• Journal of KIISE:Computing Practices and Letters
• /
• v.14 no.1
• /
• pp.1-12
• /
• 2008

In this paper, we present a real-time algorithm for recognizing the vehicle color from the indoor and outdoor vehicle images based on GPU (Graphics Processing Unit) acceleration. In the preprocessing step, we construct feature victors from the sample vehicle images with different colors. Then, we combine the feature vectors for each color and store them as a reference texture that would be used in the GPU. Given an input vehicle image, the CPU constructs its feature Hector, and then the GPU compares it with the sample feature vectors in the reference texture. The similarities between the input feature vector and the sample feature vectors for each color are measured, and then the result is transferred to the CPU to recognize the vehicle color. The output colors are categorized into seven colors that include three achromatic colors: black, silver, and white and four chromatic colors: red, yellow, blue, and green. We construct feature vectors by using the histograms which consist of hue-saturation pairs and hue-intensity pairs. The weight factor is given to the saturation values. Our algorithm shows 94.67% of successful color recognition rate, by using a large number of sample images captured in various environments, by generating feature vectors that distinguish different colors, and by utilizing an appropriate likelihood function. We also accelerate the speed of color recognition by utilizing the parallel computation functionality in the GPU. In the experiments, we constructed a reference texture from 7,168 sample images, where 1,024 images were used for each color. The average time for generating a feature vector is 0.509ms for the $150{\times}113$ resolution image. After the feature vector is constructed, the execution time for GPU-based color recognition is 2.316ms in average, and this is 5.47 times faster than the case when the algorithm is executed in the CPU. Our experiments were limited to the vehicle images only, but our algorithm can be extended to the input images of the general objects.

• Tunnel and Underground Space
• /
• v.33 no.4
• /
• pp.281-298
• /
• 2023

Continuous research efforts are being devoted to unmanned mobile platforms for lunar exploration. There is an ongoing demand for real-time information processing to accurately determine the positioning and mapping of areas of interest on the lunar surface. To apply deep learning processing and analysis techniques to practical rovers, research on software integration and optimization is imperative. In this study, a foundational investigation has been conducted on real-time analysis of virtual lunar base construction site images, aimed at automatically quantifying spatial information of key objects. This study involved transitioning from an existing region-based object recognition algorithm to a boundary box-based algorithm, thus enhancing object recognition accuracy and inference speed. To facilitate extensive data-based object matching training, the Batch Hard Triplet Mining technique was introduced, and research was conducted to optimize both training and inference processes. Furthermore, an improved software system for object recognition and identical object matching was integrated, accompanied by the development of visualization software for the automatic matching of identical objects within input images. Leveraging satellite simulative captured video data for training objects and moving object-captured video data for inference, training and inference for identical object matching were successfully executed. The outcomes of this research suggest the feasibility of implementing 3D spatial information based on continuous-capture video data of mobile platforms and utilizing it for positioning objects within regions of interest. As a result, these findings are expected to contribute to the integration of an automated on-site system for video-based construction monitoring and control of significant target objects within future lunar base construction sites.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.35 no.6
• /
• pp.563-572
• /
• 2017

The purpose of the study is to investigate the effect of flight height, flight speed, exposure time of camera shutter and autofocusing on the visual resolution of the image in order to obtain ultra-high resolution images with a GSD less than 1cm. It is also aimed to evaluate the ease of recognition of various types of aerial targets. For this purpose, we measured the visual resolution using a 7952*5304 pixel 35mm CMOS sensor and a 55mm prime lens at 20m intervals from 20m to 120m above ground. As a result, with automatic focusing, the visual resolution is measured 1.1~1.6 times as the theoretical GSD, and without automatic focusing, 1.5~3.5 times. Next, the camera was shot at 80m above ground at a constant flight speed of 5m/s, while reducing the exposure time by 1/2 from 1/60sec to 1/2000sec. Assuming that blur is allowed within 1 pixel, the visual resolution is 1.3~1.5 times larger than the theoretical GSD when the exposure time is kept within the longest exposure time, and 1.4~3.0 times larger when it is not kept. If the aerial targets are printed on A4 paper and they are shot within 80m above ground, the encoded targets can be recognized automatically by commercial software, and various types of general targets and coded ones can be manually recognized with ease.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.2
• /
• pp.89-103
• /
• 2020

As we face an aging society, the demand for personal mobility for disabled and aged people is increasing. In fact, as of 2017, the number of electric wheelchair in the country continues to increase to 90,000. However, people with disabilities and seniors are more likely to have accidents while driving, because their judgment and coordination are inferior to normal people. One of the causes of the accident is the interference of personal vehicle steering control due to unbalanced road surface conditions. In this paper, we introduce a encoder type semantic segmentation algorithm that can recognize road conditions at high speed to prevent such accidents. To this end, more than 1,500 training data and 150 test data including road surface damage were newly secured. With the data, we proposed a deep neural network composed of encoder stages, unlike the Auto-encoding type consisting of encoder and decoder stages. Compared to the conventional method, this deep neural network has a 4.45% increase in mean accuracy, a 59.2% decrease in parameters, and an 11.9% increase in computation speed. It is expected that safe personal transportation will be come soon by utilizing such high speed algorithm.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.16 no.5
• /
• pp.976-988
• /
• 2002

