• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• 제20권1호
• /
• pp.47-57
• /
• 2002

The intention of this study is to construct the spatial database and to extract attribute data which are able to complete the omitted data in the topographical map or completion map of construction using the image data of various form such as artificial satellite images, aerial photographs, terrestrial photographs and so on. This study used the single frame images only for the raw image data, supposing the case of rigorous photogrammetric method is not available or rapid acquisition of information is need. The extracted spatial and attribute data from the images are used for modifying and updating the database, and for providing visual effect useful for guide and management of the facilities. This study intended to develop the technique able to apply in the case where comparative high accuracy is not required or rapid modification is necessary, and to verify the possibility of editing and updating the digital map using the photographs or video images remained as old data. Many of previous research on the management system for university facility has been accomplished focusing on the design and construction of database itself. Otherwise, this study aimed for the construction of guide and management system based on compiling the digital map of present state using multi-imagery, and the more applicability was intended too.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• 제33권4C호
• /
• pp.321-329
• /
• 2008

H.264/AVC video coding standard enables a considerably higher improvement in coding efficiency compared with previous standards such as MPEG-2, H.263 and MPEG-4. To achieve this, for each macro-block in H.264/AVC, Rate-Distortion Optimization (RDO) technique is employed to select the best motion vector, reference frame, and macro-block mode. As a result, computational complexity is increased significantly whereas RDO achieve higher improvement. This paper presents fast intra mode selection algorithm based on constraints of frequency characteristics which are derived from intra coding modes of H.264/AVC. First of all, we observe the features of each intra mode through the frequency analysis of image. And then proposed Frequency Error Costs (FECs) are calculated to select the best mode which has minimum cost. Computational complexity is considerably reduced because rate-distortion costs only calculate the candidate modes which are set of best mode and its neighbouring two modes. Experimental results show that proposed algorithm reduces the complexity dramatically maintaining the rate-distortion performance compared with H.264/AVC reference software.

• The Transactions of the Korea Information Processing Society
• /
• 제6권2호
• /
• pp.274-281
• /
• 1999

Many popularly used recent high-sped and high-capacity disks use the Zone-Structured in which a disk consists of multiple zones. A zone-structured disk has multiple zones, and the bandwidth and the number of sectors in each zone are different from each other. When the previous studies that modeled disks based on the assumption that the number of sectors in all tracks are same are applied to the zone-structured disk and the video data stored in a round-robin manner are read out with the SCAN technique, the transfer rate of the disk is fixed with that of the innermost zone. And excessive disk space is wasted either. To resolve the problem, this paper proposes a method for reconstructing the physical zones into logical zones by split and merge operations and develops a method for determining optimum transfer block size.

• Journal of Biomedical Engineering Research
• /
• 제27권5호
• /
• pp.250-259
• /
• 2006

The information of eye movement is used in various fields such as psychology, ophthalmology, physiology, rehabilitation medicine, web design, HMI(human-machine interface), and so on. Various devices to detect the eye movement have been developed but they are too expensive. The general methods of eye movement tracking are EOG(electro-oculograph), Purkinje image tracker, scleral search coil technique, and video-oculograph(VOG). The purpose of this study is to embody the algorithm which tracks the location of the gazing point at a pupil. Two kinds of location data were compared to track the gazing point. One is the reference points(infrared LEDs) which is effected from the globe. Another is the center point of the pupil which is gained with a CCD camera. The reference point was captured with the CCD camera and infrared lights which were not recognized by human eyes. Both of images which were thrown and were not thrown an infrared light on the globe were captured and saved. The reflected reference points were detected with the brightness difference between the two saved images. In conclusion, the circumcenter theory of a triangle was used to look for the center of the pupil. The location of the gazing point was relatively indicated with the each center of the pupil and the reference point.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• 제20권5호
• /
• pp.83-99
• /
• 2021

With the advent of the fourth industrial revolution, studies on driving management and driving strategies of autonomous vehicles are emerging. While obtaining microscopic traffic data on vehicles is essential for such research, we also see that conventional traffic data collection methods cannot collect the driving behavior of individual vehicles. In this study, UAV videos were used to collect traffic data from the viewpoint of the aerial base that is microscopic. To overcome the limitations of the related research in the literature, the micro-traffic data were estimated using the multiple object tracking of deep learning and an image registration technique. As a result, the speed obtained error rates of MAE 3.49 km/h, RMSE 4.43 km/h, and MAPE 5.18 km/h, and the traffic obtained a precision of 98.07% and a recall of 97.86%.

