• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.1
• /
• pp.38-46
• /
• 2004

Image segmentation is the task which partitions the image into meaningful regions and considered to be one of the most important steps in computer vision and image processing. Image segmentation is also widely used in object-based video compression such as MPEG-4 to extract out the object regions from the given frame. Watershed algorithm is frequently used to obtain the more accurate region boundaries. But, it is well known that the watershed algorithm is extremely sensitive to gradient noise and usually results in oversegmentation. To solve such a problem, we propose an image segmentation method which is robust to noise by using stabilized inverse diffusion equation (SIDE) and is more efficient in segmentation by employing multiresolution approach. In this paper, we apply both the region projection method using labels of adjacent regions and the region merging method based on region adjacency graph (RAG). Experimental results on noisy image show that the oversegmenation is reduced and segmentation efficiency is increased.

• The KIPS Transactions:PartB
• /
• v.12B no.4 s.100
• /
• pp.395-402
• /
• 2005

Object extraction is needed to track objects in color traffic image sequence. To extract objects, we use background differencing method based on MOG(Mixture of Gaussians). In extracted objects, shadows may be included. Due to shadows, we may not find exact location of objects and sometimes we find adjacent objects are glued together. Many methods have been proposed to remove shadows. Conventional methods usually assume that color and texture information are preserved under the shadow. Thus these methods do not work well if these assumptions do not hold. In this paper, we propose a new robust shadow removal method which works well in those situations. First we extract shadow pixel candidates by analysing color information and compute the ratio of shadow pixel candidates over the total number of Pixels. W the ratio is reasonable, we remove shadow candidate Pixels and if not, we use data in history array containing Previous removal records. We applied the method to real color traffic image sequences and obtained good results.

• The KIPS Transactions:PartA
• /
• v.8A no.4
• /
• pp.489-498
• /
• 2001

A new method for local control of arbitrary scattered data interpolation in the hyperbolic plane is developed in this paper. The issue associated with local control is very critical in the interactive in the interactive design field. Especially the suggested method in this paper could be effectively applied to the interactive shape modeling of genus-N objects, which are constructed on the hyperbolic plane. Since the effects of the changed data affects only the limited area around itself, it is more convenient for end-users to design a genus-N object interactively. Therefore, by improving the global interpolation on the hyperbolic plane where the genus-N object is constructed, this research is aiming at the development and implementation of the local interpolation on the hyperbolic plane. It is implemented using the following process. First, for localizing the interpolating functions, the hyperbolic domain is tessellated into arbitrary triangle patches and the group of adjacent triangle patches of each data point is defined as a sub-domain. On each sub-domain, a weight function is defined. Last, by blending of three weight functions on the overlapped triangles, local MQ interpolation is completed. Consequently, it is compared with the global MQ interpolation using several sample data and functions.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.264-266
• /
• 2022

In order to apply the RNN model to the radio fingerprint-based indoor path generation technology, the data set must be continuous and sequential. However, Wi-Fi radio fingerprint data is not suitable as RNN data because continuity is not guaranteed as characteristic information about a specific location at the time of collection. Therefore, continuity information of sequential positions should be given. For this purpose, clustering is possible through classification of each region based on signal data. At this time, the continuity information between the clusters does not contain information on whether actual movement is possible due to the limitation of radio signals. Therefore, correlation information on whether movement between adjacent clusters is possible is required. In this paper, a deep learning network, a recurrent neural network (RNN) model, is used to predict the path of a moving object, and it reduces errors that may occur when predicting the path of an object by generating continuous location information for path generation in an indoor environment. We propose a method of giving correlation between clustering for generating an improved moving path that can avoid erroneous path prediction that cannot move on the predicted path.

