• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.11
• /
• pp.789-794
• /
• 2013

A vehicle tracking system makes it possible to induce the vehicle movement path for avoiding traffic congestion and to prevent traffic accidents in advance by recognizing traffic flow, monitoring vehicles, and detecting road accidents. To track the vehicles effectively, those which appear in a sequence of video frames need to identified by extracting the features of each object in the frames. Next, the identical vehicles over the continuous frames need to be recognized through the matching among the objects' feature values. In this paper, we identify objects by binarizing the difference image between a target and a referential image, and the labelling technique. As feature values, we use the center coordinate of the minimum bounding rectangle(MBR) of the identified object and the averages of 1D FFT(fast Fourier transform) coefficients with respect to the horizontal and vertical direction of the MBR. A vehicle is tracked in such a way that the pair of objects that have the highest similarity among objects in two continuous images are regarded as an identical object. The experimental result shows that the proposed method outperforms the existing methods that use geometrical features in tracking accuracy.

• Journal of Korea Multimedia Society
• /
• v.10 no.7
• /
• pp.923-933
• /
• 2007

In this paper, we present a method for performance enhancement of the marker detection system by using SVM(Support Vector Machine) and LDA(Linear Discriminant Analysis). It converts the input image to a binary image and extracts contours of objects in the binary image. After that, it approximates the contours to a list of line segments. It finds quadrangle by using geometrical features which are extracted from the approximated line segments. It normalizes the shape of extracted quadrangle into exact squares by using the warping technique and scale transformation. It extracts feature vectors from the square image by using principal component analysis. It then checks if the square image is a marker image or a non-marker image by using a SVM classifier. After that, it computes feature vectors by using LDA for the extracted marker images. And it calculates the distance between feature vector of input marker image and those of standard markers. Finally, it recognizes the marker by using minimum distance method. Experimental results show that the proposed method achieves enhancement of recognition rate with smaller feature vectors by using LDA and it can decrease false detection errors by using SVM.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.8
• /
• pp.55-67
• /
• 1998

This paper presents an automatic facial feature point extraction algorithm in sequential color images. To extract facial region in the video sequence, a moving color detection technique is proposed that emphasize moving skin color region by applying motion detection algorithm on the skin-color transformed images. The threshold value for the pixel difference detection is also decided according to the transformed pixel value that represents the probability of the desired color information. Eye candidate regions are selected using both of the black/white color information inside the skin-color region and the valley information of the moving skin region detected using morphological operators. Eye region is finally decided by the geometrical relationship of the eyes and color histogram. To decide the exact feature points, the PCA(Principal Component Analysis) is used on each eye and mouth regions. Experimental results show that the feature points of eye and mouth can be obtained correctly irrespective of background, direction and size of face.

• Journal of Biomedical Engineering Research
• /
• v.37 no.2
• /
• pp.61-67
• /
• 2016

This paper presented a method for random forest based the arrhythmia classification using both heart rate (HR) and heart rate variability (HRV) features. We analyzed the MIT-BIH arrhythmia database which contains half-hour ECG recorded from 48 subjects. This study included not only the linear features but also non-linear features for the improvement of classification performance. We classified abnormal ECG using mean_NN (mean of heart rate), SD1/SD2 (geometrical feature of poincare HRV plot), SE (spectral entropy), pNN100 (percentage of a heart rate longer than 100 ms) affecting accurate classification among combined of linear and nonlinear features. We compared our proposed method with Neural Networks to evaluate the accuracy of the algorithm. When we used the features extracted from the HRV as an input variable for classifier, random forest used only the most contributed variable for classification unlike the neural networks. The characteristics of random forest enable the dimensionality reduction of the input variables, increase a efficiency of classifier and can be obtained faster, 11.1% higher accuracy than the neural networks.

• Journal of Korean Society for Geospatial Information Science
• /
• v.24 no.1
• /
• pp.89-98
• /
• 2016

In this paper, we proposed an automated areal feature matching method based on geometric similarity without user intervention and is applied into areal features of many-to-many relation, for confusion of spatial data-sets of different scale and updating cycle. Firstly, areal feature(node) that a value of inclusion function is more than 0.4 was connected as an edge in adjacency matrix and candidate corresponding areal features included many-to-many relation was identified by multiplication of adjacency matrix. For geometrical matching, these multiple candidates corresponding areal features were transformed into an aggregated polygon as a convex hull generated by a curve-fitting algorithm. Secondly, we defined matching criteria to measure geometrical quality, and these criteria were changed into normalized values, similarity, by similarity function. Next, shape similarity is defined as a weighted linear combination of these similarities and weights which are calculated by Criteria Importance Through Intercriteria Correlation(CRITIC) method. Finally, in training data, we identified Equal Error Rate(EER) which is trade-off value in a plot of precision versus recall for all threshold values(PR curve) as a threshold and decided if these candidate pairs are corresponding pairs or not. To the result of applying the proposed method in a digital topographic map and a base map of address system(KAIS), we confirmed that some many-to-many areal features were mis-detected in visual evaluation and precision, recall and F-Measure was highly 0.951, 0.906, 0.928, respectively in statistical evaluation. These means that accuracy of the automated matching between different spatial data-sets by the proposed method is highly. However, we should do a research on an inclusion function and a detail matching criterion to exactly quantify many-to-many areal features in future.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.601-605
• /
• 2009

