• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06b
• /
• pp.240-245
• /
• 2008

컴퓨터 그래픽스에서 많은 광원들을 포함하는 장면을 사실적으로 렌더링하기 위해서는, 많은 양의 조명 계산을 수행해야 한다. 다수의 광원들로부터 빠르게 조명 계산을 하기 위해 많이 사용되는 기법 중에 몬테 카를로(Monte Carlo) 기법이 있다. 본 논문은 이러한 몬테 카를로(Monte Carlo) 기법을 기반으로, 다수의 광원들을 효과적으로 샘플링 할 수 있는 새로운 중요도 샘플링 기법을 제안한다. 제안된 기법의 두 가지 핵심 아이디어는 첫째, 장면 내에 다수의 광원이 존재하여도 어떤 특정 지역에 많은 영향을 주는 광원은 일부인 경우가 많다는 점이고 두 번째는 공간 일관성(spatial coherence)이 낮거나 그림자 경계 지역에 위치한 픽셀들은 영향을 받는 주요 광원이 서로 다르다는 점이다. 제안된 기법은 이러한 관찰에 착안하여 특정 지역에 광원이 기여하는 정도를 평가하고 이에 비례하게 확률 밀도 함수(PDF: Probability Density Function)를 결정하는 방법을 제안한다. 이를 위하여 이미지 공간상에서 픽셀들을 클러스터링(clustering)하고 클러스터 구조를 기반으로 대표 샘플을 선정한다. 선정된 대표 샘플들로부터 광원들의 기여도를 평가하고 이를 바탕으로 클러스터 단위의 확률 밀도 함수를 결정하여 최종 렌더링을 수행한다. 본 논문이 제안하는 샘플링 기법을 적용했을 때 전통적인 샘플링 방식과 비교하여 같은 샘플링 개수에서 노이즈(noise)가 적게 발생하는 좋은 화질을 얻을 수 있었다. 제안된 기법은 다수의 조명과 다양한 재질, 복잡한 가려짐이 존재하는 장면을 효과적으로 표현할 수 있다.

• Journal of Advanced Navigation Technology
• /
• v.19 no.2
• /
• pp.133-139
• /
• 2015

This paper surveys vision based autonomous navigation technologies for unmanned systems. Main branches of visual navigation technologies are visual servoing, visual odometry, and visual simultaneous localization and mapping (SLAM). Visual servoing provides velocity input which guides mobile system to desired pose. This input velocity is calculated from feature difference between desired image and acquired image. Visual odometry is the technology that estimates the relative pose between frames of consecutive image. This can improve the accuracy when compared with the exisiting dead-reckoning methods. Visual SLAM aims for constructing map of unknown environment and determining mobile system's location simultaneously, which is essential for operation of unmanned systems in unknown environments. The trend of visual navigation is grasped by examining foreign research cases related to visual navigation technology.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.7
• /
• pp.149-156
• /
• 2011

This paper proposes the effective edge selection algorithm for the rapid processing time and low memory usage of efficient graph-based image segmentation on mobile device. The graph-based image segmentation algorithm is to extract objects from a single image. The objects are consisting of graph edges, which are created by information of each image's pixel. The edge of graph is created by the difference of color intensity between the pixel and neighborhood pixels. The object regions are found by connecting the edges, based on color intensity and threshold value. Therefore, the number of edges decides on the processing time and amount of memory usage of graph-based image segmentation. Comparing to personal computer, the mobile device has many limitations such as processor speed and amount of memory. Additionally, the response time of application is an issue of mobile device programming. The image processing on mobile device should offer the reasonable response time, so that, the image segmentation processing on mobile should provide with the rapid processing time and low memory usage. In this paper, we demonstrate the performance of the effective edge selection algorithm, which effectively controls the edges of graph for the rapid processing time and low memory usage of graph-based image segmentation on mobile device.

• Journal of the Korea Computer Graphics Society
• /
• v.11 no.3
• /
• pp.28-33
• /
• 2005

본 논문은 색종이 리스트를 미리 생성하여 필요할 때마다 불러들여 찢어 붙이는 방법의 색종이 모자이크 렌더링 기법을 소개한다. 색종이 리스트는 색종이 이외에도 잡지와 같은 다양한 종이들을 미리 생성하여 사용할 수 있기 때문에 여러 가지 형태의 모자이크를 표현 할 수 있다는 장점을 가진다. 색종이 모자이크를 생성하기 위해서는 색종이 타일의 선택, 모양 결정, 그리고 배치의 3가지 과정을 거쳐야 한다. 먼저 색종이 타일을 붙일 위치에서 가장 알맞은 타일을 리스트로부터 선택하고, 적절한 모양으로 찢는다. 마지막으로 입력 영상의 특징(경계선 등)이 유지될 수 있도록 타일을 배치하여 최종 결과 영상을 생성한다.