The aim of this study was to examine the memory and attention enhancement effect of YMG-1 and YMG-2, which are modified herbal extracts from Yukmijihwang-tang (YMJ). YMJ, composing six herbal medicine, has been used for restoring the normal functions of the body to consolidate the constitution, nourishing and invigorating the kidney functions for hundreds years in Asian countries. A series of studies reported that YMJ and its components enhance memory retention, protects neuronal cell from reactive oxygen attack and boost immune activities. Recently the microarray analysis suggested that YMG-1 protects neurodegeneration through modulating various neuron specific genes. A total of 55 subjects were divided into three groups according to the treatment of YMG-1 (n=20), YMG-2 (n=20) and control (C; n=15) groups. Before treatments, all of subjects were subjected to the assessments on neuropsychological tests of K-WAIS test, Rey-Kim memory test, and psychophysiological test of Event-Related Potential (ERP) during auditory oddball task and repeated word recognition task. They were repeatedly assessed with the same methods after drug treatment for 6 weeks. Although no significant effect of drug was found in Rey-Kim memory test, a significant interaction (P = .010, P < 0.05) between YMG-2 and C groups was identified in the scores digit span and block design, which are the subscales of K-WAIS. The very similar but marginal interaction (P = .064) between YMG-1 and C groups was found too. In ERP analysis, only YMG-1 group showed decreasing tendency of P300 latency during oddball task while the others tended to increase, and it caused significant interaction between session and group (p= .004). This result implies the enhancement of cognitive function in due to consideration of relationship between P300 latency and the speed of information processing. However, no evidence which could demonstrate the significant drug effect was found in neither amplitude or latency. These results come together suggest that YMG-1, 2 may enhance the attention, resulting in enhancement of memory processing. For elucidating detailed mechanism of YMG on learning and memory, the further studies are necessary.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.74-77
• /
• 1999

본 논문에서는 본 연구실에서 개발한 주소 음성인식 시스템의 인식 속도를 개선시키기 위하예 새로운 가변 프루닝 문턱치를 적용하는 방법을 제안하고 실험을 통하여 그 유효성을 확인하였다. 기존의 가변 프루닝 문턱치는 일정 프레임이 경과하면 일정 값을 가진 문턱치를 계속하여 감소시켜나가는 방법을 반복하기 때문에, 불필요한 탐색공간을 탐색하게 된다. 본 논문에서 새로이 제안하는 가변 프루닝 문턱치를 채용하는 방법은 처음 일정 구간이 경과되면 일정 문턱치를 감소시키나, 다음 일정 프레임에서는 탐색되어야할 후보에 따라서 문턱치를 변화시켜 프루닝시키기 때문에 탐색공간을 효과적으로 감소시킬 수 있다. 제안된 방법의 유효성을 확인하기 위하여, 본 연구실에서 개발한 한국어 주소 입력 시스템에 적용하였다. 이 시스템은 48개의 연속 HMM 유사음소단위(Phoneme Like Units; PLUs)를 인식의 기본단위로 하고, .사용환경 변화에 의한 인식성능의 저하를 최소화하기 위해 최대사후 확률추정법(Maximum A Posteriori Probability Estimation; MAP)을 사용하며, 인식알고리즘으로는OPDP(One Pass Dynamic Programming)법을 이용하고 있다. 남성화자 3인에 의한 75개의 연결주소명을 이용하여 인식 실험을 수행한 결과 고정 프루닝 문턱치를 적용한 경우 인식률은 평균 $96.0\%$, 인식 시간은 5.26초였고, 기존의 가변 프루닝 문턱치의 경우 인식률은 평균 $96.0\%$, 인식 시간은 5.1초인 데 비하여, 새로운 가변 프루닝 문턱치를 적용찬 경우에는 인식률 저하없이 인식 시간이 4.34초로, 기존에 비해 각각 0.92초, 0.76초 인식 시간이 감소되어 제안한 방법의 유효성을 확인할 수 있었다.는 달리 각 산란 영역에서 그 지수는 1씩 작은 값을 갖는다.향에 따라 음장변화가 크게 다를 것이 예상되므로 이를 규명하기 위해서는 궁극적으로 3차원적인 음장분포 연구가 필요하다. 음향센서를 해저면에 매설할 경우 수충의 수온변화와 센서 주변의 수온변화 사이에는 어느 정도의 시간지연이 존재하게 되므로 이에 대한 영향을 규명하는 것도 센서의 성능예측을 위해서 필요하리라 사료된다.가지는 심부 가스의 개발 성공률을 증가시키기 위하여 심부 가스가 존재하는 지역의 지질학적 부존 환경 및 조성상의 특성과 생산시 소요되는 생산비용을 심도에 따라 분석하고 생산에 수반되는 기술적 문제점들을 정리하였으며 마지막으로 향후 요구되는 연구 분야들을 제시하였다. 또한 참고로 현재 심부 가스의 경우 미국이 연구 개발 측면에서 가장 활발한 활동을 전개하고 있으며 그 결과 다수의 신뢰성 있는 자료들을 확보하고 있으므로 본 논문은 USGS와 Gas Research Institute(GRI)에서 제시한 자료에 근거하였다.ऀĀ耀Ā삱?⨀؀Ā Ā?⨀ጀĀ耀Ā?돀ꢘ?⨀硩?⨀ႎ?⨀?⨀넆돐쁖잖⨀쁖잖⨀／ࠐ?⨀焆덐瀆倆Āⶇ퍟ⶇ퍟ĀĀĀĀ磀鲕좗?⨀肤?⨀⁅Ⴅ?⨀쀃잖⨀䣙熸ጁ↏?⨀