Due to the fact that fish-eye lens can provide super wide angles with the minimum number of cameras, field-of-view over 180 degrees, many vehicles are attempting to mount the camera system. Camera calibration should be preceded, and geometrical correction on the radial distortion is needed to provide the images for the driver's assistance. However, vehicle fish-eye cameras have diagonal output images rather than circular images and have asymmetric distortion beyond the horizontal angle. In this paper, we introduce a camera model and metric calibration method for vehicle cameras which uses feature points of the image. And undistort the input image through a perspective projection, where straight lines should appear straight. The method fitted vehicle fish-eye lens with different field of views.

• Journal of Institute of Control, Robotics and Systems
• /
• v.7 no.4
• /
• pp.309-318
• /
• 2001

In this paper, we describe methods that analyze a human gesture. A human interface(HI) system for analyzing gesture extracts the head and hand regions after taking image sequence of and operators continuous behavior using CCD cameras. As gestures are accomplished with operators head and hands motion, we extract the head and hand regions to analyze gestures and calculate geometrical information of extracted skin regions. The analysis of head motion is possible by obtaining the face direction. We assume that head is ellipsoid with 3D coordinates to locate the face features likes eyes, nose and mouth on its surface. If was know the center of feature points, the angle of the center in the ellipsoid is the direction of the face. The hand region obtained from preprocessing is able to include hands as well as arms. For extracting only the hand region from preprocessing, we should find the wrist line to divide the hand and arm regions. After distinguishing the hand region by the wrist line, we model the hand region as an ellipse for the analysis of hand data. Also, the finger part is represented as a long and narrow shape. We extract hand information such as size, position, and shape.

• Journal of the Korean Society for Precision Engineering
• /
• v.20 no.12
• /
• pp.25-33
• /
• 2003

A burr has been defined as undesirable projection of material formed as a result of plastic flow from a cutting or shearing operation. It is unavoidable in all kinds of machining operation. As a result, burr makes troubles on manufacturing process due to deburring cost, quality of products and productivity. In this study, the primary interest is about exit burr. The burr formation mechanism in each type of burr is classified. Data bases are developed to predict burr formation result. In the milling operation, we develop an algorithm to analyze the burr formation mechanism by the geometrical analysis on the multi featured workpiece with multi cutting path. The algorithm includes three steps, i. e., the feature identification, the cutting condition identification, and the analysis on exit burr formation. We can predict which portion of workpiece would have the exit burr in advance so that we can manage to find a way to minimize the exit burr formation in an actual cutting. Also, this algorithm can be implemented in a commercial CAM package so that we can simulate the NC code to review the burr formation in advance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.5
• /
• pp.2607-2627
• /
• 2017

Nonnegative matrix factorization (NMF) has received considerable attention due to its effectiveness of reducing high dimensional data and importance of producing a parts-based image representation. Most of existing NMF variants attempt to address the assertion that the observed data distribute on a nonlinear low-dimensional manifold. However, recent research results showed that not only the observed data but also the features lie on the low-dimensional manifolds. In addition, a few hard priori label information is available and thus helps to uncover the intrinsic geometrical and discriminative structures of the data space. Motivated by the two aspects above mentioned, we propose a novel algorithm to enhance the effectiveness of image representation, called Dual graph-regularized Constrained Nonnegative Matrix Factorization (DCNMF). The underlying philosophy of the proposed method is that it not only considers the geometric structures of the data manifold and the feature manifold simultaneously, but also mines valuable information from a few known labeled examples. These schemes will improve the performance of image representation and thus enhance the effectiveness of image classification. Extensive experiments on common benchmarks demonstrated that DCNMF has its superiority in image classification compared with state-of-the-art methods.

• The Bulletin of The Korean Astronomical Society
• /
• v.38 no.1
• /
• pp.60.2-60.2
• /
• 2013

We investigate several eruptive hot plasma observations by Hinode/XRT. Their corresponding EUV and/or white light CME features are visible in some events. Using those observations, we determine the mass constraints of eruptive plasma by assuming simplified geometrical structures of the plasma. In some events, their associated prominence eruptions and eruptive plasma were observed in EUV observations as absorption or emission features. The absorption feature provides the lower limit to the cold mass while the emission feature provides the upper limit to the mass of observed eruptive plasma in X-ray and EUV passbands. We compare the mass constraints for each temperature responses and find that the mass in EUV and XRT are smaller in their upper or lower limit than total mass in coronagraph. About half eruptive events in XRT have no corresponding CME, which may be due to failed eruptions or low plasma density. In addition, some events were observed by a few passbands in X-ray, which allows the determination of the eruptive plasma temperature using a filter ratio method. We present the isothermal plasma temperatures by the filter ratio method. These are possibly an average temperature for higher temperature plasma because the XRT is more sensitive in higher temperature.