• Journal of the Korea Society for Simulation
• /
• v.27 no.2
• /
• pp.1-10
• /
• 2018

This paper presents an autonomous detection and aiming point computation of a battle tank by using RGB images. Maximally stable extremal regions algorithm was implemented to find features of the tank, which are matched with images extracted from streaming video to figure out the region of interest where the tank is present. The median filter was applied to remove noises in the region of interest and decrease camouflage effects of the tank. For the tank segmentation, k-mean clustering was used to autonomously distinguish the tank from its background. Also, both erosion and dilation algorithms of morphology techniques were applied to extract the tank shape without noises and generate the binary image with 1 for the tank and 0 for the background. After that, Sobel's edge detection was used to measure the outline of the tank by which the aiming point at the center of the tank was calculated. For performance measurement, accuracy, precision, recall, and F-measure were analyzed by confusion matrix, resulting in 91.6%, 90.4%, 85.8%, and 88.1%, respectively.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.12B
• /
• pp.2320-2334
• /
• 1999

In this paper, we propose multiple IS-MMBS service schemes for very low power and micro-size RMIMS (radio-interfaced micro information monitoring system) terminals. In MMBS service area, when new arrival RMIMS terminals have real-time traffic characteristic or large traffic bandwidth, only single IS-MMBS service scheme can not guarantee RMIMS terminal's QoS(quality of service) such as buffer overflow or packet loss. In this case, the proposed multiple IS-MMBS service schemes can be effectively used for QoS service of RMIMS terminal. According to clustering method of RMIMS terminals and MMBS segment method, the proposed schemes can be divided into terminal segment method, region segment method, application based segment method, traffic type based segment method, overlapping segment method and hybrid segment method

• Convergence Security Journal
• /
• v.12 no.6
• /
• pp.25-30
• /
• 2012

As the network composed of numerous sensor nodes, sensor network conducts the function of sensing the surrounding information by sensor and of the sensed information. Our military has also developed ICT(Information and Communication Technology) along with the methods for effective war by sharing smooth information of battlefield resources through network with each object. In this paper, a sensor network is clustered in advance and a cluster header (CH) is elected for clusters. Before deployment, a certificate is provided between the BS and the sensor nodes, and after clustering, authentication is done between the BS and the sensor nodes. Moreover, inter-CH authentication technique is used to allow active response to destruction or replacement of sensor nodes. Also, because authentication is done twice, higher level of security can be provided.

• The Journal of the Korea Contents Association
• /
• v.11 no.1
• /
• pp.26-33
• /
• 2011

In ubiquitous environments that numerous mobile objects exist, the location-based services have risen as an important application field. For efficient location-based services, various techniques with broadcast schemes have been studied. However, they were mainly concerned with the implementation of a broadcast index and did not consider techniques for reducing the size of the entire broadcast data. Therefore, this paper proposes a data distribution broadcast scheme based on sensor networks that considers the mobile patterns of an object in road network environments. In this paper we also propose a road network based sensor clustering technique for the efficiency of the proposed distributed broadcast scheme. In order to show the superiority of the proposed scheme, we compare it with the existing broadcast scheme in various environments.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.14 no.5
• /
• pp.243-248
• /
• 2014

This study presents an investigation into the ways to detect the areas of object movement with Kinect's Depth Frame, which is capable of receiving 3D information regardless of external light sources. Applied to remove noises along the boundaries of objects among the depth information received from sensors were the blurring technique for the x and y coordinates of pixels and the frequency filter for the z coordinate. In addition, a clustering filter was applied according to the changing amounts of adjacent pixels to extract the areas of moving objects. It was also designed to detect fast movements above the standard according to filter settings, being applicable to mobile robots. Detected movements can be applied to security systems when being delivered to distant places via a network and can also be expanded to large-scale data through concerned information.

• Journal of Broadcast Engineering
• /
• v.25 no.1
• /
• pp.48-57
• /
• 2020

Recently, with the rapid development of image recognition technology, the demand for object analysis in road CCTV videos is increasing. In this paper, we propose a method that can adaptively find the counting line for traffic analysis in road CCTV videos. First, vehicles on the road are detected, and the corresponding positions of the detected vehicles are modeled as the two-dimensional pointwise Gaussian map. The paths of vehicles are estimated by accumulating pointwise Gaussian maps on successive video frames. Then, we apply clustering and linear regression to the accumulated Gaussian map to find the principal direction of the road, which is highly relevant to the counting line. Experimental results show that the proposed method for detecting the counting line is effective in various situations.

• Journal of KIISE
• /
• v.45 no.1
• /
• pp.15-21
• /
• 2018

Low-Rank Representation (LRR) based methods are widely used in many practical applications, such as face clustering and object detection, because they can guarantee high prediction accuracy when used to constructing graphs in graph - based semi-supervised learning. However, in order to solve the LRR problem, it is necessary to perform singular value decomposition on the square matrix of the number of data points for each iteration of the algorithm; hence the calculation is inefficient. To solve this problem, we propose an improved and faster LRR method based on the recently published Fast LRR (FaLRR) and suggests ways to introduce and optimize additional constraints on the underlying optimization goals in order to address the fact that the FaLRR is fast but actually poor in classification problems. Our experiments confirm that the proposed method finds a better solution than LRR does. We also propose Fast MLRR (FaMLRR), which shows better results when the goal of minimizing is added.

• Journal of Digital Convergence
• /
• v.12 no.11
• /
• pp.379-386
• /
• 2014

In this paper, the processing speed of Grabcut algorithm in order to efficiently improve the GPU (Graphics Processing Unit) for processing the data from the method. Grabcut algorithm has excellent performance object detection algorithm. Grabcut existing algorithms to split the foreground area and the background area, and then background and foreground K-cluster is assigned a cluster. And assigned to gradually improve the results, until the process is repeated. But Drawback of Grabcut algorithm is the time consumption caused by the repetition of clustering. Thus GPGPU (General-Purpose computing on Graphics Processing Unit) using the repeated operations in parallel by processing Grabcut algorithm to effectively improve the processing speed of the method. We proposed method of execution time of the algorithm reduced the average of about 95.58%.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.40 no.1
• /
• pp.30-38
• /
• 2003

This paper presents an efficient region-based motion segmentation method for segmenting of moving objects in a traffic scene with a focus on a Video Monitoring System (VMS). The presented method consists of two phases: motion detection and motion segmentation. Using the adaptive thresholding technique, the differences between two consecutive frames are analyzed to detect the movements of objects in a scene. To segment the detected regions into meaningful objects which have the similar intensity and motion information, the regions are initially segmented using a k-means clustering algorithm and then, the neighboring regions with the similar motion information are merged. Since we deal with not the whole image, but the detected regions in the segmentation phase, the computational cost is reduced dramatically. Experimental results demonstrate robustness in the occlusions among multiple moving objects and the change in environmental conditions as well.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.5
• /
• pp.1155-1163
• /
• 2011

In this paper, we propose a new pre-processing algorithm applied to depth map to improve the coding efficiency. Now, 3DV/FTV group in the MPEG is working for standard of 3DVC(3D video coding), but compression method for depth map images are not confirmed yet. In the proposed algorithm, after dividing the histogram distribution of a given depth map by EM clustering method based on GMM, we classify the depth map into several layered images. Then, we apply different mean shift filter to each classified image according to the existence of background or foreground in it. In other words, we try to maximize the coding efficiency while keeping the boundary of each object and taking average operation toward inner field of the boundary. The experiments are performed with many test images and the results show that the proposed algorithm achieves bits reduction of 19% ~ 20% and computation time is also reduced.