• Journal of Korea Society of Industrial Information Systems
• /
• v.14 no.5
• /
• pp.43-51
• /
• 2009

In this paper, we propose an efficient method of face retrieval by using PCA(principal component analysis) based features. The coarse-to-fine strategy is adopted to sort the retrieval results in the lower dimensional eigenface space and to rearrange candidates at high ranks in higher dimensional eigenface space. To evaluate similarity between a query face image and class reference image, we utilize the PD (projection distance), MQDF(modified quadratic distance function) and MED(minimum Euclidean distance). The experimental results show that the proposed method which rearrange the retrieval results incrementally by using projection distance is efficient for face image retrieval.

• Journal of the Korean Institute of Telematics and Electronics T
• /
• v.36T no.4
• /
• pp.38-46
• /
• 1999

This paper discusses the repetitive tracking control method for a coarse-fine actuator. The proposed system is composed of a magnetic linear drive as a coarse actuator and a piezoelectric linear positioner as a fine actuator. In particular, nonlinear friction in a magnetic linear drive and hysteresis characteristic of a piezoelectric linear positioner are modeled first. The feedback linearization loop uses these models in tracking position control. The control strategy is then further extended to include a repetitive control algorithm in tracking periodic reference inputs. This repetitive controller is implemented on the existing PID controller augmented with feedback linearization loop. The experimental results show that performance in tracking sinusoidal waveforms is noticeably improved by augmenting a PID controller with feedback linearization loop and a repetitive controller together.

• The Journal of Korea Robotics Society
• /
• v.3 no.1
• /
• pp.33-41
• /
• 2008

Based on object recognition technology, we present a new global localization method for robot navigation. For doing this, we model any indoor environment using the following visual cues with a stereo camera; view-based image features for object recognition and those 3D positions for object pose estimation. Also, we use the depth information at the horizontal centerline in image where optical axis passes through, which is similar to the data of the 2D laser range finder. Therefore, we can build a hybrid local node for a topological map that is composed of an indoor environment metric map and an object location map. Based on such modeling, we suggest a coarse-to-fine strategy for estimating the global localization of a mobile robot. The coarse pose is obtained by means of object recognition and SVD based least-squares fitting, and then its refined pose is estimated with a particle filtering algorithm. With real experiments, we show that the proposed method can be an effective vision- based global localization algorithm.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.6
• /
• pp.3086-3103
• /
• 2017

Video images captured by vehicle cameras often contain blurry or dithering frames due to inadvertent motion from bumps in the road or by insufficient illumination during the morning or evening, which greatly reduces the perception of objects expression and recognition from the records. Therefore, a real-time electronic stabilization method to correct fuzzy video from driving recorders has been proposed. In the first stage of feature detection, a coarse-to-fine inspection policy and a scale nonlinear diffusion filter are proposed to provide more accurate keypoints. Second, a new antiblurry binary descriptor and a feature point selection strategy for unintentional estimation are proposed, which brought more discriminative power. In addition, a new evaluation criterion for affine region detectors is presented based on the percentage interval of repeatability. The experiments show that the proposed method exhibits improvement in detecting blurry corner points. Moreover, it improves the performance of the algorithm and guarantees high processing speed at the same time.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_1
• /
• pp.871-884
• /
• 2021

The purpose of this study was to determine ways to increase efficiency in constructing and verifying artificial intelligence learning data on land cover using aerial and satellite images, and in applying the data to AI learning algorithms. To this end, multi-resolution datasets of 0.51 m and 10 m each for 8 categories of land cover were constructed using high-resolution aerial images and satellite images obtained from Sentinel-2 satellites. Furthermore, fine data (a total of 17,000 pieces) and coarse data (a total of 33,000 pieces) were simultaneously constructed to achieve the following two goals: precise detection of land cover changes and the establishment of large-scale learning datasets. To secure the accuracy of the learning data, the verification was performed in three steps, which included data refining, annotation, and sampling. The learning data that wasfinally verified was applied to the semantic segmentation algorithms U-Net and DeeplabV3+, and the results were analyzed. Based on the analysis, the average accuracy for land cover based on aerial imagery was 77.8% for U-Net and 76.3% for Deeplab V3+, while for land cover based on satellite imagery it was 91.4% for U-Net and 85.8% for Deeplab V3+. The artificial intelligence learning datasets on land cover constructed using high-resolution aerial and satellite images in this study can be used as reference data to help classify land cover and identify relevant changes. Therefore, it is expected that this study's findings can be used in the future in various fields of artificial intelligence studying land cover in constructing an artificial intelligence learning dataset on land cover of the whole of Korea.

