• Journal of Institute of Control, Robotics and Systems
• /
• v.8 no.9
• /
• pp.776-787
• /
• 2002

Automation of welding process in shipyards is ultimately necessary, since the welding site is spatially enclosed by floors and girders, and therefore welding operators are exposed to hostile working conditions. To solve this problem, a welding mobile robot that can navigate autonomously within the enclosure has been developed. To achieve the welding task in the closed space, the robotic welding system needs a sensor system for the working environment recognition and the weld seam tracking, and a specially designed environment recognition strategy. In this paper, a three-dimensional laser vision system is developed based on the optical triangulation technology in order to provide robots with 3D work environmental map. Using this sensor system, a spatial filter based on neural network technology is designed for extracting the center of laser stripe, and evaluated in various situations. An environment modeling algorithm structure is proposed and tested, which is composed of the laser scanning module for 3D voxel modeling and the plane reconstruction module for mobile robot localization. Finally, an environmental recognition strategy for welding mobile robot is developed in order to recognize the work environments efficiently. The design of the sensor system, the algorithm for sensing the partially structured environment with plane segments, and the recognition strategy and tactics for sensing the work environment are described and discussed with a series of experiments in detail.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.2C
• /
• pp.162-171
• /
• 2003

It is difficult to reuse the captured motion data, because the data has a difficulty in editing it. In this paper, a uniform posture mar (UPM) algorithm, one of unsupervised learning neural network is proposed to edit the captured motion data. Because it needs much less computational cost than other motion editing algorithms, it is adequate to apply in teal-time applications. The UPM algorithm prevents from generating an unreal posture in learning phase. It not only makes more realistic motion curves, but also contributes to making more natural motions. Above of all, it complements the weakness of the existing algorithm where the calculation quantity increases in proportion to increase the number of restricted condition to solve the problems of high order articulated body. In this paper, it is shown two applications as a visible the application instance of UPM algorithm. One is a motion transition editing system, the other is a inductive inverse kinematics system. This method could be applied to produce 3D character animation based on key frame method, 3D game, and virtual reality, etc.

• Korean Journal of Agricultural Science
• /
• v.47 no.3
• /
• pp.633-644
• /
• 2020

Rice paper is an element of Vietnamese cuisine that can be used to wrap vegetables and meat. Rice and starch are the main ingredients of rice paper and their mixing ratio is important for quality control. In a commercial factory, assessment of food safety and quantitative supply is a challenging issue. A rapid and non-destructive monitoring system is therefore necessary in commercial production systems to ensure the food safety of rice and starch flour for the rice paper wrap. In this study, fluorescence hyperspectral imaging technology was applied to classify grain flours. Using the 3D hyper cube of fluorescence hyperspectral imaging (fHSI, 420 - 730 nm), spectral and spatial data and chemometric methods were applied to detect and classify flours. Eight flours (rice: 4, starch: 4) were prepared and hyperspectral images were acquired in a 5 (L) × 5 (W) × 1.5 (H) cm container. Linear discriminant analysis (LDA), partial least square discriminant analysis (PLSDA), support vector machine (SVM), classification and regression tree (CART), and random forest (RF) with a few preprocessing methods (multivariate scatter correction [MSC], 1^st and 2^nd derivative and moving average) were applied to classify grain flours and the accuracy was compared using a confusion matrix (accuracy and kappa coefficient). LDA with moving average showed the highest accuracy at A = 0.9362 (K = 0.9270). 1D convolutional neural network (CNN) demonstrated a classification result of A = 0.94 and showed improved classification results between mimyeon flour (MF)1 and MF2 of 0.72 and 0.87, respectively. In this study, the potential of non-destructive detection and classification of grain flours using fHSI technology and machine learning methods was demonstrated.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.47 no.3
• /
• pp.177-186
• /
• 2019

Wind power tower has been used to augment the performance of VAWT (Vertical Axis Wind Turbine). However, inappropriately designed wind power tower could reduce the performance of VAWT. Hence, an optimization study was conducted on a wind power tower. Six design variables were selected, such as the outer radius and the inner radius of the guide wall, the adoption of the splitter, the inner radius of the splitter, the number of the guide wall and the circumferential angle. For the objective function, the periodic averaged torque obtained at the VAWT was selected. In the optimization, Design of Experiment (DOE), Genetic Algorithm (GA), and Artificial Neural Network (ANN) have been applied in order to avoid a localized optimized result. The ANN has been continuously improved after finishing the optimization process at each generation. The performance of the VAWT was improved more than twice when it operated within the optimized wind power tower compared to that obtained at a standalone.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.3
• /
• pp.384-390
• /
• 2020

The reverberation effect on the sound when producing movies or VR contents is a very important factor in the realism and liveliness. The reverberation time depending the space is recommended in a standard called RT60(Reverberation Time 60 dB). In this paper, we propose a scene recognition technique for automatic reverberation editing. To this end, we devised a classification model that independently trains color images and predicted depth images in the same model. Indoor scene classification is limited only by training color information because of the similarity of internal structure. Deep learning based depth information extraction technology is used to use spatial depth information. Based on RT60, 10 scene classes were constructed and model training and evaluation were conducted. Finally, the proposed SCR + DNet (Scene Classification for Reverb + Depth Net) classifier achieves higher performance than conventional CNN classifiers with 92.4% accuracy.

