• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1999.06a
• /
• pp.125-131
• /
• 1999

In this paper, we address practical methods for calculating camera lens distortion for real time applications. Although the lens distortion problem can be easily ignored for constant-parameter lenses, in the field of real-time camera calibrations, for zoom lenses a large number of calculations are needed to calculate the distortion. However, if the distortion can be calculated independently of the other camera parameter, we can easily calibrate a camera without the need for a large number of calculations. Based on Tsai's camera model, we propose two different methods for calculating lens distortion. These methods are so simple and require so few calculations that the lens distortion can be rapidly calculated even in real-time applications. The first method is to refer to the focal length - lens distortion Look Up Table(LUT), which is constructed in the initialization process. The second method is to use the relationship between the feature points found in the image. Experiments were carried out for both methods, results of which show that the proposed methods are favorably comparable in performance with non-real full optimization method.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.250-255
• /
• 2003

The position of a 3-dimensional(3D) point can be measured by using calibrated stereo camera. To obtain more accurate measurement ,more accurate camera calibration is required. There are many existing methods to calibrate camera. The simple linear methods are usually not accurate due to nonlinear lens distortion. The nonlinear methods are accurate more than linear method, but it increase computational cost and good initial guess is needed. The multi step methods need to know some camera parameters of used camera. Recent years, these explicit model based camera calibration work with the development of more precise camera models involving correction of lens distortion. But these explicit model based camera calibration have disadvantages. So implicit camera calibration methods have been derived. One of the popular implicit camera calibration method is to use neural network. In this paper, we propose implicit stereo camera calibration method for 3D reconstruction using support vector machine. SVM can learn the relationship between 3D coordinate and image coordinate, and it shows the robust property with the presence of noise and lens distortion, results of simulation are shown in section 4.

• Journal of Korean Port Research
• /
• v.14 no.3
• /
• pp.303-312
• /
• 2000

In this paper, we describe an image processing algorithm which is able to recognize the road lane. This algorithm performs to recognize the interrelation between AGV and the other vehicle. We experimented on AGV driving test with color CCD camera which is setup on the top of vehicle and acquires the digital signal. This paper is composed of two parts. One is image preprocessing part to measure the condition of the condition of the lane and vehicle. This finds the information of lines using RGB ratio cutting algorithm, the edge detection and Hough transform. The other obtains the situation of other vehicles using the image processing and viewport. At first, 2 dimension image information derived from vision sensor is interpreted to the 3 dimension information by the angle and position of the CCD camera. Through these processes, if vehicle knows the driving conditions which are lane angle, distance error and real position of other vehicles, we should calculate the reference steering angle.

• Journal of Institute of Control, Robotics and Systems
• /
• v.9 no.10
• /
• pp.774-781
• /
• 2003

The important factors that cause position error in X-Y robot are inertial force, frictions and spring distortion in screw or coupling. We have to estimate these factors precisely to correct position errors, Which is very difficult. In this paper, we makes systems to inspect metal stencil which is used to print solder paste on pads of SMD of PCB with low precision X-Y robot and vision system. To correct position error that is caused by low precision X-Y robot, we defines position error vector that is formed with position of objects that exist in reference and camera image. We apply MHT(Modified Hough Transformation) for the aim of determining the dominant position error vector. We modify reference image using extracted dominant position error vector and obtain reference image that is the same with camera image. Effectiveness and performance of this method are verified by simulation and experiment.

• Proceedings of the IEEK Conference
• /
• 2001.09a
• /
• pp.415-418
• /
• 2001

The automatic construction of large, high-resolution image mosaics is an active area of reasearch in the fields of photogrammetry, computer vision, image processing, and computer graphics. In this study, we describe a automatic mosaicing method that makes a panorama from images by placing camera in a emitted-grid. In the images captured by cameras, there must be a matched area and the area is in the particular area of the image. Initial transformation matrix, there(ore, is calculated from points searched in the partial area. It is possible to find best transformation matrix by Levenberg-Marquardt method. Finally, each images are multiplied by blending function and stitched by the transformation matrix to complete panoramic image.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2002.04a
• /
• pp.500-504
• /
• 2002

The purpose of this paper is to implement a guidance system for an object on the road. A watch camera equipped on the auto door recognizes the direction for the destination of an object, after that it determines whether opening or closing the door, and then the door is opened automatically, based on the decision. The motion of the moving object is approximated by using the technique of the image processing of tracking images and the affine model. The direction of the moving object is predicted from image information obtained by applying linear Kalman filter to the motion estimation in order to reduce the search region, the moving position, and the direction of the center of the object. Along with the guidance function, the system has the announcing function to the object. The experimental results confirm the veridity and applicability of the proposed system.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.12a
• /
• pp.203-207
• /
• 2001

In this Paper, we propose the neural network based emotion recognition method for intelligently recognizing the human's emotion using CCD color image. To do this, we first acquire the color image from the CCD camera, and then propose the method for recognizing the expression to be represented the structural correlation of man's feature Points(eyebrows, eye, nose, mouse) It is central technology that the Process of extract, separate and recognize correct data in the image. for representation is expressed by structural corelation of human's feature Points In the Proposed method, human's emotion is divided into four emotion (surprise, anger, happiness, sadness). Had separated complexion area using color-difference of color space by method that have separated background and human's face toughly to change such as external illumination in this paper. For this, we propose an algorithm to extract four feature Points from the face image acquired by the color CCD camera and find normalization face picture and some feature vectors from those. And then we apply back-prapagation algorithm to the secondary feature vector. Finally, we show the Practical application possibility of the proposed method.

• Journal of Korea Society of Industrial Information Systems
• /
• v.22 no.2
• /
• pp.53-60
• /
• 2017

In This Paper, We Propose a Method to Estimate the Human Height from the Depth Image Obtained using a Depth Camera. Using the depth Image, Accurate Measurement for Human Height is Possible Compared with Color Image. This Paper Presents a Method to Detect the Center of a Person in the Vertical Direction and to Accumulate the Measured Height Values ​at the Center Position. Simulation Results Show that the Proposed Method has Better Performance than the Conventional Methods.

• Journal of Korea Multimedia Society
• /
• v.21 no.8
• /
• pp.888-896
• /
• 2018

In this paper, we report detection and recognition of vehicle logo from images captured from street CCTV. Image data includes both the front and rear view of the vehicles. The proposed method is a two-step process which combines image preprocessing and faster region-based convolutional neural network (R-CNN) for logo recognition. Without preprocessing, faster R-CNN accuracy is high only if the image quality is good. The proposed system is focusing on street CCTV camera where image quality is different from a front facing camera. Using perspective transformation the top view images are transformed into front view images. In this system, the detection and accuracy are much higher as compared to the existing algorithm. As a result of the experiment, on day data the detection and recognition rate is improved by 2% and night data, detection rate improved by 14%.

• Journal of Multimedia Information System
• /
• v.4 no.1
• /
• pp.43-50
• /
• 2017

In this paper, we propose a method which detects the nose and face of certain human by using the depth image. The proposed method has advantages of the low computational complexity and the high accuracy even in dark environment. Also, the detection accuracy of nose and face does not change in various postures. The proposed method first locates the locally protruding part from the depth image of the human body captured through the depth camera, and then confirms the nose through the depth characteristic of the nose and surrounding pixels. After finding the correct pixel of the nose, we determine the region of interest centered on the nose. In this case, the size of the region of interest is variable depending on the depth value of the nose. Then, face region can be found by performing binarization using the depth histogram in the region of interest. The proposed method can detect the nose and the face accurately regardless of the pose or the illumination of the captured area.