• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.28 no.7
• /
• pp.818-825
• /
• 2004

In this paper, the study of effects of flow parameters on flame structure and NOx emission concentration was performed in co-axial. laminar partially premixed methane/air flames. Such (low parameters as equivalence ratio(${\Phi}$), fuel split percentage($\sigma$), and mixing distance(x/D$\_$i/) were defined as a premixing degree and varied within ${\Phi}$=1.36∼9.52, $\sigma$=50∼100, and x/D$\_$i/=5∼20. The image of OH$\^$*/ and NOx concentration were obtained with an ICCD camera and a NOx analyzer. The flame structure observations show a categorization of partially premixed flames into three distinct flame regimes corresponding to ${\Phi}$<1.7(premixed flame structure), 1.7<${\Phi}$<3.3(hybrid structure), and ${\Phi}$>3.3(diffusion flame structure existing a luminous sooting region) at $\sigma$=75%, and x/D$\_$i/=10. As o decreases from 100% to 50%, and x/D$\_$i/ decreases, nonpremixed flame structure appear at low equivalence ratio relatively. In addition, the measured emissions for NOx rise steeply from ${\Phi}$=1.7, to ${\Phi}$=3.3, then constants ${\Phi}$>4.76. NOx emissions decrease with increase the level of premixing level. In conclusion, the main effect on flame structure and NOx production was at first equivalence ratio(${\Phi}$), and next fuel split percentage($\sigma$), and finally mixing distance(x/D$\_$i/).

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.6
• /
• pp.29-36
• /
• 2012

In this paper, we suggest a new method of detecting human skin-color regions from three-dimensional static or dynamic stereoscopic images by effectively integrating depth and color features. The suggested method first extracts depth information that represents the distance between a camera and an object from input left and right stereoscopic images through a stereo matching technique. It then performs labeling for pixels with similar depth features and determines the labeled regions having human skin color as actual skin color regions. Our experimental results show that the suggested skin region extraction method outperforms existing skin detection methods in terms of skin-color region extraction accuracy.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.46 no.6
• /
• pp.65-72
• /
• 2009

This paper presents a vision based localization method for indoor mobile robots using the types of vertices from a monocular image. In the images captured from a camera of a robot, the types of vertices are determined by searching vertical edges and their branch edges with a geometric constraints. For obtaining correspondence between the comers of a 2-D map and the vertex of images, the type of vertices and geometrical constraints induced from a geometric analysis. The vertices are matched with the comers by a heuristic method using the type and position of the vertices and the comers. With the matched pairs, nonlinear equations derived from the perspective and rigid transformations are produced. The pose of the robot is computed by solving the equations using a least-squares optimization technique. Experimental results show that the proposed localization method is effective and applicable to the localization of indoor environments.

• Korean Journal of Agricultural Science
• /
• v.47 no.2
• /
• pp.205-217
• /
• 2020

In this study, a deep learning-based tillage boundary detection method for autonomous tillage by a tractor was developed, which consisted of image cropping, object classification, area segmentation, and boundary detection methods. Full HD (1920 × 1080) images were obtained using a RGB camera installed on the hood of a tractor and were cropped to 112 × 112 size images to generate a dataset for training the classification model. The classification model was constructed based on convolutional neural networks, and the path boundary was detected using a probability map, which was generated by the integration of softmax outputs. The results show that the F1-score of the classification was approximately 0.91, and it had a similar performance as the deep learning-based classification task in the agriculture field. The path boundary was determined with edge detection and the Hough transform, and it was compared to the actual path boundary. The average lateral error was approximately 11.4 cm, and the average angle error was approximately 8.9°. The proposed technique can perform as well as other approaches; however, it only needs low cost memory to execute the process unlike other deep learning-based approaches. It is possible that an autonomous farm robot can be easily developed with this proposed technique using a simple hardware configuration.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2017.05a
• /
• pp.475-481
• /
• 2017

In this paper, high speed camera images were used to analyze the supercritical injection behavior of liquid hydrocarbon compounds used as main components of propellant fuel. Decane and Methylcyclohexane (MCH), which have different critical points among kerosene constituents, were selected as experimental fluid and Shadowgraphy technique was used for the analysis. The difference in the temperature variation from the initial injector state of the subcritical condition until the vaporization occurs was represented by the different behaviors of Decane and MCH. However, under the Supercritical conditions, the enthalpy of vaporization near the critical point approaches zero and the phase change to the Supercritical phase occurs instead of vaporization process. In the phase change of the Supercritical system, there was no rapid density change, so the liquid state image was observed in both the Decane and MCH.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.21 no.4
• /
• pp.347-353
• /
• 2003

