http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
A Novel Fractal Dimensions Estimation Algorithm for Texture Characterization
Artem Lenskiy,Jong?Soo Lee 대한전자공학회 2010 대한전자공학회 학술대회 Vol.2010 No.6
In this paper we propose generalized fractal dimensions (GFD) to characterize textures. It has been proven that fractal dimensions are invariant under bi?.Lipshitz transforms [1], which are general smooth transforms including perspective transforms. Although, fractal dimensions have been applied earlier for texture segmentation, we propose a novel GFD estimation algorithm. Furthermore, we estimate GFD locally, which allows us to characterize local regions and further segment them.
A vehicle driver iris detection algorithm
Artem Lenskiy,Jong-Soo Lee 제어로봇시스템학회 2009 제어로봇시스템학회 국제학술대회 논문집 Vol.2009 No.8
Many car accidents happen due to driver inattention. In this paper we will present a novel system for driver facial and facial features detection, which could be a preliminary step toward driver awareness control. This system consists of the following major steps: Skin-color segmentation, facial features segmentation, and iris position location. For skin-segmentation we applied a multi-layer perceptron to approximate the statistical probability of skin-color pixels appearance and filter out pixels with small probabilities. There maining skin-segments were segmented into the following categories: eye, mouth, eyebrow, and there maining facial regions. For this purpose we propose a novel segmentation technique based on non parametric estimation of probability density functions(PDF) using salient features. Each pixelis classified according to the highest probability selected from four PDFs. Detected eye regions are analyzed with the circular Hough transform to find the position and radius of their is. We tested our system in real enivorment using a CCD camera. The system showed a 92% detection rate.
Rugged terrain segmentation based on salient features
Artem A. Lenskiy,Jong-Soo Lee 제어로봇시스템학회 2010 제어로봇시스템학회 국제학술대회 논문집 Vol.2010 No.10
In the last decade significant progress in computer vision based control of unmanned ground vehicles (UGV) has been achieved. However, until now textural information has been somewhat less effective than color or laser range information. In this paper we propose a computer vision based cross country segmentation system that is capable of distinguishing cross-country road, grass and trees during day-time and night times. For this purpose we extract Speeded-Up Robust Features (SURF) from the training image set and construct texture class models using two-layer feed-forward neural network. Using these constructed models and extracted features from the images captured by the CCD and IR cameras we estimate features’ class membership values. These estimated values and features’ spatial positions are then applied for image segmentation. A number of experiments are conducted with the lowest mean error segmentation rate of 16.78% and 20.60% for images in IR and visible spectrum correspondingly.
Biomarker gradients of super-viscous oil as an estimation method of oil-water distribution
Artem Chemodanov,Vladislav Sudakov,Rinat Khayrtdinov,Regina Safina 한국자원공학회 2019 Geosystem engineering Vol.22 No.5
In this article, we consider a promising method for estimating the water saturation of a super-viscous oilfield (hereinafter, SVO field) in the case of Cheremshansky oilfield, Russian Federation. A lithological description of the reservoir was carried out and gas chromatography-massspectrometry analysis of hydrocarbon fractions of core bitumoid was performed. It is shown that the ratios of certain biomarkers (methyldibenzothiophenes, 6H-Farnesol and pristane) SVO have extrema, both at the end of oil reservoir, and in the middle. Based on the fact that such dependencies indirectly indicate the distribution of water in the oil reservoir, the authors formulated the conclusion that there is no pure water reservoir (along the studied wells). Also, the authors have shown that the distribution of the ‘oil-water’ by measuring the gradients of concentrations of biomarkers SVO bears certain advantages and is a good addition to the classic geophysical methods.
Student’s attention and fatigue monitoring in use for online education
Artem Lenskiy,Rabey Husini,Jong?Soo Lee 대한전자공학회 2010 대한전자공학회 학술대회 Vol.2010 No.6
The paper discusses one of the problems with online education related to the lack of control of student attention. Based on the earlier proposed iris detection system[1] a solution for students’fatigue monitoring is suggested. Specifically, we estimate blink duration and compare it with the blink duration corresponding to the drowsy state.
Driver’s Eye Blinking Detection Using Novel Color and Texture Segmentation Algorithms
Artem A. Lenskiy,이종수 제어·로봇·시스템학회 2012 International Journal of Control, Automation, and Vol.10 No.2
In this paper we propose a system that measures eye blinking rate and eye closure duration. The system consists of skin-color segmentation, facial features segmentation, iris positioning and blink detection. The proposed skin-segmentation procedure is based on a neural network approximation of a RGB skin-color histogram. This method is robust and adaptive to any skin-color training set. The largest remaining skin-color region among skin-color segmentation results is further segmented into open/closed eyes, lips, nose, eyebrows, and the remaining facial regions using a novel texture segmen-tation algorithm. The segmentation algorithm classifies pixels according to the highest probability among the estimated facial feature class probability density functions (PDFs). The segmented eye re-gions are analyzed with the Circular Hough transform with the purpose of finding iris candidates. The finial iris position is selected according to the location of the maximum correlation value obtained from correlation with a predefined mask. The positions of irises and eye states are monitored through time to estimate eye blinking frequency and eye closure duration. The method of the driver drowsiness detection using these parameters is illustrated. The proposed system is tested on CCD and CMOS cam-eras under different environmental conditions and the experimental results show high system perform-ance.