• Proceedings of the KSRS Conference
• /
• 2008.10a
• /
• pp.37-40
• /
• 2008

The purpose of this paper is to extract DEMs from Spot-3 strips using orbit modeling technique. Spot-3 stereo strip images along 420km in distance were used for experiments. The orbit modeling technique has been suggested to establish accurate geometric models for a whole strip taken on the same orbit using only a small number of GCPs on the top area of the strip. This method enables extraction of orientation parameters of the scene along the strip that is needed to generate DEMs. Consequently, we were able to extract DEMs over the areas without accurate GCPs obtained by GPS surveying per each scene. Assessment of accuracy was carried out using USGS DTED. DEMs generated from the orbit modelling technique suggested showed satisfactory performance when quantitative analysis of accuracy assessment was carried out.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2011.10a
• /
• pp.107-108
• /
• 2011

A methodology to measure 3-dimensional vibrational displacement of a structure by digital photogrammetry is proposed in this paper. Stereo digital images of a vibrating structure were obtained by two non-metric cameras. Then by applying the collinearity condition to the images, the 3-d displacement time history data of a point or many points can be calculated by the present methodology. Experimental work was performed to measure the displacement time history for a cantilever beam excited by a piezoelectric patch, in which the in-depth displacement data obtained by the proposed method well matched the laser sensor data.

• Proceedings of the KSRS Conference
• /
• 1998.09a
• /
• pp.163-168
• /
• 1998

Extracting a Digital Elevation Model (DEM) from spaceborne imagery is important for cartographic applications of remote sensing data. The procedure for such DEM generation can be divided into stereo matching, sensor modelling and DEM interpolation. Among these, DEM interpolation contributes significantly to the completeness and accuracy of a DEM and, yet, this technique is often considered "trivial". However, na\ulcornere DEM interpolation may result in a less accurate and sometimes meaningless DEM. This paper reports the performance analysis of various DEM interpolation techniques. Using a manually derived DEM as reference, a number of sample points were created randomly. Different interpolation techniques were applied to the sample points to generate DEMs. The performance of interpolation was assessed by the accuracy of such DEMs. The results showed that kriging gave the best results at all times whereas nearest neighborhood interpolation provided a fast solution with moderate accuracy when sample points were large enough.

• Proceedings of the KSR Conference
• /
• 2008.06a
• /
• pp.553-558
• /
• 2008

Advancement in information technology have enabled applying vision sensor to railway, such as CCTV. CCTV has been widely used in railway application, however the CCTV is a passive system that provide limited capability to maintain safety from boarding platform. The station employee should monitor continuously CCTV monitors. Therefore immediate recognition and response to the situation is difficultin emergency situation. Recently, urban transit operators are pursuing applying an unattended station operation system for their cost reduction. Therefore, an intelligent monitoring system is need for passenger's safety in railway. The paper proposes a vision based monitoring system and object detection algorithm for passenger's safety in railway platform. The proposed system automatically detects accident in platform and analyzes level of danger using image processing technology. The system uses stereo vision technology with multi-sensors for minimizing detection error in various railway platform conditions.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.13 no.2
• /
• pp.73-81
• /
• 2018

This paper describes a device platform which the blind can wear to keep path and to get surrounding information during their independent walking. Compared to the existing technologies, the proposed device could be used indoors and outdoors, and maps need not be provided in advance. It is composed of a glasses type device equipped with image sensors, and a portable device that analyzes sensor data for sighted guiding. RGB images and depth images are extracted to generate a walking map based on feature points. It also can cope with the risk of collision with bollard, color cone by applying vertical obstacle detection technology based on floor detection.