• Steel and Composite Structures
• /
• v.41 no.5
• /
• pp.761-773
• /
• 2021

This study presents a 3D non-linear finite element (FE) assessment of dynamic soil-structure interaction (SSI). The numerical investigation has been performed on the time domain through a Finite Element (FE) system, while considering the nonlinear behavior of soil and the multi-directional nature of genuine seismic events. Later, the FE outcomes are analyzed to the recorded in-situ free-field and structural movements, emphasizing the numerical model's great result in duplicating the observed response. In this work, the soil response is simulated using an isotropic hardening elastic-plastic hysteretic model utilizing HSsmall. It is feasible to define the non-linear cycle response from small to large strain amplitudes through this model as well as for the shift in beginning stiffness with depth that happens during cyclic loading. One of the most difficult and unexpected tasks in resolving soil-structure interaction concerns is picking an appropriate ground motion predicted across an earthquake or assessing the geometrical abnormalities in the soil waves. Furthermore, an artificial neural network (ANN) has been utilized to properly forecast the non-linear behavior of soil and its multi-directional character, which demonstrated the accuracy of the ANN based on the RMSE and R² values. The total result of this research demonstrates that complicated dynamic soil-structure interaction processes may be addressed directly by passing the significant simplifications of well-established substructure techniques.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.2
• /
• pp.79-88
• /
• 2004

Gaze detection is to locate the position on a monitor screen where a user is looking by computer vision. Gaze detection systems have numerous fields of application. They are applicable to the man-machine interface for helping the handicapped to use computers and the view control in three dimensional simulation programs. In our work, we implement it with a computer vision system setting a IR-LED based single camera. To detect the gaze position, we locate facial features, which is effectively performed with IR-LED based camera and SVM(Support Vector Machine). When a user gazes at a position of monitor, we can compute the 3D positions of those features based on 3D rotation and translation estimation and affine transform. Finally, the gaze position by the facial movements is computed from the normal vector of the plane determined by those computed 3D positions of features. In addition, we use a trained neural network to detect the gaze position by eye's movement. As experimental results, we can obtain the facial and eye gaze position on a monitor and the gaze position accuracy between the computed positions and the real ones is about 4.8 cm of RMS error.

• Korean Journal of Remote Sensing
• /
• v.38 no.2
• /
• pp.167-177
• /
• 2022

In order to obtain satellite image products using the image transmitted to the ground station after capturing the satellite images, many image pre/post-processing steps are involved. During the pre/post-processing, when converting from level 1R images to level 1G images, geometric correction is essential. An interpolation method necessary for geometric correction is inevitably used, and the quality of the level 1G images is determined according to the accuracy of the interpolation method. Also, it is crucial to speed up the interpolation algorithm by the level processor. In this paper, we proposed a lightweight CNN-based interpolation method required for geometric correction when converting from level 1R to level 1G. The proposed method doubles the resolution of satellite images and constructs a deep learning network with a lightweight deep convolutional neural network for fast processing speed. In addition, a feature map fusion method capable of improving the image quality of multispectral (MS) bands using panchromatic (PAN) band information was proposed. The images obtained through the proposed interpolation method improved by about 0.4 dB for the PAN image and about 4.9 dB for the MS image in the quantitative peak signal-to-noise ratio (PSNR) index compared to the existing deep learning-based interpolation methods. In addition, it was confirmed that the time required to acquire an image that is twice the resolution of the 36,500×36,500 input image based on the PAN image size is improved by about 1.6 times compared to the existing deep learning-based interpolation method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.3
• /
• pp.924-942
• /
• 2020

The facial expression is diverse and various among persons due to the impact of the psychology factor. Whilst the facial action is comparatively steady because of the fixedness of the anatomic structure. Therefore, to improve performance of the action unit recognition will facilitate the facial expression recognition and provide profound basis for the mental state analysis, etc. However, it still a challenge job and recognition accuracy rate is limited, because the muscle movements around the face are tiny and the facial actions are not obvious accordingly. Taking account of the moving of muscles impact each other when person express their emotion, we propose to make full use of co-occurrence relationship among action units (AUs) in this paper. Considering the dynamic characteristic of AUs as well, we adopt the 3D Convolutional Neural Network(3DCNN) as base framework and proposed to recognize multiple action units around brows, nose and mouth specially contributing in the emotion expression with putting their co-occurrence relationships as constrain. The experiments have been conducted on a typical public dataset CASME and its variant CASME2 dataset. The experiment results show that our proposed AU co-occurrence constraint 3DCNN based AU recognition approach outperforms current approaches and demonstrate the effectiveness of taking use of AUs relationship in AU recognition.

• Journal of the Korean Society for Precision Engineering
• /
• v.30 no.9
• /
• pp.901-908
• /
• 2013

The introduction of industrial intelligent robot using vision sensor has been interested in automated factory. 2D and 3D vision sensors have used to recognize object and to estimate object pose, which is for packaging parts onto a complete whole. But it is not trivial task due to illumination and various types of objects. Object image has distorted due to illumination that has caused low reliability in recognition. In this paper, recognition method of complex shape object has been proposed. An accurate object region has detected from combined binary image, which has achieved using DoG filter and local adaptive binarization. The object has recognized using neural network, which is trained with sub-divided object class according to object type and rotation angle. Predefined shape model of object and maximal slope have used to estimate the pose of object. The performance has evaluated on ETRI database and recognition rate of 96% has obtained.