• Journal of Broadcast Engineering
• /
• v.13 no.3
• /
• pp.310-318
• /
• 2008

The H.264/AVC standard achieves higher coding efficiency than previous video coding standards with the rate-distortion optimization (RDO) technique which selects the best coding mode and reference frame for each macroblock. As a result, the complexity of the encoder have been significantly increased. In this paper, a fast intra-mode decision algorithm is proposed to reduce the computational load of intra-mode search, which is based on the inverse tree-structure edge prediction algorithm. First, we obtained the dominant edge for each $4{\times}4$ block from local edge information, then the RDO process is only performed by the mode which corresponds to dominant edge direction. Then, for the $8{\times}8$ (or $16{\times}16$) block stage, the dominant edge is calculated from its four $4{\times}4$ (or $16{\times}16$) blocks' dominant edges without additional calculation and the RDO process is also performed by the mode which is related to dominant edge direction. Experimental results show that proposed scheme can significantly improve the speed of the intra prediction with a negligible loss in the peak signal to noise ratio (PSNR) and a little increase of bits.

• Journal of Broadcast Engineering
• /
• v.24 no.5
• /
• pp.713-725
• /
• 2019

Automatic License Plate Recognition (ALPR) is a technology required for many applications such as Intelligent Transportation Systems and Video Surveillance Systems. Most of the studies have studied were about the detection and recognition of license plates on cars, and there is very little about detecting and recognizing license plates on motorbikes. In the case of a car, the license plate is located at the front or rear center of the vehicle and is a straight or slightly sloped license plate. Also, the background of the license plate is mainly monochromatic, and license plate detection and recognition process is less complicated. However since the motorbike is parked by using a kickstand, it is inclined at various angles when parked, so the process of recognizing characters on the motorbike license plate is more complicated. In this paper, we have developed a 2-stage YOLOv2 algorithm to detect the area of a license plate after detection of a motorbike area in order to improve the recognition accuracy of license plate for motorbike data set parked at various angles. In order to increase the detection rate, the size and number of the anchor boxes were adjusted according to the characteristics of the motorbike and license plate. Image warping algorithms were applied after detecting tilted license plates. As a result of simulating the license plate character recognition process, the proposed method had the recognition rate of license plate of 80.23% compared to the recognition rate of the conventional method(YOLOv2 without image warping) of 47.74%. Therefore, the proposed method can increase the recognition of tilted motorbike license plate character by using the adjustment of anchor boxes and the image warping which fit the motorbike license plate.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.1
• /
• pp.141-148
• /
• 2021

In some intersections or busy traffic roads, there are more pedestrians in a specific period of time, and there are many traffic accidents caused by road congestion. Especially at the intersection where there are schools nearby, it is particularly important to protect the traffic safety of students in busy hours. In the past, when designing traffic lights, the safety of pedestrians was seldom taken into account, and the identification of motor vehicles and traffic optimization were mostly studied. How to keep the road smooth as far as possible under the premise of ensuring the safety of pedestrians, especially students, will be the key research direction of this paper. This paper will focus on person, motorcycle, bicycle, car and bus recognition research. Through investigation and comparison, this paper proposes to use YOLO v4 network to identify the location and quantity of objects. YOLO v4 has the characteristics of strong ability of small target recognition, high precision and fast processing speed, and sets the data acquisition object to train and test the image set. Using the statistics of the accuracy rate, error rate and omission rate of the target in the video, the network trained in this paper can accurately and effectively identify persons, motorcycles, bicycles, cars and buses in the moving images.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.12
• /
• pp.1-9
• /
• 2020

As pet dogs rapidly increase in number, abandoned and lost dogs are also increasing in number. In Korea, animal registration has been in force since 2014, but the registration rate is not high owing to safety and effectiveness issues. Biometrics is attracting attention as an alternative. In order to increase the recognition rate from biometrics, it is necessary to collect biometric images in the same form as much as possible-from the face. This paper proposes a method to determine whether a dog is facing front or not in a real-time video. The proposed method detects the dog's eyes and nose using deep learning, and extracts five types of directional face information through the relative size and position of the detected face. Then, a machine learning classifier determines whether the dog is facing front or not. We used 2,000 dog images for learning, verification, and testing. YOLOv3 and YOLOv4 were used to detect the eyes and nose, and Multi-layer Perceptron (MLP), Random Forest (RF), and the Support Vector Machine (SVM) were used as classifiers. When YOLOv4 and the RF classifier were used with all five types of the proposed face orientation information, the face recognition rate was best, at 95.25%, and we found that real-time processing is possible.

• Journal of the Society of Disaster Information
• /
• v.18 no.4
• /
• pp.922-929
• /
• 2022

Purpose: The purpose of this paper is to develop a deep learning model to detect fire extinguishers in images taken from CCTVs in underground utility tunnels. Method: Various fire extinguisher images were collected for detection of fire extinguishers in the running-based underground utility tunnel, and a model applying the One-stage Detector method was developed based on the CNN algorithm. Result: The detection rate of fire extinguishers photographed within 10m through CCTV video in the underground common area is over 96%, showing excellent detection rate. However, it was confirmed that the fire extinguisher object detection rate drops sharply at a distance of 10m or more, in a state where it is difficult to see with the naked eye. Conclusion: This paper develops a model for detecting fire extinguisher objects in underground common areas, and the model shows high performance, and it is judged that it can be used for underground common area digital twin model synchronizing.

