• Journal of Broadcast Engineering
• /
• v.13 no.2
• /
• pp.236-244
• /
• 2008

We propose a new building detection and description algorithm for Lidar data and photogrammetric imagery using color segmentation, line segments matching, perceptual grouping. Our algorithm consists of two steps. In the first step, from the initial building regions extracted from Lidar data and the color segmentation results from the photogrammetric imagery, we extract coarse building boundaries based on the Lidar results with split and merge technique from aerial imagery. In the secondstep, we extract precise building boundaries based on coarse building boundaries and edges from aerial imagery using line segments matching and perceptual grouping. The contribution of this algorithm is that color information in photogrammetric imagery is used to complement collapsed building boundaries obtained by Lidar. Moreover, linearity of the edges and construction of closed roof form are used to reflect the characteristic of man-made object. Experimental results on multisensor data demonstrate that the proposed algorithm produces more accurate and reliable results than Lidar sensor.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.2
• /
• pp.93-100
• /
• 2014

3D object recognition using only 2D images is a difficult work because each images are generated different to according to the view direction of cameras. Because SIFT algorithm defines the local features of the projected images, recognition result is particularly limited in case of input images with strong perspective transformation. In this paper, we propose the object recognition method that improves SIFT algorithm by using several sequential images captured from rotating 3D object around a rotation axis. We use the geometric relationship between adjacent images and merge several images into a generated feature space during recognizing object. To clarify effectiveness of the proposed algorithm, we keep constantly the camera position and illumination conditions. This method can recognize the appearance of 3D objects that previous approach can not recognize with usually SIFT algorithm.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.39 no.6
• /
• pp.565-574
• /
• 2002

We propose an algorithm for the robust transmission of video in error prone environment based on multiple description (MD) scheme and simple rate-distortion operators. The redundancy rate-distortion (RRD) criteria is used to split a one-layer compressed video stream into two correlated descriptions. The proposed algorithm can find more candidate points on the RRD curve than the conventional RRD based methods. A new distortion measure is also defined in this paper, which considers more realistic error environments. Since the proposed MD video coder is based on the standard H.263 coder, each description can be decoded independently by the standard H.263 decoder. Also, several descriptions can be decoded into a single stream by additional merge stage and the H.263 decoder. Simulation results show that the proposed MD video coder yields better performance than the conventional MD splitting algorithm at all bitrates both in single and two description cases.

• The Journal of the Korea Contents Association
• /
• v.8 no.7
• /
• pp.1-8
• /
• 2008

In this paper, an algorithm to compensate the inter-view mismatch in the multi-view video according to the different characteristics of cameras is presented. Interview mismatches make it difficult to merge the multi-view images and decrease the coding performance. So, a preprocessing operation to compensate the mismatches is requisite in the multi-view video coding. It is shown that the mismatch in the outputs of multi-view cameras with different electro-optical transfer functions can be approximated with a linear model of a gain and an offset. In addition, a new algorithm for estimating and compensating the inter-view mismatch based on the detection of the overlapped region is presented. Experimental results using various rectified stereo images show that the proposed method compensates inter-view mismatches more accurately compared to the conventional approach.

• Journal of Korea Society of Industrial Information Systems
• /
• v.18 no.2
• /
• pp.19-25
• /
• 2013

In this paper, we propose an approach to tracking road regions from video sequences. The proposed method segments and tracks road regions by utilizing the prior information from the result of the previous frame. For the efficiency of the system, we have a simple assumption that the road region is usually shown in the lower part of input images so that lower 60% of input images is set to the region of interest(ROI). After initial segmentation using flood-fill algorithm, we merge neighboring regions based on color similarity measure. The previous segmentation result, in which seed points for the successive frame are extracted, is used as prior information to segment the current frame. The similarity between the road region of the previous frame and that of the current frame is measured by the modified Jaccard coefficient. According to the similarity we refine and track the detected road regions. The experimental results reveal that the proposed method is effective to segment and track road regions in noisy and non-noisy environments.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.5
• /
• pp.129-139
• /
• 2012

Given digraph network $D=(N,A),n{\in}N,a=c(u,v){\in}A$ with source s and sink t, the maximum flow from s to t is determined by cut (S, T) that splits N to $s{\in}S$ and $t{\in}T$ disjoint sets with minimum cut value. The Ford-Fulkerson (F-F) algorithm with time complexity $O(NA^2)$ has been well known to this problem. The F-F algorithm finds all possible augmenting paths from s to t with residual capacity arcs and determines bottleneck arc that has a minimum residual capacity among the paths. After completion of algorithm, you should be determine the minimum cut by combination of bottleneck arcs. This paper suggests maximum adjacency merging and compute cut value method is called by MA-merging algorithm. We start the initial value to S={s}, T={t}, Then we select the maximum capacity $_{max}c(u,v)$ in the graph and merge to adjacent set S or T. Finally, we compute cut value of S or T. This algorithm runs n-1 times. We experiment Ford-Fulkerson and MA-merging algorithm for various 8 digraph. As a results, MA-merging algorithm can be finds minimum cut during the n-1 running times with time complexity O(N).

• Journal of computational fluids engineering
• /
• v.13 no.4
• /
• pp.126-134
• /
• 2008

We developed a three dimensional Navier-Stokes code based on the level set method to simulate two phase flows with high density ratio. The Navier-Stokes equations with consideration of the surface tension effects are solved by using SIMPLE algorithm on a non-staggered grid. The present code is validated by simulating two test problems. First one is to simulate a rising bubble inside a cube. The thickness of the interface of the bubble is shown to affect the pressure distribution around the interface. As the thickness decreases, the pressure field around the interface becomes more oscillatory. As the bubble rises, a ring vortex is shown to form around the interface and the bubble eventually develops into an ellipsoidal shape. Merge of two bubbles inside a container is secondly tested to show the robustness of the present code for two phase flow simulation. Numerical results show stable and reliable behavior during the process of merging of two bubbles. The velocity and pressure fields around the interface of bubbles are shown oscillation free during the merging of two bubbles.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.22 no.1
• /
• pp.53-60
• /
• 1985

A computer vision system for robot is developed which can recognize a variety of two dimensional complex objects in gray level noisy scenes. the system is also capable of determining the position and orientation of the objects for robotlc manipulation. The hardware of the vision system is developed and a new edge tracking technique is also proposed. The linked edges are approximated to sample line drawing by split and merge algorithm. The system extracts many features from line drawing and constructs relational structure by the concave and convex hull of objects. In matching process, the input obhects are compared with the objects database which is formed by learning ability. Thelearning process is so simple that the system is very flexible. Several examples arc shown to demonstrate the usefulness of this system.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.44 no.6
• /
• pp.11-20
• /
• 2007

This paper proposes a new efficient method to detect ellipses using a segment merging based Randomized Hough Transform. The key idea of the proposed method is to separate single line segments from an edge image, to estimate ellipses from any pair of the single line segments using Randomized Hough Transform (RHT), and to merge the ellipses. This algorithm is able to accuracy estimate the number of ellipses and largely improves the computational time by reducing iterations.

• Journal of KIISE:Software and Applications
• /
• v.28 no.1
• /
• pp.14-25
• /
• 2001

For having various applications, XML is widely used in various fields. But, there have not been proposed a system to integrate and manage XML and its applications together. In this paper, we propose methods to integrate web-based XML applications(SMIL, RDF, WIDL) and for object-oriented modeling of each DTD and document instance. We prppose and system to merge object modeling of XML applications. With the proposed integrating algorithm, we can not only easily analysis various web-based XML applications which is represented by complex tags but also generate object-oriented schema for each document and store it to OODBMS.