• Korean Journal of Remote Sensing
• /
• v.15 no.1
• /
• pp.31-38
• /
• 1999

In this paper, we introduce an algorithm for the ortho-rectification of high resolution pushbroom-type satellite images. The generation of ortho-images in the ultimate level of the satellite image preprocessing which also includes systematic geocoding and precision geocoding. It is also essential for the mapping of satellite images because topotraphic maps are based on the orthographic projection. The newly developed ortho-image generation algorithm introduced in this paper is on the line of the algorithms previously developed (Shin and Lee, 1997; Shin e 1998). Various experimental results are shown in this paper. The results show that the algorithm completely eliminates the disparities in the perspectively viewed images which were caused by the terrain height. The absolute accuracy of the developed algorithm depends on the accuracy of the camera model and the digital elevation model used.

• Journal of Broadcast Engineering
• /
• v.19 no.4
• /
• pp.533-546
• /
• 2014

This paper presents a method for a hybrid (color and depth) camera system construction using a photogrammetric technology. A TOF depth camera is efficient since it measures range information of objects in real-time. However, there are some problems of the TOF depth camera such as low resolution and noise due to surface conditions. Therefore, it is essential to not only correct depth noise and distortion but also construct the hybrid camera system providing a high resolution texture map for generating a 3D model using the depth camera. We estimated geometry of the hybrid camera using a traditional relative orientation algorithm and performed texture mapping using backward mapping based on a condition of collinearity. Other algorithm was compared to evaluate performance about the accuracy of a model and texture mapping. The result showed that the proposed method produced the higher model accuracy.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06b
• /
• pp.498-500
• /
• 2012

비디오 해석 및 추적기술은 특정한 시스템에서만 적용되는 것이 아니다. 이것은 비디오 내에서 의미 있는 정보를 능동적으로 감시 대상을 정의, 해석, 모델화, 추정 및 추적 할 수 있는 기반 기술을 의미하다. 일반적으로 감시시스템에서 감시 대상은 사람이나 차량이며, 상황에 따라 출입통제 구역으로 설정하기도 한다. 이는 연속된 영상에서 객체의 형태, 모양, 행동 분석, 움직임, 색상정보를 가지고 데이터 정의, 검출, 모델화를 통하여 인식, 식별 그리고 추적한다. 본 논문에서는 비디오 영상분석을 통해 단일카메라기반의 감시시스템과 PTZ 카메라기반 감시시스템 제안한다. 이때 단일 카메라기반의 감시는 배경생성방법을 이용하여 연속된 영상내의 객체를 지속적으로 관리가 가능하도록 설계하였고, PTZ 카메라기반의 감시는 카메라의 이동에 따른 배경안정화 방법과 카메라의 절대좌표를 활용하여 카메라 이동을 제어함과 동시에 오검출 문제를 해결하였다. 실험 및 결과분석으로는 시나리오 환경에서 배경생성방법을 이용한 검출의 정확성과 PTZ카메라 위치 변화에도 강인한 검출 결과를 비교 분석하였다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.11a
• /
• pp.119-121
• /
• 2019

부가적 백색 잡음 모델(additive white Gaussian noise, AWGN에서 학습된 깊은 신경만 (deep neural networks)을 이용한 잡음 제거기는 제거하려는 잡음이 AWGN인 경우에는 뛰어난 성능을 보이지만 실제 카메라 잡음에 대해서 잡음 제거를 시도하였을 때는 성능이 크게 저하된다. 본 논문은 U-Net 구조의 깊은 인공신경망 모델에 residual block을 결합함으로서 실제 카메라 영상에서 기존 알고리즘보다 뛰어난 성능을 지니는 신경망을 제안하다. 제안한 방법을 통해 Darmstadt Noise Dataset에서 PSNR과 SSIM 모두 CBDNet 대비 향상됨을 확인하였다.

