• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권2호
• /
• pp.643-661
• /
• 2018

This paper proposes a novel algorithm for lane detection based on inverse perspective transformation and Kalman filter. A simple inverse perspective transformation method is presented to remove perspective effects and generate a top-view image. This method does not need to obtain the internal and external parameters of the camera. The Gaussian kernel function is used to convolute the image to highlight the lane lines, and then an iterative threshold method is used to segment the image. A searching method is applied in the top-view image obtained from the inverse perspective transformation to determine the lane points and their positions. Combining with feature voting mechanism, the detected lane points are fitted as a straight line. Kalman filter is then applied to optimize and track the lane lines and improve the detection robustness. The experimental results show that the proposed method works well in various road conditions and meet the real-time requirements.

• 전자공학회논문지
• /
• 제50권2호
• /
• pp.193-200
• /
• 2013

본 연구에서는 허프 변환을 이용하여 원통형 수중 물체를 식별하는 방법을 제안한다. 이미 광학분야에서는 타원을 식별하는데 허프 변환을 많이 사용하고 있다. 하지만 수중 영상의 경우 낮은 해상도와 잡음 환경으로 인해서 광학에서 사용하는 허프 변환을 그대로 적용하기가 어렵다. 따라서 본 연구에서는 수중 영상의 원통형 물체를 모델링 한 뒤 평균 필터와 다항식 보간법을 적용하여 허프 변환에 적합한 형태로 원통형 물체의 기하학적 깊이 정보를 다시 복원했다. 결과적으로 이 방법을 이용하여 타원 형태의 기하학적 깊이 정보를 복원하고 허프 변환을 적용한 결과 높은 타원 식별률을 나타내었다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2013년도 춘계학술발표대회
• /
• pp.667-670
• /
• 2013

Noise is unwanted in high quality images, but it can aid image tampering. For example, noise can be intentionally added in image to conceal tampered regions or to create special visual effects. It may also be introduced unknowingly during camera imaging process, which makes the noise levels inconsistent in splicing images. In this paper, we present an image forgery detection method using a noise dependent watershed transformation. Image is segmented into objects for initial noise estimation by the watershed transformation, and different noise level in objects are estimated to obtain final decision result. Experimental results of the proposed method on natural images are presented.

• 한국측량학회지
• /
• 제17권3호
• /
• pp.311-320
• /
• 1999

본 연구에서는 두만강 하류지역 다분광 TM영상의 변환기법과 그에 대한 감독분류방법을 비교 분석하였다. 총체적 분류 정확도는 최대우도법이 높으며 식생은 MNF와 TC 변환 영상에서 비교적 좋은 분류 결과를 얻을 수 있다. MNF, TC, NDVI 등 영상들로 구성된 7차원 영상은 3차원 영상보다 좋은 결과를 나타내며 그 중에서도 최대우도법의 분류 결과가 제일 좋았다. 다분광 영상은 두만강 지역 경제 개발 계획과 산업 입지 선정에 중요한 기초자료로 활용될 수 있다.

• 한국인쇄학회지
• /
• 제25권1호
• /
• pp.65-80
• /
• 2007

The input and output device requires precise color representation and CMS (Color Management System) because of the increasing number of ways to apply the digital image into electronic publishing. However, there are slight differences in the device dependent color signal among the input and output devices. Also, because of the non-linear conversion of the input signal value to the output signal value, there are color differences between the original copy and the output copy. It seems necessary for device-dependent color information values to change into device-independent color information values. When creating an original copy through electronic publishing, there should be color management with the input and output devices. From the devices' three phases of calibration, characterization and color conversion, the device-dependent color should undergo a color transformation into a device-independent color. In this paper, an experiment was done where the input device used the linear multiple regression and the sRGB color space to perform a color transformation. The output device used the GOG, GOGO and sRGB for the color transformation. After undergoing a color transformation in the input and output devices, the best results were created when the original target underwent a color transformation by the scanner and digital camera input device by the linear multiple regression, and the LCD output device underwent a color transformation by the GOG model.

• Journal of Multimedia Information System
• /
• 제5권2호
• /
• pp.83-86
• /
• 2018

Owing to high speed internet technologies, video conferencing systems are exploited in our home as well as work places using a laptop or a webcam. Although eye contact in the video conferencing system is significant, most systems do not support good eye contact due to improper locations of cameras. Several ideas have been proposed to solve the eye contact problem; however, some of them require complicated hardware configurations and expensive customized hardwares. In this paper, we propose a simple eye gaze correction method using the three-dimensional (3D) affine transformation. We also apply an image in-painting method to fill empty holes that are caused by round-off errors from the coordinate transformation. From experiments, we obtained visually improved results.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1987년도 한국자동제어학술회의논문집; 한국과학기술대학, 충남; 16-17 Oct. 1987
• /
• pp.109-114
• /
• 1987

In this thesis, we work on the curve recognition with real time processing and the Robot tracking method on recognized curve. Image information of segment curve is supplied to computer to run to a Robot so that it is a feedback system. Image coordinate frame to world coordinate transformation represents in this paper and curve matching algorithm subscribes by two method, first transformation matching algorithm, second image coordinate matching algorithm. Also Robot running time to computer image processing time relationships finally includes.

• 디지털산업정보학회논문지
• /
• 제8권3호
• /
• pp.133-145
• /
• 2012

This paper describes the high density discrete wavelet transformation which is one that expands an N point signal to M transform coefficients with M > N. The double-density discrete wavelet transform is one of the high density discrete wavelet transformation. This transformation employs one scaling function and two distinct wavelets, which are designed to be offset from one another by one half. And it is nearly shift-invariant. Similarly, triple-density discrete wavelet transformation is a new set of dyadic wavelet transformation with two generators. The construction provides a higher sampling in both time and frequency. Specifically, the spectrum of the first wavelet is concentrated halfway between the spectrum of the second wavelet and the spectrum of its dilated version. In addition, the second wavelet is translated by half-integers rather than whole-integers in the frame construction. This arrangement leads to high density wavelet transformation. But this new transform is approximately shift-invariant and has intermediate scales. In two dimensions, this transform outperforms the standard and double-density discrete wavelet transformation in terms of multiple directions. Resultingly, the proposed wavelet transformation services good performance in image and video processing fields.

• Journal of Information Processing Systems
• /
• 제19권3호
• /
• pp.370-376
• /
• 2023

Aiming at the problems of low image enhancement accuracy, long enhancement time and poor image quality in the traditional robot sequence motion image enhancement methods, an adaptive enhancement method for robot sequence motion image is proposed. The feature representation of the image was obtained by Karhunen-Loeve (K-L) transformation, and the nonlinear relationship between the robot joint angle and the image feature was established. The trajectory planning was carried out in the robot joint space to generate the robot sequence motion image, and an adaptive homomorphic filter was constructed to process the noise of the robot sequence motion image. According to the noise processing results, the brightness of robot sequence motion image was enhanced by using the multi-scale Retinex algorithm. The simulation results showed that the proposed method had higher accuracy and consumed shorter time for enhancement of robot sequence motion images. The simulation results showed that the image enhancement accuracy of the proposed method could reach 100%. The proposed method has important research significance and economic value in intelligent monitoring, automatic driving, and military fields.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 제14회 신호처리 합동 학술대회 논문집
• /
• 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.