Lately, Digital Photogrammetry has been increasingly applied to various hightech industries and becomes one of more interesting focuses of study than ever. Thus, this study aims to develop a Road Horizontal Alignment Information System by means of digital photogrammetry. Data acquired from digital photographic techniques were processed using Delphi, an object oriented programming language to develop a computer aided program, that allows us to build the information on Road Horizontal Alignment(Beginning Point of Curve, Ending Point of Curve, Radius, Intersection Point). The developed program could maximize visualization for better analysis compared with traditional programs because it utilizes many image data. Comparing with data from traditional horizontal alignment extraction programs based on the principle of least square method, the data acquired by Horizontal Alignment Information and kinematic GPS showed out of the developed road information systems the improved accuracy of IP value up to about 2m in the direction of X, Y axes, where the accuracy of curve radius(R) becomes enhanced up to about 2.5 m.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.6
• /
• pp.718-723
• /
• 2011

In this paper, we propose a visual multi-touch air input device using vision cameras. The implemented device provides a barehanded interface which copes with the multi-touch operation. The proposed device is easy to apply to the real-time systems because of its low computational load and is cheaper than the existing methods using glove data or 3-dimensional data because any additional equipment is not required. To do this, first, we propose an image processing algorithm based on the HSV color model and the labeling from obtained images. Also, to improve the accuracy of the recognition of hand gestures, we propose a motion recognition algorithm based on the geometric feature points, the skeleton model, and the Kalman filter. Finally, the experiments show that the proposed device is applicable to remote controllers for video games, smart TVs and any computer applications.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.4
• /
• pp.494-499
• /
• 2007

In this paper we realized a system, if a user selects the area of the important parts or the arrangement parts when he reads the books or the papers, which amends, stores and readjusts the characters that are included in the selected area by outputting the characters to the word processor in sequence. If a user selects what he wishes lot with his finger, the system detects the movement of the finger by applying the hand recognition algorithm and recognizes the selected area. The system converts the distance of the width and the length of the selected area to the number of the pulse, and controls the motor to move the camera at the position. After the system scales up/down the zoom to be able to recognize the character and controls the focus to the regulated zoom closely, it controls the focus in detail to get more distinct image by using the difference of the light and darkness. We realize the recognition and editing support system of korean language that converts the obtained images to the document by applying the character recognition algorithm and arrange the important parts.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.8
• /
• pp.1823-1830
• /
• 2003

This paper presents a multiple face detector based on a robust pupil detection technique. The pupil detector uses active illumination that exploits the retro­reflectivity property of eyes to facilitate detection. The detection range of this method is appropriate for interactive desktop and kiosk applications. Once the location of the pupil candidates are computed, the candidates are filtered and grouped into pairs that correspond to faces using heuristic rules. To demonstrate the robustness of the face detection technique, a dual mode face tracker was developed, which is initialized with the most salient detected face. Recursive estimators are used to guarantee the stability of the process and combine the measurements from the multi­face detector and a feature correlation tracker. The estimated position of the face is used to control a pan­tilt servo mechanism in real­time, that moves the camera to keep the tracked face always centered in the image.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.11
• /
• pp.2753-2758
• /
• 2014

Around-View, the image processing device which increases the comfort of drivers is sold in the market. This system prevents accidents in advance while driving or parking. The accidents are caused with their inexperienced driving or bad visibility. It is developed for driving convenience. However, it dosen't spread to the driver widely due to the problem of the high installation costs and complex installation process. First, expensive equipment second, difficult development environment and third, inconvenient installation procedure. So the drivers don't have many opportunities to use this system and dare to develop this system. I think if one of the problems can be solved, users might be able to access this system at low cost. In this paper, the AVM(Around-View Monitoring) minimizes two of them. Expensive equipment, inconvenient installation. The costly problems were solved by using low-cost USB device and rear cameras. In view of inconvenient installation process, the new system was designed to make it easy for people to install it. Through this, it can ease the burden of consumers.