• The Journal of Korean Institute of Information Technology
• /
• v.17 no.8
• /
• pp.11-19
• /
• 2019

Against advanced image-related crimes, a high level of digital forensic methods is required. However, feature-based methods are difficult to respond to new device features by utilizing human-designed features, and deep learning-based methods should improve accuracy. This paper proposes a deep learning model to identify camera models based on DenseNet, the recent technology in the deep learning model field. To extract camera sensor features, a HPF feature extraction filter was applied. For camera model identification, we modified the number of hierarchical iterations and eliminated the Bottleneck layer and compression processing used to reduce computation. The proposed model was analyzed using the Dresden database and achieved an accuracy of 99.65% for 14 camera models. We achieved higher accuracy than previous studies and overcome their disadvantages with low accuracy for the same manufacturer.

• Proceedings of the KSME Conference
• /
• 2005.11a
• /
• pp.130.1-130.1
• /
• 2005

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2014.11a
• /
• pp.88-89
• /
• 2014

본 논문에서는 미리 모델링된 실객체에 대한 3차원 모델을 변형하면서 애니메이션을 정의하고, 실사 객체를 추적하면서 카메라 뷰 상의 실사 객체에 애니메이션을 적용하는 방법을 제안한다. 애니메이션 정의는 라플라시안 기반 메쉬 변형 방법으로 3차원 모델을 변형시키며 키프레임을 지정함으로써 이루어진다. 정의된 애니메이션은 실제 환경에서 추적된 실사 객체의 영상으로부터 모델에 텍스처를 입힌 뒤, 카메라 포즈를 이용하여 객체 위치에 객체 모델을 렌더링할 때 적용된다. 제안된 방법을 통해 사용자가 원하는 대로 실제 환경에 대한 카메라 뷰 상에서 실사 객체가 변형되는 모습을 용이하게 보여줄 수 있다.

• Journal of KIISE:Software and Applications
• /
• v.35 no.12
• /
• pp.780-788
• /
• 2008

Modeling hand poses and tracking its movement are one of the challenging problems in computer vision. There are two typical approaches for the reconstruction of hand poses in 3D, depending on the number of cameras from which images are captured. One is to capture images from multiple cameras or a stereo camera. The other is to capture images from a single camera. The former approach is relatively limited, because of the environmental constraints for setting up multiple cameras. In this paper we propose a method of reconstructing 3D hand poses from a 2D input image sequence captured from a single camera by means of Belief Propagation in a graphical model and recognizing a finger clicking motion using a hidden Markov model. We define a graphical model with hidden nodes representing joints of a hand, and observable nodes with the features extracted from a 2D input image sequence. To track hand poses in 3D, we use a Belief Propagation algorithm, which provides a robust and unified framework for inference in a graphical model. From the estimated 3D hand pose we extract the information for each finger's motion, which is then fed into a hidden Markov model. To recognize natural finger actions, we consider the movements of all the fingers to recognize a single finger's action. We applied the proposed method to a virtual keypad system and the result showed a high recognition rate of 94.66% with 300 test data.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.38 no.2
• /
• pp.27-32
• /
• 2001

In this paper, the three dimension scanner system employing the parallel camera model is discussed. The camera calibration process and the three dimension scanning algorithm are developed. The laser strip line is utilized for assisting stereo matching. An object being scanned rotates on the plate which is activated by a stepping motor, The world coordinate which is. the measured distance from the camera to the object is converted into the model coordinate. The facets created from the point. cloud of the model coordinate is used for rendering the scanned model by using the graphic library such as OpenGL. The unmatched points having no validate matching points are interpolated from the validate matching points of the vicinity epipolar lines.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.39 no.12
• /
• pp.1160-1165
• /
• 2011

This study is focused on the structural dynamic responses, i.e., vibration analysis results of the high-accuracy observation multi-axial camera, which is installed and operated for the UAV (Unmanned Aerial Vehicle) and helicopter etc. And, the authors newly suggest a modeling technology of the ball bearing applied to the camera by using three-axis spring elements. The vibration analysis results well agreed to the randum vibration test results. Also, the vibration responses characteristics of the multi-axial camera through the time history analysis of the random vibration were analyzed and evaluated. The above results can be applied to the FE-modeling of the ball bearings used for the space cameras.