• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2000.08a
• /
• pp.325-328
• /
• 2000

텍스쳐 분석은 장면 분할, 물체 인식, 모양과 깊이 인식 등의 많은 영상 처리 분야에서 중요한 기술 중의 하나이다. 그러나 실영상에 포함된 다양한 텍스쳐 성분에 대해서 보편적으로 적용 가능한 효율적인 방법들에 대한 연구는 미흡한 실정이다. 본 논문에서는 텍스쳐 인식을 위해서 비교사 학습 방법에 기반 한 효율적인 텍스쳐 분석 기법을 제안한다. 제안된 방법은 텍스쳐 영상이 지닌 방향특징 정보로서 각(angle)과 강도(power)를 추출하여 자기 조직화 신경회로망에 의해서 블록기반으로 군집화(clustering)된다. 비교사적 군집 결과는 통합(merging)과 불림(dilation) 과정을 통해서 영상에 내재된 텍스쳐 성분의 분할을 수행한다. 제안된 시스템의 성능 평가를 위해서는 다양한 형태의 다중 텍스쳐 영상을 생성하여 적용한 후 그 유효성을 보인다.

• The KIPS Transactions:PartB
• /
• v.9B no.3
• /
• pp.327-336
• /
• 2002

Texture analysis is an important technique in many image understanding areas, such as perception of surface, object, shape and depth. But the previous works are intend to the issue of only texture segment, that is not capable of acquiring recognition information. No unsupervised method is basased on the recognition of texture in image. we propose a novel approach for efficient texture image analysis that uses unsupervised learning schemes for the texture recognition. The self-organization neural network for multiple texture image identification is based on block-based clustering and merging. The texture features used are the angle and magnitude in orientation-field that might be different from the sample textures. In order to show the performance of the proposed system, After we have attempted to build a various texture images. The final segmentation is achieved by using efficient edge detection algorithm applying to block-based dilation. The experimental results show that the performance of the system Is very successful.

• Korean Journal of Remote Sensing
• /
• v.30 no.2
• /
• pp.161-172
• /
• 2014

Established in the lower reaches of the Nakdong river in Busan, the Noksan national industrial complex is one of the deepest soft ground areas in Korea. In case of the costal landfill having deep soft ground, there is a significant residual settlement over a long period of time. In this study, there was observed ground subsidence occurred in the Noksan national industrial complex from September 2002 to April 2007 by applying DInSAR and SBAS time series method using RADARSAT-1 and Envisat SAR datasets. As a result, it was calculated that ground subsidence developed at the velocity of about maximum 10 cm/yr and mean 6 cm/yr at the eastern center, west, western center and southern area contiguous on the coastline of the study area during the period from September 2002 to April 2007. In addition, the RADARSAT-1 average displacement map has been compared with the total displacement map observed by accurate magnetic probe extensometer during the period from 2001 to 2002. Since the time series displacement has shown a linear trend mostly, we consider that continuous monitoring should be needed until the ground subsidence of the study area has been stabilized.

• Journal of Broadcast Engineering
• /
• v.19 no.6
• /
• pp.866-876
• /
• 2014

Generating of digital hologram of video contents with computer graphics(CG) requires natural fusion of 3D information between real and virtual. In this paper, we propose the system which can fuse real-virtual 3D information naturally and fast generate the digital hologram of fused results using multiple-GPUs based computer-generated-hologram(CGH) computing part. The system calculates camera projection matrix of RGB-Depth camera, and estimates the 3D information of virtual object. The 3D information of virtual object from projection matrix and real space are transmitted to Z buffer, which can fuse the 3D information, naturally. The fused result in Z buffer is transmitted to multiple-GPUs based CGH computing part. In this part, the digital hologram of fused result can be calculated fast. In experiment, the 3D information of virtual object from proposed system has the mean relative error(MRE) about 0.5138% in relation to real 3D information. In other words, it has the about 99% high-accuracy. In addition, we verify that proposed system can fast generate the digital hologram of fused result by using multiple GPUs based CGH calculation.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.95-96
• /
• 2021

본 논문에서는 단안비디오 입력으로부터 각 SAI(sub-aperture image)간의 넓은 기준선을 갖는 라이트필드 합성기법을 제안한다. 기존의 라이트필드 영상은 취득의 어려움에 의해 규모가 작고 특정 물체위주로 구성되어 있어 컴퓨터 비전 및 그래픽스 분야의 최신 딥러닝 기법들을 라이트필드 분야에 적용하기 어렵다는 문제를 갖고 있다. 이러한 문제점들을 해결하기 위해 사실적 렌더링 기반의 가상환경상에서 실제환경과 유사함을 갖는 데이터를 취득하였다. 생성한 데이터셋을 이용하여 기존의 새로운 시점을 생성하는 기법 중 하나인 다중 평면 영상(Multi Plane Image) 기반 합성기법을 통해 라이트필드 영상을 합성한다. 제안하는 네트워크는 단안비디오의 연속된 두개의 프레임으로부터 MPI 추정하는 네트워크와 입력영상의 깊이 정보를 추정하는 네트워크로 구성되어 있다.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_2
• /
• pp.961-973
• /
• 2020

