• Journal of Broadcast Engineering
• /
• v.20 no.6
• /
• pp.938-949
• /
• 2015

In this paper, we propose a robust speed-limit sign recognition system which is durable to any sign changes caused by exterior damage or color contrast due to light direction. For recognition of speed-limit sign, we apply CNN which is showing an outstanding performance in pattern recognition field. However, original CNN uses multiple hidden layers to extract features and uses fully-connected method with MLP(Multi-layer perceptron) on the result. Therefore, the major demerit of conventional CNN is to require a long time for training and testing. In this paper, we apply randomly-connected classifier instead of fully-connected classifier by combining random forest with output of 2 layers of CNN. We prove that the recognition results of CNN with random forest show best performance than recognition results of CNN with SVM (Support Vector Machine) or MLP classifier when we use eight speed-limit signs of GTSRB (German Traffic Sign Recognition Benchmark).

• Journal of Korean Society of Forest Science
• /
• v.94 no.2 s.159
• /
• pp.112-116
• /
• 2005

This study was conducted to obtain the information of distribution, protection and management for mammal species in fragmented forest areas around the road from June 2002 to May 2003 in 9 study sites of Baekdugdaegan mountains, Korea. Field signs of twelve mammals, moles Molera robusta, Korean hares Lepus coreanus, Manchurian chipmunk Tamias sibiricus, red squirrels Sciurus vulgaris, Korean racoon dogs Nyctereutes procyonoides, Siberian weasels Mustela sibirica, badgers Meles meles, otters Lutra lutra, Bengal cats Felis bengalensis, wild boars Sus scrofa, water deer Hydropotes inermis and roe deer Capreolus pygargus were recorded in this study. There were no differences in total number of species between 50 m areas and 50-100 m areas from road in snow and non-snow season. Number of mammals' field signs were different in non-snow season between both areas. Red squirrels and Siberian weasels were more abundant in 50 m areas, and Korean hares and Manchurian chipmunks were in 50-100 m areas. Habitat using pattern of mammal species may be affected by the road. Reasonable road construction and maintenance would be needed for protection and management of wildlife and their habitats.

• Journal of Korea Multimedia Society
• /
• v.25 no.9
• /
• pp.1257-1265
• /
• 2022

Recognition of sign language is challenging due to the occlusion of hands, accuracy of hand gestures, and high computational costs. In recent years, deep learning techniques have made significant advances in this field. Although these methods are larger and more complex, they cannot manage long-term sequential data and lack the ability to capture useful information through efficient information processing with faster convergence. In order to overcome these challenges, we propose a word-level sign language recognition (SLR) system that combines a real-time human pose detection library with the minimized version of the gated recurrent unit (GRU) model. Each gate unit is optimized by discarding the depth-weighted reset gate in GRU cells and considering only current input. Furthermore, we use sigmoid rather than hyperbolic tangent activation in standard GRUs due to performance loss associated with the former in deeper networks. Experimental results demonstrate that our pose-based optimized GRU (Pose-OGRU) outperforms the standard GRU model in terms of prediction accuracy, convergency, and information processing capability.

• Korea Science and Art Forum
• /
• v.19
• /
• pp.281-292
• /
• 2015

For this study, I conducted a survey investigating current situation, user preference, and field experiment. Hospitals utilizing digital sign systems at least five years were selected, which are connected with visual elements (layout, typo, color) used in waiting areas and elements of the systems (time, video time line). The results obtained from the field survey showed that digital sign systems used the color of typo and background contrasted to one another to increase explicitness and to ensure easy understanding of contents. In addition, the Gothic typo with relatively high legibility was adopted. Time and video timeline, which characterize digital sign systems, showed the advertising screens of the hospitals and the guidance of medical treatment at regular intervals. Moreover, survey results on user satisfaction showed that a majority of respondents indicated they had difficulty in understanding digital information conveyed from digital sign systems due to time setting for rotational speed or the small size of typo although most of the users had previous experience with digital sign systems. The highest proportion of respondents (n=86, 86%) answered that information related to medical departments was what they sought most frequently and that this kind of information should be importantly considered in digital sign systems. For the experiment, new samples with restructured contents of current digital sign systems were created and tested while keeping its design unchanged as well as applying these new samples. Study participants were in their 20s through 50s. When the size of typo was larger under the same conditions for all age groups, study participants found the desired information approximately 3.5 seconds faster. In addition, those in their 20-30s and 40-50s showed the time difference of 4.7 seconds for small typo and 6 seconds for large typo, which suggested that there was a difference by age in the amount of time taken in the experiment to find the desired information from the rotating digital sign system regardless of age and the size of typo.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.32 no.5D
• /
• pp.437-444
• /
• 2012

This study intended to improve traffic safety in work zones using fluorescent orange color traffic signs. For this end, the current problems of existing traffic signs and facilities in work zones were analyzed and some good examples of foreign countries were compared. More specifically, in order to identify current problems, the basic shape and color of traffic signs in use were examined through literature review, surveys and field studies. It was found that the fluorescent color worked more effectively than other colors in terms of visibility and conspicuity in work zone sign system. For evaluation, both Conspicuity surveys and in-door simulator experiments were conducted to effectively assess the merits and demerits of different types of traffic signs for work zones. The results of evaluations showed that black lettering on a fluorescent orange background outperformed more than 70% in terms of visibility and ability to call drivers' attention compared with those from black/red lettering on yellow/white backgrounds currently used at work zones on expressways and national highways. In addition, simulated driving experiment disclosed that drivers recognized the fluorescent orange background sign 15m ahead compared with the yellow background sign and 25m ahead compared with the white background sign, respectively. As for the diamond-shaped "Under Construction" sign, drivers recognized fluorescent orange background 11m ahead compared with the yellow background sign and 19m ahead compared with the white background sign, respectively.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.4
• /
• pp.190-211
• /
• 2022