• Proceedings of the KIEE Conference
• /
• 2003.07d
• /
• pp.2468-2470
• /
• 2003

비주얼 서보잉이란 로봇팔 등과 같은 제어기의 폐루프에서 입력단에 영상을 이용하는 것이다. 영상에 나타난 정보는 특징점을 통해 얻을 수 있으며, 매시간 이 특징점의 위치를 추적함으로써 제어기의 출력값을 결정한다. Optical flow를 이용하는 가나데 특징점 추적기는 특징점 추적기 중에서 성능이 우수하다고 알려져 있다. 본 논문에서는 가나데 특징점 추적기를 이용하여 실시간으로 로봇팔을 제어하고 결과를 분석하도록 한다. 실험에 이용되는 로봇팔은 전체 6축이며 기존의 5축 상용로봇의 end-effector에 ccd카메라를 좌우로 회전가능하도록 기구부를 추가하였다. 6DOF를 갖도륵 변형된 로봇팔을 기구적으로 분석하고 자코비안을 획득한 후, 로봇팔의 end-effector에 설치된 카메라를 통하여 특정 영상이 얻어지도록 로봇의 end-effector의 속도를 생성해내고, 자코비안의 역행렬을 통해 로봇의 각 관절을 제어하는 과정을 기술하고 분석한다.

• The Journal of the Korea Contents Association
• /
• v.9 no.6
• /
• pp.1-8
• /
• 2009

There are a lot of influences, such as location of camera, luminosity, brightness, and direction of light, which affect the performance of 2-dimensional image recognition. This paper suggests an adaptive method for face-image recognition in noisy environments using evolvable filtering and feature extraction which uses one sample image from camera. This suggested method consists of two main parts. One is the environmental-adjustment module which determines optimum sets of filters, filter parameters, and dimensions of features by using "steady state genetic algorithm". The other another part is for face recognition module which performs recognition of face-image using the previous results. In the processing, we used Gabor wavelet for extracting features in the images and k-Nearest Neighbor method for the classification. For testing of the adaptive face recognition method, we tested the adaptive method in the brightness noise, in the impulse noise and in the composite noise and verified that the adaptive method protects face recognition-rate's rapidly decrease which can be occurred generally in the noisy environments.

• The Journal of the Korea Contents Association
• /
• v.13 no.12
• /
• pp.38-47
• /
• 2013

An image coding based on MRC model, a kind of multi-layer image model, first segments a screen image into foreground, mask, and background layers, and then compresses each layer using a codec that is suitable to the layer. The mask layer defines the position of foreground regions such as textual and graphical contents. The colour signal of the foreground (background) region is saved in the foreground (background) layer. The mask layer which contains the segmentation result of foreground and background regions is of importance since its accuracy directly affects the overall coding performance of the codec. This paper proposes a new layer segmentation algorithm for the MRC based image coding. The proposed method extracts text pixels from the background using morphological top hat filtering. The application of white or black top hat transformation to local blocks is controlled by the information of relative brightness of text compared to the background. In the proposed method, the boundary information of text that is extracted from the edge map of the block is used for the robust decision on the relative brightness of text. Simulation results show that the proposed method is superior to the conventional methods.

• Journal of Satellite, Information and Communications
• /
• v.9 no.4
• /
• pp.1-6
• /
• 2014

Color image processing based on smoke detection is suitable detecting target to early detection of fire smoke. A method for detecting the smoke is processed in the pre-processing movement and color. And Next, characteristics of smoke such as diffusion, texture, shape, and directionality are used to post-processing. In this paper, propose the detection method of density distribution characteristic in characteristics of smoke. the generate a candidate regions by color thresholding image in Detecting the movement of smoke to the 10Frame interval and accumulated while 1second image. then check whether the pattern of the smoke by candidate regions to applying OBTP(Object Block Ternary Pattern). every processing is Block-based processing, moving detection is decided the candidate regions of the moving object by applying an adaptive threshold to frame difference image. The decided candidate region accumulates one second and apply the threshold condition of the smoke color. make the ternary pattern compare the center block value with block value of 16 position in each candidate region of the smoke, and determine the smoke by compare the candidate ternary pattern and smoke ternary pattern.

• The Journal of the Convergence on Culture Technology
• /
• v.5 no.3
• /
• pp.251-256
• /
• 2019

With the fast development of modern society, the interests concerned about the significance of nature and environment become major issue nowadays. Especially, threats for our health due to severe environmental pollution and fine dusts become serious problem with the fast industrialization of our society, and extra attention is focused on interests about conservation of nature and management of forest resources. Precious forest resources, however, are not properly managed and destroyed vainly due to frequent fire, damage by storms and floods, and unplanned land development. So systematic and scientific construction and management of forest resources are required in order to solve these problems efficiently. Furthermore, implementation of the forest resource information database that contains information of trees, Topography, ecosystem of the forest is urgently needed. In this paper, we design and implement the forest resource information database based on the information of location based forest resources and Topography using forest images taken by a drone, that enables us to manage forest resources efficiently, make decision for logging, and construct a future tree-planting project easily.

• Journal of the Korea Computer Graphics Society
• /
• v.30 no.3
• /
• pp.109-123
• /
• 2024

Research into vision-based end-to-end autonomous driving systems utilizing deep learning and reinforcement learning has been steadily increasing. These systems typically encode continuous and high-dimensional vehicle states, such as location, velocity, orientation, and sensor data, into latent features, which are then decoded into a vehicular control policy. The complexity of urban driving environments necessitates the use of state representation learning through networks like Variational Autoencoders (VAEs) or Convolutional Neural Networks (CNNs). This paper analyzes the impact of different image state encoding methods on reinforcement learning performance in autonomous driving. Experiments were conducted in the CARLA simulator using RGB images and semantically segmented images captured by the vehicle's front camera. These images were encoded using VAE and Vision Transformer (ViT) networks. The study examines how these networks influence the agents' learning outcomes and experimentally demonstrates the role of each state representation technique in enhancing the learning efficiency and decision- making capabilities of autonomous driving systems.