• Tuberculosis and Respiratory Diseases
• /
• v.45 no.4
• /
• pp.785-794
• /
• 1998

Background: Chemical pleurodesis is a widely used method for the control of symptomatic and recurrent malignant pleural effusions. Talc has been accepted to be the most effective sclerosing agent for chemical pleurodesis. This study was undertaken to evaluate the usefulness of talc pleurodesis via video-assisted thoracoscopic surgery (VATS) in treatment of malignant pleural effusions. Methods : A retrospective analysis of the medical records and radiographic findings was performed. The success of the procedure was defined as daily pleural fluid drainage below 100ml within 1 week after pleurodesis and complete expansion of the lung on simple chest radiograph. Recurrence was defined as reaccumulation of pleural fluid on follow-up chest radiographs, and complete response as no fluid accumulation on follow-up chest radiographs. Results: Between October 1994 and August 1996, talc pleurodesis via VATS was performed in 35 patients. Duration of follow-up ranged from 5 days to 828 days(median 79days). The initial success rate of procedure was 88.6%(31 of 35 cases). Complete responses were observed in 92.8% at 30 days, 75.7% at 90 days and 64.9% at 180 days. Postoperative complications were fever (54.3%), subcutaneous emphysema(11.4%), reexpansion pulmonary edema(2.9%) and respiratory failure(5.7%). But procedure related mortality or respiratory failure was not found. Conclusion: Talc pleurodesis via VATS is a safe and effective method for the control of symptomatic malignant pleural effusions.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.4A
• /
• pp.451-463
• /
• 2000

In this paper, we design the radio data link protocols with QoS provisioning for mobile multimedia such as voice, data, and video in CDMA-based ATM networks, and analyze the performance of the data link protocols. To support mobile multimedia traffic, the required QoS parameters and the characteristics are analyzed, and wireless protocol stacks are proposed for integrating the wireless access network and ATM transport networks, and radio data link protocols are designed for provisioning QoS Control. The data link protocols are analyzed assuming that the system is supporting voice and data traffic simultaneously. In case of data traffic, the delay and throughput of SREJ ARQ and Type-1 Hybrid ARQ scheme are compared, and in case of voice traffic, the packet loss rate of BCH coding is analyzed according to the varying data traffic loads. The results indicate that the adaptive radio link protocols are efficient to support QoS requirements while the complexities are increased.

• Macromolecular Research
• /
• v.9 no.4
• /
• pp.197-205
• /
• 2001

Platelet adhesion onto elastic polymeric biomaterials was tested in vitro by perfusing human whole blood at a shear rate of 100 sec$\^$-1/ for possible verification of mechanisms of initial platelet adhesion perfusion of blood on the polymeric substrates was performed after treatments either with or without pre-adsorption of 1% blood plasma, and either with or without residence of the protein-preadsorbed substrate in phosphate buffered solution. The surfaces employed were elastic polymers such as poly(ether urethane urea), poly(ether urethane), silicone urethane copolymer, silicone rubber and poly(ether urethane) with the anti-calcifying agent hydroxyethane bisphosphate. Each polymer surface treated was exposed in vitro to the dynamic, heparinized whole blood perfused for upto 6 min and the surface area of platelets initially adhered was measured by employing in situ epifluorescence video microscopy. The blood perfusion was performed on the surfaces treated at the following three different conditions: directly on the bare surfaces, after protein pre-adsorption and after residence in buffer for 3 days of the surfaces protein pre-adsorbed for 2 h. The effects of blood plasma pre-adsorption on the initial platelet adhesion was surface-dependent. The amount of the adsorbed fibrinogen and the surface coverage area of the adhered platelets were dependent on the surface conditions whether substrates were bare surfaces or protein pre-adsorbed ones. To test an effect of possible morphological (re)orientations of the adsorbed proteins on the initial platelet adhesion, the polymeric substrate pre-adsorbed with 1% blood plasma was immersed in phosphate buffered solution for 3 days and then exposed to physiological blood perfusion. The surface area of the platelets adhered on these surfaces was significantly different from that of the surfaces treated with protein pre-adsorption only. These results indicated that platelet adhesion was dependent on the surface property itself and pre-treatment conditions such as blood perfusion without any pre-adsorption of proteins, and blood perfusion either after protein pre-adsorption or after subsequent substrate residence in buffer of the substrate pre-adsorbed with proteins. Understanding of these results may guide for better designs of blood-contacting materials based on protein behaviors.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.3
• /
• pp.112-118
• /
• 2009

Skin color segmentation techniques have been widely utilized for face/hand detection and tracking in many applications such as a diagnosis system using facial information, human-robot interaction, an image retrieval system. In case of a video image, it is common that the skin color model for a target is updated every frame for the robust target tracking against illumination change. As for a single image, however, most of studies employ a fixed skin color model which may result in low detection rate or high false positive errors. In this paper, we propose a novel method for effective skin color segmentation in a single image, which modifies the conditions for skin color segmentation iteratively by the image feedback of segmented skin color region in a given image.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.2C
• /
• pp.184-190
• /
• 2002

This paper compares and analyzes and analyzes the transmission performance of the OpenCable system and the DBD-C system which are adopted as the digital CATV transmission standard in U.S.A. and Europe respectively through computer simulation under the same channel environment. We considered the channel environment including the random noise and the CTB (Composite Tripple Beats) noise as channel impairments in order to compare the two standard fairly. Additionally, we analyzed the transmission performance of the OpenCable system for the various interleaving depths. We implemented each transmission system by software, and we analyzed BER values with respect to the C/N in order to compare their transmission performance. As a result of the computer simulation, to get the BER of ${10}^{-6}$ the OpenCable system requires 1.2 dB kiwer C/N than the DVB-C system in the 64-QAM mode, and the two system require similar C/N in the 256-QAM mode.