• The Journal of the Convergence on Culture Technology
• /
• v.6 no.3
• /
• pp.431-436
• /
• 2020

Information service organizations that provide science and technology information with a relatively short information life cycle for free or paid are in need of reflecting rapidly changing user needs and behaviors and grafting the latest technologies. The purpose of this study is to derive improvements for each system by comparing and analyzing general recognition of science and technology information users' domestic and foreign science and technology information sites and importance by science and technology information attributes. A total of 816 users of science and technology information participated in the online survey, and the collected data were analyzed by quantitative methods including IPA (Importance Performance Analysis) technique. The importance was evaluated by the impact value calculated through regression analysis. As a result of data analysis, the general recognition of users on science and technology information sites was relatively high in national science and technology information services, and Google Scholar and Science Direct were also high. Google Scholar was found to have more strength than improvement. A better understanding of the user's preferred system is a good driving force for improving the lack of existing systems. It is necessary to improve the information retrieval of the science and technology information service system, that is, to improve the search speed and functions, and also to improve the user interface with improved convenience and usability.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.3
• /
• pp.600-611
• /
• 1996

Recently, neural network-based speech recognition has been studied to utilize the adaptivity and learnability of neural network models. However, conventional neural network models have difficulty in the co-articulation processing and the boundary detection of similar phonmes of the Korean speech. Also, in case of using one phonotopic map, learning speed may dramatically increase and inaccuracies may be caused because homogeneous learning and recognition method should be applied for heterogenous data. Hence, in this paper, a neural net typewriter has been designed using a hierarchical self-organizing classifier(HSOC), and related algorithms are presented. This HSOC, during its learing stage, distributed phoneme data on hierarchically structured multiple phonotopic maps, using Kohonen's self-organizing feature maps(SOFM). Presented and experimented in this paper were the algorithms for deciding the number of maps, map sizes, the selection of phonemes and their placement per map, an approapriate learning and preprocessing method per map. If maps are divided according to a priorlinguistic knowledge, we would have difficulty in acquiring linguistic knowledge and how to alpply it(e.g., processing extended phonemes). Contrarily, our HSOC has an advantage that multiple phonotopic maps suitable for given input data are self-organizable. The resulting three korean phonotopic maps are optimally labelled and have their own optimal preprocessing schemes, and also confirm to the conventional linguistic knowledge.

• 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.

• The Journal of Bigdata
• /
• v.7 no.1
• /
• pp.15-27
• /
• 2022

In the past five years, the fatality rate of single-vehicle accidents has been 4.7 times higher than that of all accidents, so it is necessary to establish a system that can detect and respond to single-vehicle accidents immediately. The IoT(Internet of Thing)-based real-time traffic accident recognition system proposed in this study is as following. By attaching an IoT sensor which detects the impact and vehicle ingress to the guardrail, when an impact occurs to the guardrail, the image of the accident site is analyzed through artificial intelligence technology and transmitted to a rescue organization to perform quick rescue operations to damage minimization. An IoT sensor module that recognizes vehicles entering the monitoring area and detects the impact of a guardrail and an AI-based object detection module based on vehicle image data learning were implemented. In addition, a monitoring and operation module that imanages sensor information and image data in integrate was also implemented. For the validation of the system, it was confirmed that the target values were all met by measuring the shock detection transmission speed, the object detection accuracy of vehicles and people, and the sensor failure detection accuracy. In the future, we plan to apply it to actual roads to verify the validity using real data and to commercialize it. This system will contribute to improving road safety.