• Journal of KIISE:Software and Applications
• /
• v.36 no.11
• /
• pp.936-946
• /
• 2009

A graph cuts method has recently attracted a lot of attentions for image segmentation, as it can globally minimize energy functions composed of data term that reflects how each pixel fits into prior information for each class and smoothness term that penalizes discontinuities between neighboring pixels. In previous approaches to graph cuts-based automatic image segmentation, GMM(Gaussian mixture models) is generally used, and means and covariance matrixes calculated by EM algorithm were used as prior information for each cluster. However, it is practicable only for clusters with a hyper-spherical or hyper-ellipsoidal shape, as the cluster was represented based on the covariance matrix centered on the mean. For arbitrary-shaped clusters, this paper proposes graph cuts-based image segmentation using mean shift analysis. As a prior information to estimate the data term, we use the set of mean trajectories toward each mode from initial means randomly selected in $L^*u^*{\upsilon}^*$ color space. Since the mean shift procedure requires many computational times, we transform features in continuous feature space into 3D discrete grid, and use 3D kernel based on the first moment in the grid, which are needed to move the means to modes. In the experiments, we investigate the problems of mean shift-based and normalized cuts-based image segmentation methods that are recently popular methods, and the proposed method showed better performance than previous two methods and graph cuts-based automatic image segmentation using GMM on Berkeley segmentation dataset.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.30 no.4
• /
• pp.335-342
• /
• 2012

3D point cloud is widely used in Architecture, Civil Engineering, Medical, Computer Graphics, and many other fields. Due to the improvement of 3D laser scanner, a massive 3D point cloud whose gigantic file size is bigger than computer's memory requires efficient preprocessing and visualization. We suggest a data structure to solve the problem; a 3D point cloud is gradually subdivided by arbitrary-sized cube grids structure and corresponding point cloud subsets generated by the center of each grid cell are achieved while preprocessing. A massive 3D point cloud file is tested through two algorithms: QSplat and ours. Our algorithm, grid-based, showed slower speed in preprocessing but performed faster rendering speed comparing to QSplat. Also our algorithm is further designed to editing or segmentation using the original coordinates of 3D point cloud.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.9
• /
• pp.2605-2625
• /
• 2024

Siamese-based segmentation and tracking algorithms improve accuracy and stability for video object segmentation and tracking tasks simultaneously. Although effective, variability in target appearance and background clutter can still affect segmentation accuracy and further influence the performance of tracking. In this paper, we present a memory propagation-based target-aware and mask-attention decision network for robust object segmentation and tracking. Firstly, a mask propagation-based attention module (MPAM) is constructed to explore the inherent correlation among image frames, which can mine mask information of the historical frames. By retrieving a memory bank (MB) that stores features and binary masks of historical frames, target attention maps are generated to highlight the target region on backbone features, thus suppressing the adverse effects of background clutter. Secondly, an attention refinement pathway (ARP) is designed to further refine the segmentation profile in the process of mask generation. A lightweight attention mechanism is introduced to calculate the weight of low-level features, paying more attention to low-level features sensitive to edge detail so as to obtain segmentation results. Finally, a mask fusion mechanism (MFM) is proposed to enhance the accuracy of the mask. By utilizing a mask quality assessment decision network, the corresponding quality scores of the "initial mask" and the "previous mask" can be obtained adaptively, thus achieving the assignment of weights and the fusion of masks. Therefore, the final mask enjoys higher accuracy and stability. Experimental results on multiple benchmarks demonstrate that our algorithm performs outstanding performance in a variety of challenging tracking tasks.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.11 no.4
• /
• pp.89-97
• /
• 2015

In this paper, a method of color image segmentation based on DBSCAN(Density Based Spatial Clustering of Applications with Noise) using compactness of superpixels and texture information is presented. The DBSCAN algorithm can generate clusters in large data sets by looking at the local density of data samples, using only two input parameters which called minimum number of data and distance of neighborhood data. Superpixel algorithms group pixels into perceptually meaningful atomic regions, which can be used to replace the rigid structure of the pixel grid. Each superpixel is consist of pixels with similar features such as luminance, color, textures etc. Superpixels are more efficient than pixels in case of large scale image processing. In this paper, superpixels are generated by SLIC(simple linear iterative clustering) as known popular. Superpixel characteristics are described by compactness, uniformity, boundary precision and recall. The compactness is important features to depict superpixel characteristics. Each superpixel is represented by Lab color spaces, compactness and texture information. DBSCAN clustering method applied to these feature spaces to segment a color image. To evaluate the performance of the proposed method, computer simulation is carried out to several outdoor images. The experimental results show that the proposed algorithm can provide good segmentation results on various images.

