being integrated into a computer-assisted diagnostic system for ophthalmic disorders.