• Spatial Information Research
• /
• v.18 no.5
• /
• pp.93-105
• /
• 2010

Spatial neighborhoods are spaces which are relate to target space. A 3D spatial query which is a function for searching spatial neighborhoods is a significant function in spatial analysis. Various methodologies have been proposed in related these studies, this study suggests an adjacent based methodology. The methodology of this paper implements topological data for represent a adjacency via using network based topological data model, then apply modifiable Dijkstra's algorithm to each topological data. Results of ordering analysis about an adjacent space from a target space were visualized and considered ways to take advantage of. Object of this paper is to implement a 3D spatial query for searching a target space with a adjacent relationship in 3D space. And purposes of this study are to 1)generate adjacency based 3D network data via network based topological data model and to 2)implement a 3D spatial query for searching spatial neighborhoods by applying Dijkstra's algorithms to these data.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.1
• /
• pp.428-435
• /
• 2017

In this paper, we propose a novel motion field estimation algorithm for which a U-disparity map and forward-and-backward error removal are applied in a vehicular environment. Generally, a motion exists in an image obtained by a camera attached to a vehicle by vehicle movement; however, the obtained motion vector is inaccurate because of the surrounding environmental factors such as the illumination changes and vehicles shaking. It is, therefore, difficult to extract an accurate motion vector, especially on the road surface, due to the similarity of the adjacent-pixel values; therefore, the proposed algorithm first removes the road surface region in the obtained image by using a U-disparity map, and uses then the optical flow that represents the motion vector of the object in the remaining part of the image. The algorithm also uses a forward-backward error-removal technique to improve the motion-vector accuracy and a vehicle's movement is predicted through the application of the RANSAC (RANdom SAmple Consensus) to the previously obtained motion vectors, resulting in the generation of a motion field. Through experiment results, we show that the performance of the proposed algorithm is superior to that of an existing algorithm.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.1
• /
• pp.63-76
• /
• 1996

In this paper, we propose a new dynamic spatial index structure, called PR -file, for handling spatial objects and the modified hierarchical variance which measures the degree of spatial locality at each level. Under the assumption that a multidimensional search space has a circular domain, PR-file uses the modified hierarchical variance for clustering spatially adjacent objects. The insertion and splitting algorithms of PR_file preserve and index which has a low hierarchical variance regardless of object distributions. The simulation result shows that PR- file has a high hit ratio during a retrieval of objects by using an index with low hierarchical variance. And it shows a characteristic that the larger the bucket capacity, the higher the bucket utilization.

• The KIPS Transactions:PartB
• /
• v.10B no.4
• /
• pp.359-366
• /
• 2003

We propose a real-time stereoscopic image conversion method that can generate stereoscopic image with different perspective depth using motion parallax from 2-D image and offer realistic 3-D effect regardless of the direction and velocity of the moving object in the 2-D image. The stereoscopic image is generated by computing the motion parallax between adjacent two 2-D images using the proposed method for motion detection, region segmentation and depth map generation. The proposed method is suitable for real-time stereoscopic conversion processing on various image formats. It has been verified the proposed method by comparing between the stereoscopic image of the proposed method and that of MTD.

• Proceedings of the KSME Conference
• /
• 2007.05a
• /
• pp.814-819
• /
• 2007

Palletizing task is well-known time consuming and laborious process in factory, hence automation is seriously required. To do this, artificial robot is generally used. These systems however, mostly user teaches the robot point to point and to avoid time-variable obstacle, robot is required to attach the vision camera. These system structures bring about inefficiency and additional cost. In this paper we propose task-oriented trajectory generation algorithm for palletizing. This algorithm based on $A^{*}$ algorithm and slice plane theory, and modify the object dealing method. As a result, we show the elapsed simulation time and compare with old method. This simulation algorithm can be used directly to the off-line palletizing simulator and raise the performance of robot palletizing simulator not using excessive motion area of robot to avoid adjacent components or vision system. Most of all, this algorithm can be used to low-level PC or portable teach pendent

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.07a
• /
• pp.437-438
• /
• 2011

Spectral segmentation is a major trend in image segmentation. Specially, constrained spectral segmentation, inspired by the user-given inputs, remains its challenging task. Since it makes use of the spectrum of the affinity matrix of a given image, its overall quality depends mainly on how to design the graphical model. In this work, we propose a sparse, multi-layer graphical model, where the pixels and the over-segmented regions are the graph nodes. Here, the graph affinities are computed by using the must-link and cannot-link constraints as well as the likelihoods that each node has a specific label. They are then used to simultaneously cluster all pixels and regions into visually coherent groups across all layers in a single multi-layer framework of Normalized Cuts. Although we incorporate only the adjacent connections in the multi-layer graph, the foreground object can be efficiently extracted in the spectral framework. The experimental results demonstrate the relevance of our algorithm as compared to existing popular algorithms.