• Proceedings of the KIEE Conference
• /
• 1992.07a
• /
• pp.449-452
• /
• 1992

Before performing an adaptive stereo matching using satellite images, classification is needed as a preprocessing step. This paper describes that classification of three land cover types : river, mountain, and agricultural fields. We proposed that classification algorithm using pyramid structure and texture features. Results of applying the proposed algorithm to satellite image improved classification accuracy.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.605-606
• /
• 2008

The distance detection system receives stereo video input through 2 CCD cameras. Using a decoder, the image is changed to the YCbCr4:2:2 format and only the Y signal is saved in the 4*256*8bit shift register of the Dual-Port SRAM. As a result of the matching procedure, the Depth value, which is the distance information, is saved in SRAM, and the Depth Map is made and output to the TFT-LCD screen.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.91.2-91
• /
• 2001

This paper describes the path planning of an autonomous mobile robot using one camera-based sequence image processing. As an assumption, all objects in front of the mobile robot are located on the same plane where robot moves. Using the moving camera grounded on the autonomous mobile robot, the robot extracts the angular points of obstacle objects, calculates the height using the assumption and discrepancy between two consecutive images. In the image processing, angular points of objects must correspond so that they deliver the size of objects. Thus, the robot passes through if the object has not the height, like the paper or the shadow projected. Otherwise, the robot passes aside if ...

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.100.4-100
• /
• 2002

For visual navigation, mobile robot can use a stereo camera which has large field of view. In this paper, we propose an algorithm to detect and recognize human face on the basis of such camera system. In this paper, a new coarse to fine detection algorithm is proposed. For coarse detection, nearly face-like areas are found in entire image using dual ellipse templates. And, detailed alignment of facial outline and features is performed on the basis of view- based multiple appearance model. Because it hard to finely align with facial features in this case, we try to find most resembled face image area is selected from multiple face appearances using most distinguished facial features- two eye...

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.233-237
• /
• 2009

This paper represents a new approach which addresses quality degradation of a synthesized view, when a virtual camera moves forward. Generally, interpolation technique using only two neighboring views is used when a virtual view is synthesized. Because a size of the object increases when the virtual camera moves forward, most methods solved this by interpolation in order to synthesize a virtual view. However, as it generates a degraded view such as blurred images, we prevent a synthesized view from being blurred by using more cameras in multiview camera configuration. That is, we solve this by applying super-resolution concept which reconstructs a high resolution image from several low resolution images. Therefore, data fusion is executed by geometric warping using a disparity of the multiple images followed by deblur operation. Experimental results show that the image quality can further be improved by reducing blur in comparison with interpolation method.

• 한국지형공간정보학회:학술대회논문집
• /
• 1995.10a
• /
• pp.121-142
• /
• 1995

Using SPOT satellite imagery, 3 dimensional geographic information can be obtained from SPOT's oblique viewing image. Especially, SPOT provides high spatial resolution, adequate base/height ratio and stable orbit characteristics. In this paper, 3D terrain features were extracted using SPOT stereo image and also the techniques for generation of 3D graphic data were developed for the extracted terrain features. We developed computer programs to generate automatically 3D graphic files and to display geographic information on the computer screen. The results of this study may be effectively utilized for the development of 3D geographic information using satellite images.

• The Journal of Korea Robotics Society
• /
• v.2 no.2
• /
• pp.129-136
• /
• 2007

This paper introduces a position-based robust visual servoing method which is developed for operation of a human-like robot with two arms. The proposed visual servoing method utilizes SIFT algorithm for object detection and CAMSHIFT algorithm for object tracking. While the conventional CAMSHIFT has been used mainly for object tracking in a 2D image plane, we extend its usage for object tracking in 3D space, by combining the results of CAMSHIFT for two image plane of a stereo camera. This approach shows a robust and dependable result. Once the robot's task is defined based on the extracted 3D information, the robot is commanded to carry out the task. We conduct several position-based visual servoing tasks and compare performances under different conditions. The results show that the proposed visual tracking algorithm is simple but very effective for position-based visual servoing.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.5 no.2
• /
• pp.47-55
• /
• 1987

In this paper, the direct linear transformation is described in which a inner and exterior orientation parameters are treated as unknown for non-iterative direct space resection, and the computer program was developed to obtain object space coordinates. Image coordinates measurements are conducted with analogue stereo-plotter and digitizer. To prove the appropriateness of the two image coordinate measurement devices and the DLT method, the standard errors of object space coordinates are compared with semi-analytical method.

• 한국지형공간정보학회:학술대회논문집
• /
• 2004.10a
• /
• pp.33-37
• /
• 2004

고해상 입체 위성영상 엄밀 모델링(Rigorous Modeling)을 구현하고, 이를 기반으로 각 입체시 영상을 제작하여 3차원 정확도 평가를 수행하였다. 본 연구 지역으로 진주지역의 SPOTS 입체영상을 이용하였으며, 각 영상별 기준점 자료는 1/5000 수치지도를 이용하여 입체영상의 중복영역 내에 균등하게 지상기준점 40점을 추출하였다. 추출된 점을 각각 기준점과 검사점으로 구분하여 엄밀 모델링의 정확도를 분석하였다. 또한, 입체시 제작시에 기준점으로 사용된 지상좌표와 이에 대응하는 영상점을 이용하여 입체시 영상을 제작하였다. 제작된 입체시 영상에서 동일점을 획득하기 위해 영상 매칭 및 수치해석도화기(Helava System)를 이용하여 정확한 영상점을 획득하여 3차원 좌표를 계산하여 정확도 평가를 수행하였다.

• Journal of the Optical Society of Korea
• /
• v.20 no.3
• /
• pp.413-426
• /
• 2016

There has been much advancement in the field of aerial cameras for geographical features with the help of drones, image processing power and computer aided optical programs. In this study, we propose a new optical lens design technique which minimizes the amount of ‘the third order Seidel aberration’ for enhancing MTF. In addition, we suggest a new optical lens design which stabilizes the mass-production yield through R.S.M and has robustness secure through the Taguchi method. Eventually, the image processing algorithm of stereo matching is implemented in order to evaluate whether the proposed lens design result meets adequate specifications for the use of dual aerial photographs or not. This paper provides good guidance for the optical design by development of experiments.