This study investigated the effect of the shape and height of road signs on detection performance when detecting road signs with LiDAR, which is recognized as an essential sensor for autonomous vehicles. For the study, four types of road signs with the same area and material and different shapes were produced, and a road driving test was performed by installing a 32Ch rotating LiDAR on the upper part of the vehicle. As a result of comparing the shape of the point cloud and the NPC according to the shape of the road sign, It is expected that a distance of less than 40m is required to recognize the overall shape of a road sign using 32Ch LiDAR, and shapes such as triangles and rectangles are more advantageous than squares in securing the maximum point cloud from a long distance. As a result of the study according to the height of the road sign, At short distances (within 20m), if the height of the sign is raised to more than 2m, it deviates from the vertical viewing angle of the LiDAR and cannot express the complete point cloud shape. However, it showed a negligible effect compared to the near-field height change. These research results are expected to be utilized in the development of road facilities dedicated to LiDAR for the commercialization of autonomous cooperative driving technology.

• Journal of the Korean Magnetic Resonance Society
• /
• v.8 no.2
• /
• pp.70-76
• /
• 2004

ZORA-DFT calculations of $^{11}$B EFG (electric field gradient) tensors for lithium borates, LiB$_3O_5$ (LBO) and Li$_2B_4O_7$ (LTB), were performed. The calculated values of 11B quadrupole coupling constant and asymmetry parameter are in good agreement with the experimental values. The sign of the quadrupole coupling constant for the tetrahedral boron site was deduced from the distortion from the ideal tetrahedral symmetry.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.27 no.3
• /
• pp.299-306
• /
• 2016

In this paper, a vital sign sensor based on impedance variation of resonator is proposed to detect the respiration and heartbeat signals within near-field range as a function of the separation distance between resonator and subject. The sensor consists of an oscillator with a built-in planar type patch resonator, a diplexer for only pass the second harmonic frequency, amplifier, SAW filter, and RF detector. The cardiac activity of a subject such as respiration and heartbeat causes the variation of the oscillation frequency corresponding impedance variation of the resonator within near-field range. The combination of the second harmonic oscillation frequency deviation and the superior skirt frequency of the SAW filter enables the proposed sensor to extend twice detection range. The experimental results reveal that the proposed sensor placed 40 mm away from a subject can reliably detect respiration and heartbeat signals.

• Korean Journal of Construction Engineering and Management
• /
• v.5 no.4 s.20
• /
• pp.139-146
• /
• 2004

Resent removal work for road signs has been labor intensive and required times since it has been done manually using shaving type equipment. While traditional process is conducting, there are traffic jams caused by the passing control, and happened unexpected accidents to workers working at dangerous road circumstance. Besides, in current shaving method, there are high potentialities on the air pollution as well as the explosive accident occurred by using a propane gas. So, as an alternative, we have studied to develop the automatic erasing equipment made up with a high pressure water-jet system and automatic control system, mobile system; Wate-rjet system consists of an intensifier and nozzles to give a high pressure and spray on the sign, and automatic control system is composed of one axis robot using a hydraulic servo actuator controlled by a lever, And as a mobile system, a truck plays an important role for the transport of equipment and the forward movement in a removal process. In this paper, we have analyzed the characteristics of road signs and have investigated current erasing methods in the field. And we have organized and designed automatic erasing equipment, and we have made a basic experiment to find out the optimal spray condition as like the spray distance, spray angle and injection pressure.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.25 no.1
• /
• pp.138-143
• /
• 2011

In spite of abundant clinical resources of stroke patients, the objective and logical data analyses or diagnostic systems were not established in oriental medicine. As a part of researches for standardization and objectification of differentiation of syndromes for stroke, in this present study, we tried to develop the statistical diagnostic tool discriminating the 4 subtypes of syndrome differentiation using the essential indices considering the sex. Discriminant analysis was carried out using clinical data collected from 1,448 stroke patients who was identically diagnosed for the syndrome differentiation subtypes diagnosed by two clinical experts with more than 3 year experiences. Empirical discriminant model(V) for different sex was constructed using 61 significant symptoms and sign indices selected by stepwise selection. We comparison. We make comparison a between discriminant model(V) and discriminant model(IV) using 33 significant symptoms and sign indices selected by stepwise selection. Development of statistical diagnostic tool discriminating 4 subtypes by sex : The discriminant model with the 24 significant indices in women and the 19 significant indices in men was developed for discriminating the 4 subtypes of syndrome differentiation including phlegm-dampness, qi-deficiency, yin-deficiency and fire-heat. Diagnostic accuracy and prediction rate of syndrome differentiation by sex : The overall diagnostic accuracy and prediction rate of 4 syndrome differentiation subtypes using 24 symptom and sign indices was 74.63%(403/540) and 68.46%(89/130) in women, 19 symptom and sign indices was 72.05%(446/619) and 70.44%(112/159) in men. These results are almost same as those of that the overall diagnostic accuracy(73.68%) and prediction rate(70.59%) are analyzed by the discriminant model(IV) using 33 symptom and sign indices selected by stepwise selection. Considering sex, the statistical discriminant model(V) with significant 24 symptom and sign indices in women and 19 symptom and sign indices in men, instead of 33 indices would be used in the field of oriental medicine contributing to the objectification of syndrome differentiation with parsimony rule.