• Journal of KIISE:Software and Applications
• /
• v.26 no.12
• /
• pp.1482-1496
• /
• 1999

기존의 스테레오 정합 알고리즘은 크게 명암기반기법과 특징기반기법의 두 가지로 나눌 수 있다. 그리고, 각 기법은 그들 나름대로의 장단점을 갖는다. 본 논문은 이 두 기법을 결합하는 새로운 알고리즘을 제안한다. 본 논문에서는 물체모델링을 목적으로 하기 때문에 배경을 제거하여 정합하는 방법을 사용한다. 이를 위해, 정합요소들과 정합유사함수가 정의되고, 정합유사함수는 두 기법사이의 장단점을 하나의 인수에 의해 조절한다. 그 외에도 거리차 지도의 오류를 제거하는 coarse-to-fine기법, 폐색문제를 해결하는 다중윈도우 기법을 사용하였고, 물체의 표면형태를 알아내기 위해 morphological closing 연산자를 이용하여 물체와 배경을 분리하는 방법을 제안하였다. 이러한 기법들을 기반으로 하여 여러가지 영상에 대해 실험을 수행하였으며, 그 결과들은 본 논문이 제안하는 기법의 효율성을 보여준다. 정합의 결과로 만들어지는 거리차 지도는 3차원 모델링을 통해 가상공간상에서 보여지도록 하였다.Abstract Classical stereo matching algorithms can be classified into two major areas; intensity-based and feature-based stereo matching. Each technique has advantages and disadvantages. This paper proposes a new algorithm which merges two main matching techniques. Since the goal of our stereo algorithm is in object modeling, we use images for which background is removed. Primitives and a similarity function are defined. The matching similarity function selectively controls the advantages and disadvantages of intensity-based and feature-based matching by a parameter.As an additional matching strategy, a coarse-to-fine method is used to remove a errorneous data on the disparity map. To handle occlusions, multiple windowing method is used. For finding the surface shape of an object, we propose a method that separates an object and the background by a morphological closing operator. All processes have been implemented and tested with various image pairs. The matching results showed the effectiveness of our method. From the disparity map computed by the matching process, 3D modeling is possible. 3D modeling is manipulated by VRML(Virtual Reality Manipulation Language). The results are summarized in a virtual reality space.

• Journal of Korean Society for Atmospheric Environment
• /
• v.24 no.3
• /
• pp.367-375
• /
• 2008

To characterize atmospheric particles in Cheonan area, 5 monitoring sites representing highway area, commercial area, residential area, and industrial areas were selected, and the mass concentrations of PM10 and PM2.5 were monitored for 14 days at each site during 2007. The daily average PM10 and PM2.5 concentrations were in the range from 18.5 to $140.9{\mu}g/m^3$ and 8.2 to $116.6{\mu}g/m^3$, respectively, showing the highest mean concentrations at the commercial area site and the lowest concentration at the residential area site. The daily average PM 10 concentrations at Shinan (Commercial area) and Bakseok (Industrial area) sites were exceeded the current National Standard for 1 and 2 days during the monitoring periods. The fractions of PM2.5 in PM10 were above 70% for all sites, indicating fine particles are the major constituent of atmospheric particles in Cheonan. The results indicate that PM10 concentrations in Cheonan are at the concerning level, and the control strategy for fine particles is necessary to address this issue.

• Korean Journal of Materials Research
• /
• v.31 no.5
• /
• pp.245-254
• /
• 2021

Wire arc additive manufacturing (WAAM) is being considered as a technology to replace the conventional manufacturing process of titanium alloys. However, coarse β grains, which can extend through several deposited materials, result in strong textures and anisotropy. As a solution, we study the plastic deformation effects of ultrasonic needle peening (UNP) on the microstructure. UNP treated materials deform plastically and the dislocation density increases. Fine α+α' grains with low aspect ratio are observed in the UNP treated specimens. UNP treated WAAM Ti-6Al-4V alloys have higher strength and lower elongation than those characteristics of WAAM Ti-6Al-4V alloys. Due to UNP treatment, the z-axis directional specimens exhibit a greater effect of reducing elongation than do the x-axis directional specimens. The UNP treatment produces fine grains in proportion to the number of times UNP is performed, thereby increasing strength. UNP processes produce a large number of dislocations in the WAAM Ti-6Al-4V alloys, with the most dislocations being formed at the surface.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.7
• /
• pp.2480-2495
• /
• 2014

This paper describes a hierarchical method for image-based age estimation that combines age group classification and age value estimation. The proposed method uses a coarse-to-fine strategy with different appearance features to describe facial shape and texture. Considering the damage to continuity between neighboring groups caused by fixed divisions during age group classification, a dynamic grouping technique is employed to allow non-fixed groups. Based on the given group, an ordinal hyperplane ranking (OHRank) model is employed to transform age estimation into a series of binary enquiry problems that can take advantage of the intrinsic correlation and ordinal information of age. A set of experiments on FG-NET are presented and the results demonstrate the validity of our solution.

• Journal of Advanced Research in Ocean Engineering
• /
• v.4 no.2
• /
• pp.78-85
• /
• 2018

This paper presents a study of the effects of the free surface to marine propeller including the mesh effect of the models. In the present study, we conduct the numerical simulation for propeller performance employing the openwater test. The numerical simulations compare the meshing strategies for the propeller and show the effects on both thrust and torque. OpenFOAM is applied to solve the propeller problem and then open water performances of KCS propeller (KP505) are estimated using a Reynold-averaged Navier-Stokes equations (RANS) solver and the turbulence of the $K-{\omega}$ SST model. Unstructured meshes are used in the numerical simulation employing hexahedral meshing for mesh generation. The arbitrary mesh interfacing (AMI) and multiple rotating frame (MRF) are compared to define the best meshing strategy. The meshing strategies are evaluated through 3 classifications, i.e., coarse, medium, and fine mesh. Thus, the propeller can be performed utilizing the best mesh strategy. The computational results are validated by comparison with the experimental results. The $K_T$, $K_Q$, and efficiency of the propeller are compared to an experimental result and for all of the meshing strategies. Thus, the simulations show the influence of meshing in order to perform the propeller performances.