In this manuscript, a new pansharpening model based on Convolutional Neural Network (CNN) was developed. Dilated convolution, which is one of the representative convolution technologies in CNN, was applied to the model by making it deep and complex to improve the performance of the deep learning architecture. Based on the dilated convolution, the residual network is used to enhance the efficiency of training process. In addition, we consider the spatial correlation coefficient in the loss function with traditional L1 norm. We experimented with Dilated Residual Networks (DRNet), which is applied to the structure using only a panchromatic (PAN) image and using both a PAN and multispectral (MS) image. In the experiments using KOMPSAT-3A, DRNet using both a PAN and MS image tended to overfit the spectral characteristics, and DRNet using only a PAN image showed a spatial resolution improvement over existing CNN-based models.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.45 no.6
• /
• pp.95-101
• /
• 2008

In this paper, we present a new smoothing algorithm for variable depth mapping for real time stereoscopic image for 3D display. Proposed algorithm is based on the physical concept, called Laplacian equation and we also discuss the mapping of the depth from scene to displayed image. The approach to solve the problem in stereoscopic image which we adopt in this paper is similar to multi-region algorithm which was proposed by N.Holliman. The main difference thing in our algorithm compared with the N.Holliman's multi-region algorithm is that we use the Laplacian equation by considering the distance between viewer and object. We implement the real time stereoscopic image generation method for OpenGL on the circular polarized LCD screen to demonstrate its real functioning in the visual sensory system in human brain. Even though we make and use artificial objects by using OpenGL to simulate the proposed algorithm we assure that this technology may be applied to stereoscopic camera system not only for personal computer system but also for public broad cast system.

• Electronics and Telecommunications Trends
• /
• v.28 no.6
• /
• pp.167-179
• /
• 2013

측면주사음탐기(side scan sonar) 센서는 해저면의 영상을 실시간으로 탐색하는 장비로서 해양탐사 및 지질조사, 해저통신 및 어초조사, 기뢰 및 잠수정 탐색 등 해양탐사와 관련한 대표적 장비라고 할 수 있다. 센서는 해저와 목표물을 표시하기 위해 소나 플랫폼의 움직임을 사용하며, 동작주파수 범위는 20kHz~500kHz이다. 이 주파수는 요구되는 깊이와 목표물의 크기에 의해서 결정된다. 센서는 수직으로 $45^{\circ}$, 수평으로 $2^{\circ}$ 정도의 신호전파 방사각도 폭을 가진다. 최근에는 해양탐사와 개발을 위해 빠른 스캔속도와 정확한 정보, 고해상도의 영상을 얻기 위해 해저면에 대한 다중빔 영상센서의 핵심기술로 활용되면서 그 활용성과 중요성이 점차 증가되고 있다. 본고에서는 측면주사소나 센서의 기본 원리 및 종류, 디중빔측면주사소나 기술동향, 응용분야의 사례를 소개함으로써, 국내 기반기술 및 상용화 개발이 취약한 측면주사 음탐기 센서에 대한 이해를 돕고자 한다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.6
• /
• pp.1311-1316
• /
• 2021

In this paper, we present a bifocal stereo camera system combining two cameras with different focal length cameras to generate stereoscopic image and their corresponding depth map. In order to obtain the depth data using the bifocal stereo camera system, we perform camera calibration to extract internal and external camera parameters for each camera. We calculate a common image plane and perform a image rectification for generating the depth map using camera parameters of bifocal stereo camera. Finally we use a SGM(Semi-global matching) algorithm to generate the depth map in this paper. The proposed bifocal stereo camera system can performs not only their own functions but also generates distance information about vehicles, pedestrians, and obstacles in the current driving environment. This made it possible to design safer autonomous vehicles.

• Journal of Advanced Navigation Technology
• /
• v.25 no.6
• /
• pp.569-575
• /
• 2021

Deep learning shows differences in prediction performance depending on data quality and model. This study uses various input data and multiple deep learning models to build an optimal deep learning model for predicting solar radiation, which has the most influence on power generation prediction. did. As the input data, the weather data of the Korea Meteorological Administration and the clairvoyant meteorological image were used by segmenting the image of the Korea Meteorological Agency. , comparative evaluation, and predicting solar radiation by constructing multiple deep learning models connecting the models with the best error rate in each model. As an experimental result, the RMSE of model A, which is a multiple deep learning model, was 0.0637, the RMSE of model B was 0.07062, and the RMSE of model C was 0.06052, so the error rate of model A and model C was better than that of a single model. In this study, the model that connected two or more models through experiments showed improved prediction rates and stable learning results.