• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.30 no.6_1
• /
• pp.583-590
• /
• 2012

This study proposes fusion image matching method according to land cover property to generate a detailed DEM using the high resolution IKONOS-2 stereo pair. A classified image, consists of building, crop-land, forest, road and shadow-water, is produced by color image with four bands. Edges and points are also extracted from panchromatic image. Matching is performed by the cross-correlation computing after five classes are automatically selected in a reference image. In each of building class, crop-land class, forest class and road class, matching was performed by the grid and edge, only grid, only grid, grid and point, respectively. Shadow-water class was excepted in the matching because this area causes excessive error of the DEM. As the results, edge line, building and residential area could be expressed more dense than DEM by the conventional method.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.25 no.1
• /
• pp.9-17
• /
• 2007

In this study, Digital Elevation Models (DEMs) were constructed from color images, grayscale images and each bands (Red, Green, Blue) of color image, and the accuracies of each DEMs were evaluated, And then, correlation coefficients between left and right images of each stereopairs were analyzed. The DEM can be constructed conventionally from the digital map and stereopair images using image matching. The image matching requires stereo satellite images or aerial photographs. In case of rotor aerial photographs, these are to be scanned in 3 bands (Red, Green, Blue). For this study, 5 types of images were acquired; color, grayscale, RED band, GREEN band, and BLUE band image. DEMs were constructed from 5 types of stereopair images and evaluated using elevation points of digital maps. In order to analyze the cause of various accuracies of each DEMs, the similarity between left and right images of each stereopairs were analyzed. Consequently, the accuracy of the DEM constructed from RED band images of color aerial photograph were proved best.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.1D
• /
• pp.153-160
• /
• 2009

In relation to digital elevation model(DEM) production using high resolution satellite imagery, existing studies present that DEM accuracy differently show according to land cover property. This study therefore proposes auto-selection method of window size for correlation matching according to land cover property of IKONOS Geo-level stereo image. For this, land cover classified image is obtained by IKONOS color image with four bands. In addition, correlation-coefficients are computed at regular intervals in pixels of the window-search area to shorten of matching time. As the results, DEM by the proposed method showed more accurate than DEM using the fixed window-size matching. We estimate that accuracy of the proposed DEM improved more than DEM by digital map and ERDAS in agricultural land.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.12
• /
• pp.168-175
• /
• 2013

Color consistency in stereoscopic contents is important for 3D display systems. Even with a stereo camera of the same model and with the same hardware settings, complex color discrepancies occur when acquiring high quality stereo images. In this paper, we propose an integrated color matching method that use cumulative histogram in global matching and estimated 3D-distance for the stage of local matching. The distance between the current pixel and the target local region is computed using depth information and the spatial distance in the 2D image plane. The 3D-distance is then used to determine the similarity between the current pixel and the target local region. The overall algorithm is described as follow; First, the cumulative histogram matching is introduced for reducing global color discrepancies. Then, the proposed local color matching is established for reducing local discrepancies. Finally, a weight-based combination of global and local matching is computed. Experimental results show the proposed algorithm has improved global and local error correction performance for stereoscopic contents with respect to other approaches.

• Journal of KIISE:Computer Systems and Theory
• /
• v.32 no.10
• /
• pp.520-529
• /
• 2005

A feature-based 3D modeling algorithm is presented in this paper. Since conventional methods use depth-based techniques, they need much time for the image matching to extract depth information. Even feature-based methods have less computation load than that of depth-based ones, the calculation of modeling error about whole pixels within a triangle is needed in feature-based algorithms. It also increase the computation time. Therefore, the proposed algorithm consists of three phases, which are an initial 3D model generation, model evaluation, and model refinement phases, in order to acquire an efficient 3D model. Intensity gradients and incremental Delaunay triangulation are used in the Initial model generation. In this phase, a morphological edge operator is adopted for a fast edge filtering, and the incremental Delaunay triangulation is modified to decrease the computation time by avoiding the calculation errors of whole pixels and selecting a vertex at the near of the centroid within the previous triangle. After the model generation, sparse vertices are matched, then the faces are evaluated with the size, approximation error, and disparity fluctuation of the face in evaluation stage. Thereafter, the faces which have a large error are selectively refined into smaller faces. Experimental results showed that the proposed algorithm could acquire an adaptive model with less modeling errors for both smooth and abrupt areas and could remarkably reduce the model acquisition time.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2007.04a
• /
• pp.149-152
• /
• 2007