• International Journal of Precision Engineering and Manufacturing
• /
• v.6 no.4
• /
• pp.60-66
• /
• 2005

In this paper, we propose the basic measurement method of a 3D digitizer using a CCD camera in detail. In the localization measurement with a CCD camera, the effect of the background light and the sensitivity consideration are always problems in realizing a high precision. In this research, a new measurement principle is proposed in which the pulse compression technique known in radar is used to eliminate the effect of background light even under a low intensity light source, and the coordinate values on the CCD camera image plane are determined accurately. From the quantitative evaluation of the S/N ratio improvement and the fundamental experiment, it is verified that a substantial improvement in the S/N ratio is realized for both the background noise and the pixel noise and that a resolution of less than the pixel is sufficiently possible.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38C no.10
• /
• pp.920-927
• /
• 2013

Chroma key technique which composes images by separating an object from its background in specific color has restrictions on color and space. Especially, unlike general chroma key technique, image composition for stereo 3D display requires natural image composition method in 3D space. The thesis attempted to compose images in 3D space using depth keying method which uses high resolution depth information. High resolution depth map was obtained through camera calibration between the DSLR and Kinect sensor. 3D mesh model was created by the high resolution depth information and mapped with RGB color value. Object was converted into point cloud type in 3D space after separating it from its background according to depth information. The image in which 3D virtual background and object are composed obtained and played stereo 3D images using a virtual camera.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.10
• /
• pp.35-42
• /
• 2014

It is possible to improve the obstacle avoidance capability by training and recognizing the obstacles which is in certain indoor environment. We propose the technique that use underlying intensity value along with intensity map from RGB-D image which is derived from stereo vision Kinect sensor and recognize an obstacle within constant distance. We test and experiment the accuracy and execution time of the pattern recognition algorithms like PCA, ICA, LDA, SVM to show the recognition possibility of it. From the comparison experiment between RGB-D data and intensity data, RGB-D data got 4.2% better accuracy rate than intensity data but intensity data got 29% and 31% faster than RGB-D in terms of training time and intensity data got 70% and 33% faster than RGB-D in terms of testing time for LDA and SVM, respectively. So, LDA, SVM have good accuracy and better training/testing time to use for obstacle avoidance based on intensity dataset of mobile robot.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.55 no.4
• /
• pp.173-180
• /
• 2006

A key component of autonomous navigation of intelligent home robot is localization and map building with recognized features from the environment. To validate this, accurate measurement of relative location between robot and features is essential. In this paper, we proposed relative localization algorithm based on 3D reconstruction of scale invariant features of two images which are captured from two parallel cameras. We captured two images from parallel cameras which are attached in front of robot and detect scale invariant features in each image using SIFT(scale invariant feature transform). Then, we performed matching for the two image's feature points and got the relative location using 3D reconstruction for the matched points. Stereo camera needs high precision of two camera's extrinsic and matching pixels in two camera image. Because we used two cameras which are different from stereo camera and scale invariant feature point and it's easy to setup the extrinsic parameter. Furthermore, 3D reconstruction does not need any other sensor. And the results can be simultaneously used by obstacle avoidance, map building and localization. We set 20cm the distance between two camera and capture the 3frames per second. The experimental results show :t6cm maximum error in the range of less than 2m and ${\pm}15cm$ maximum error in the range of between 2m and 4m.

• Journal of Sensor Science and Technology
• /
• v.7 no.6
• /
• pp.418-425
• /
• 1998

Stereo cameras are the most widely used sensing systems for automated machines including robots to interact with their three-dimensional(3D) working environments. The position of a target point in the 3D world coordinates can be measured by the use of stereo cameras and the camera calibration is an important preliminary step for the task. Existing camera calibration techniques can be classified into two large categories - linear and nonlinear techniques. While linear techniques are simple but somewhat inaccurate, the nonlinear ones require a modeling process to compensate for the lens distortion and a rather complicated procedure to solve the nonlinear equations. In this paper, a method employing a neural network for the calibration problem is described for tackling the problems arisen when existing techniques are applied and the results are reported. Particularly, it is shown experimentally that by utilizing the function approximation capability of multi-layer neural networks trained by the back-propagation(BP) algorithm to learn the error pattern of a linear technique, the measurement accuracy can be simply and efficiently increased.