• Proceedings of the KIEE Conference
• /
• 2015.07a
• /
• pp.331-332
• /
• 2015

Since $20^{th}$ century, along with the rapid industrial advancement, the concentrated urban development in specific large cities have made people migrate to those cities, thus causing problems in the power system stability. In case of Korea, more than 40% of the power system demand comes from the consumers in Seoul Metropolitan area and the rate is expected to increase. With the continuous increase of power demand, in order to meet the demand for system reliability improvement, the power system was multi-looped for reliability enhancement, the problem of fault current happened. In this situation, there are several methods for fault current reduction likes current limiting reactor, replacing circuit breaker, splitting busses, etc. But these methods reached its limit, power system needs more fundamental solutions such as grid segmentation. In this paper, we assume grid segmentation already has been progressed using VSC BTB HVDC. Then, this paper discusses operating point of HVDC in metropolitan area considering loss minimization and handy flow control. The simulation is proceeded on 2027 KEPCO system.

• Journal of Auto-vehicle Safety Association
• /
• v.16 no.2
• /
• pp.20-26
• /
• 2024

The delivery using drones has been attracting attention because it can innovatively reduce the delivery time from the time of order to completion of delivery compared to the current delivery system, and there have been pilot projects conducted for safe drone delivery. However, the current drone delivery system has the disadvantage of limiting the operational efficiency offered by fully autonomous delivery drones in that drones mainly deliver goods to pre-set landing sites or delivery bases, and the final delivery is still made by humans. In this paper, to overcome these limitations, we propose obstacle detection and landing site selection algorithm based on a vision sensor that enables safe drone landing at the delivery location of the product orderer, and experimentally prove the possibility of station-to-door delivery. The proposed algorithm forms a 3D map of point cloud based on simultaneous localization and mapping (SLAM) technology and presents a grid segmentation technique, allowing drones to stably find a landing site even in places without prior information. We aims to verify the performance of the proposed algorithm through streaming data received from the drone.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.1137-1139
• /
• 2003

This paper proposed a practical method for building detection and extraction using airborne laser scanning data. The proposed method consists mainly of two processes: low and high level processes. The major distinction from the previous approaches is that we introduce a concept of pseudogrid (or binning) into raw laser scanning data to avoid the loss of information and accuracy due to interpolation as well as to define the adjacency of neighboring laser point data and to speed up the processing time. The approach begins with pseudo-grid generation, noise removal, segmentation, grouping for building detection, linearization and simplification of building boundary , and building extraction in 3D vector format. To achieve the efficient processing, each step changes the domain of input data such as point and pseudo-grid accordingly. The experimental results shows that the proposed method is promising.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.12 no.3
• /
• pp.320-330
• /
• 2012

In this paper, we investigate the power integrity of grid structures for power and ground distribution on printed circuit board (PCB). We propose the 2D transmission line method (TLM)-based model for efficient frequency-dependent impedance characterization and PCB-package-integrated circuit (IC) co-simulation. The model includes an equivalent circuit model of fringing capacitance and probing ports. The accuracy of the proposed grid model is verified with test structure measurements and 3D electromagnetic (EM) simulations. If the grid structures replace the plane structures in PCBs, they should provide effective shielding of the electromagnetic interference in mobile systems. An analytical model to predict the shielding effectiveness (SE) of the grid structures is proposed and verified with EM simulations.

• International Journal of Computer Science & Network Security
• /
• v.22 no.5
• /
• pp.143-148
• /
• 2022

Brain tumor classification is an important process that allows doctors to plan treatment for patients based on the stages of the tumor. To improve classification performance, various CNN-based architectures are used for brain tumor classification. Existing methods for brain tumor segmentation suffer from overfitting and poor efficiency when dealing with large datasets. The enhanced CNN architecture proposed in this study is based on U-Net for brain tumor segmentation, RefineNet for pattern analysis, and SegNet architecture for brain tumor classification. The brain tumor benchmark dataset was used to evaluate the enhanced CNN model's efficiency. Based on the local and context information of the MRI image, the U-Net provides good segmentation. SegNet selects the most important features for classification while also reducing the trainable parameters. In the classification of brain tumors, the enhanced CNN method outperforms the existing methods. The enhanced CNN model has an accuracy of 96.85 percent, while the existing CNN with transfer learning has an accuracy of 94.82 percent.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.27 no.1
• /
• pp.723-733
• /
• 2009

This study proposes a sequence of procedures to extract building boundaries and planar patches through segmentation of rasterized lidar data. Although previous approaches to building extraction have been shown satisfactory, there still exist needs to increase the degree of automation. The methodologies proposed in this study are as follows: Firstly, lidar data are rasterized into grid form in order to exploit its rapid access to neighboring elevations and image operations. Secondly, propagation of errors in raw data is taken into account for in assessing the quality of gradients-driven properties and further in choosing suitable parameters. Thirdly, extraction of planar patches is conducted through a sequence of processes: histogram analysis, least squares fitting, and region merging. Experimental results show that the geometric components of building models could be extracted by the proposed approach in a streamlined way.