The horizontal geo-location accuracy of KOMPSAT-2, without GCPs (Ground Control Points) is 80 meters CE90 for monoscopic image of up to 26 degrees off-nadir angle, after processing including POD (Precise Orbit Determination), PAD(Precise Attitude Determination) and AOCS (Attitude and Orbit Control Subsystem) sensor calibration. In case of multiple stereo images, without GCPs, the vertical geometric accuracy is less than 22.4 meters LE 90 and the horizontal geometric accuracy is less than 25.4 meters. There are two types of sensor model for KOMPSAT-2, direct sensor model and Rational Function Model (RFM). In general, a sensor model relates object coordinates to image coordinates The major objective of this investigation is to check and verify the geometrical performance when initial KOMPSAT-2 images are employed and briefly introduce the sensor model of KOMPSAT-2.

• Journal of the Korean Society of Industry Convergence
• /
• v.23 no.3
• /
• pp.463-471
• /
• 2020

Recently, various tries to apply ROV (Remotely Operated Vehicle) into underwater are being developed. However, due to underwater environment uniqueness, the additional problem must be taken into account when designing an ROV for the inspection of the underwater structure. This is because a GPS-based information method cannot be applied, and the obtainable image is also dependent on the turbidity. Also, it is necessary to be able to satisfy waterproof and operating speeds in consideration of most practical application environments. This paper describes the design results of the ROV system for underwater structure inspection considering the above problems. The designed system applied INS / DVL for location recognition and was configured to support 3D mapping and stereo camera-based image information using sonar depending on visibility. To satisfy the waterproof, a pressure vessel using a composite material was applied. And over-actuated system using eight thrusters to maintain a stable posture and operating speed was applied also. The designed system was verified by structural analysis and flow analysis also.

• Journal of Korea Multimedia Society
• /
• v.19 no.6
• /
• pp.1003-1013
• /
• 2016

This paper proposes a framework of superpixel-based vehicle detection method using plane normal vector in disparity space. We utilize two common factors for detecting vehicles: Hypothesis Generation (HG) and Hypothesis Verification (HV). At the stage of HG, we set the regions of interest (ROI) by estimating the lane, and track them to reduce computational cost of the overall processes. The image is then divided into compact superpixels, each of which is viewed as a plane composed of the normal vector in disparity space. After that, the representative normal vector is computed at a superpixel-level, which alleviates the well-known problems of conventional color-based and depth-based approaches. Based on the assumption that the central-bottom of the input image is always on the navigable region, the road and obstacle candidates are simultaneously extracted by the plane normal vectors obtained from K-means algorithm. At the stage of HV, the separated obstacle candidates are verified by employing HOG and SVM as for a feature and classifying function, respectively. To achieve this, we trained SVM classifier by HOG features of KITTI training dataset. The experimental results demonstrate that the proposed vehicle detection system outperforms the conventional HOG-based methods qualitatively and quantitatively.

• Journal of Advanced Navigation Technology
• /
• v.13 no.5
• /
• pp.705-713
• /
• 2009

This paper proposes CORBA-based visual servoing system of humanoid robot. To effectively control the humanoid robot which is connected to network, it needs to define necessary services for visual servoing as distribution object, and realize them in the middleware. For realizing it following services should be addressed. Naming service for searching a necessary service with unique name assigned to each object, image service for supplying image obtained from stereo camera. In the experiment, we show the result of balloon tracking and bursting that the robot tracks balloons as target objects in the real time, and if a balloon stop for a certain time, then the robot bursts the balloon.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.6
• /
• pp.547-554
• /
• 2013

This paper proposes a novel formation algorithm of identical robots based on object tracking method using omni-directional images obtained through fisheye lenses which are mounted on the robots. Conventional formation methods of multi-robots often use stereo vision system or vision system with reflector instead of general purpose camera which has small angle of view to enlarge view angle of camera. In addition, to make up the lack of image information on the environment, robots share the information on their positions through communication. The proposed system estimates the region of robots using SURF in fisheye images that have $360^{\circ}$ of image information without merging images. The whole system controls formation of robots based on moving directions and velocities of robots which can be obtained by applying Lucas-Kanade Optical Flow Estimation for the estimated region of robots. We confirmed the reliability of the proposed formation control strategy for multi-robots through both simulation and experiment.