• Journal of the Korean Society of Laryngology, Phoniatrics and Logopedics
• /
• 제29권2호
• /
• pp.98-102
• /
• 2018

Background and Objectives : Detection of vascular abnormalities in vocal cord (VC) leukoplakia is important for the diagnosis of neoplastic change of the mucosa. The aim of this study was to investigate the value of i-scan in the differential diagnosis of VC leukoplakia based on visualization of abnormal vascular features. Material and Methods : Fifty-two patients with leukoplakia were enrolled in the study. Images of their larynx obtained using conventional white light endoscopy and an i-scan-enhanced endoscopy (Pentax DEFINA EPK-3000 Video Processors, with Pentax VNLJ10) were reviewed. The microvascular features of the lesions and vascular changes were analyzed and the results were compared with the histopathologic diagnosis. Results : Among the 52 leukoplakia patients, 7 (13.5%) patients had squamous hyperplasia, 10 (19.3%) mild dysplasia, 2 (3.8%) moderate dysplasia, 14 (26.9%) severe dysplasia, 4 (7.7%) carcinoma in situ, and 15 (28.8%) invasive squamous cell carcinoma on histopathologic examination. Using i-scan-enhanced endoscopy, abnormal vascular change with neoplastic neoangiogenesis was detected in most cases of malignant VC lesion [severe dysplasia : 9/14 (64.3%), carcinoma in situ: 2/4 (50.0%), and invasive squamous cell carcinoma : 11/15 (73.4%)]. Conclusion : i-scan-enhanced endoscopy is a useful optical technique for the diagnosis of VC leukoplakia. Our results suggest that i-scan may be a promising diagnostic tool in the early detection of laryngeal cancer.

• Korean Journal of Head & Neck Oncology
• /
• 제34권2호
• /
• pp.29-34
• /
• 2018

Background/Objectives: The aim of this study was to investigate the diagnostic value of i-scan in the differential diagnosis of oral cavity leukoplakia based on visualization of abnormal vascular features. Materials & Methods: Thirty- one patients with oral cavity leukoplakia were enrolled in the study. Images of their oral cavity obtained using conventional white light endoscopy and an i-scan-enhanced endoscopy (Pentax DEFINA EPK-3000 Video Processors, with Pentax VNLJ10) were reviewed. The microvascular features of the lesions and vascular changes were analyzed and the results were compared with the histopathologic diagnosis. Results: Among the 31 oral cavity leukoplakia patients, 8 (25.8%) patients revealed hyperkeratosis, 10 (31.2%) low-grade dysplasia, 5 (16.2%) high-grade dysplasia and 8 (25.8%) invasive squamous cell carcinoma on histopathologic examination. Using i-scan-enhanced endoscopy, we could found abnormal vascular change with neoplastic neoangiogenesis in most high-grade dysplasia or invasive cancer in oral cavity. (high-grade dysplasia: 4/5 [80.0%], and invasive squamous cell carcinoma: 7/8 [87.5%]). Conclusion: i-scan-enhanced endoscopy could be a useful optical technique for the diagnosis of oral cavity leukoplakia. Our results suggest that i-scan may be a promising diagnostic tool in the early detection of suspected oral mucosal lesion.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• 제18권6호
• /
• pp.63-68
• /
• 2018

Offloading is a method of communicating, processing, and receiving results from some of the applications performed on local computers to overcome the limitations of computing resources and computational speed.Recently, it has been applied in mobile games, multimedia data, 360-degree video processing, and image processing for Internet broadcasting to speed up processing and reduce battery consumption in the mobile computing sector. This paper implements a viewer that enables users to convert various flat-panel images and view contents in a wireless Internet environment and presents actual results of an experiment so that users can easily understand the images. The 360 degree spherical image is successfully converted to a plane image with Double Panorama, Quad, Single Rectangle, 360 Overview + 3 Rectangle depending on the image acquisition position of the 360 degree camera through the interface. During the experiment, more than 100 360 degree spherical images were successfully converted into plane images through the interface below.

• KIPS Transactions on Computer and Communication Systems
• /
• 제8권7호
• /
• pp.167-176
• /
• 2019

Recently, as the types of services that can be enjoyed in mobile telecommunication networks such as social networks and video streaming are increasing, mobile users(MUs) can access mobile contents easily by consuming mobile data. However, under a mobile telecommunication environment, MUs have to pay a high data fee to a network service provider(SP) in order to enjoy contents. The 'data sponsor' technique, introduced as a way to solve this problem, has attracted attention as a breakthrough method for enhancing contents accessibility of MUs. In this paper, we propose an algorithm that determines the optimal discount rate through the Stackelberg game in the data sponsor environment. We also propose an algorithm to design edge caching, which caches highly popular content for MUs on edge server, through many-to-many matching game. Simulation results clearly indicate that the profit for CP's content consumption is improved by about 6~11%, and the profit of CP according to the ratio of edge caching is improved by about 12% than the other existing schemes under data sponsor environment.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• 제24권5호
• /
• pp.576-583
• /
• 2020

This paper proposes a technique to determine the spam comments on YouTube, which have recently seen tremendous growth. On YouTube, the spammers appeared to promote their channels or videos in popular videos or leave comments unrelated to the video, as it is possible to monetize through advertising. YouTube is running and operating its own spam blocking system, but still has failed to block them properly and efficiently. Therefore, we examined related studies on YouTube spam comment screening and conducted classification experiments with six different machine learning techniques (Decision tree, Logistic regression, Bernoulli Naive Bayes, Random Forest, Support vector machine with linear kernel, Support vector machine with Gaussian kernel) and ensemble model combining these techniques in the comment data from popular music videos - Psy, Katy Perry, LMFAO, Eminem and Shakira.