• International Journal of Internet, Broadcasting and Communication
• /
• v.13 no.1
• /
• pp.210-218
• /
• 2021

CNN (Convolutional Neural Network), a type of deep learning algorithm, is a type of artificial neural network used to analyze visual images. In deep learning, it is classified as a deep neural network and is most commonly used for visual image analysis. Accordingly, an AI autonomous driving model was constructed through real-time image processing, and a crosswalk image of a road was used as an obstacle. In this paper, we proposed a low-cost model that can actually implement autonomous driving based on the CNN model. The most well-known deep neural network technique for autonomous driving is investigated and an end-to-end model is applied. In particular, it was shown that training and self-driving on a simulated road is possible through a practical approach to realizing lane detection and keeping.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.9 no.2
• /
• pp.144-150
• /
• 2000

Surface roughness is one of the most important parameters to estimate quality of products. As this reason so many studies were car-ried out through various attempts that were contact or non-contact using computer vision. Even through these efforts there were few good results in this research., however texture analysis making a important role to solve these problems in various fields including universe aviation living thing and fibers. In this study feature value of co-occurrence matrix was calculated by statistic method and roughness value of worked surface was classified, of it. Experiment was carried out using input vector of neural network with characteristic value of texture calculated from worked surface image. It's found that recognition rate of 74% was obtained when adapting texture features. In order to enhance recogni-tion rate combination type in characteristics value of texture was changed into input vector. As a result high recognition rate of 92.6% was obtained through these processes.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.05a
• /
• pp.671-674
• /
• 2018

In this study, we implement a YOLO driving assistance system using a model car. The YOLO is an object detection and recognition algorithm using deep running which is becoming an issue recently. The system alerts the lane departure by applying the image processing technology to the image acquired through the camera, recognizes the objects using the YOLO, and performs various functions according to the type of the object and the distance between the vehicle. the YOLO, which is superior to the existing object detection and recognition algorithm, improves the performance of the driving assist system without additional equipment. The driving assist system using the YOLO will ensure the safety of the driver with low cost.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.6
• /
• pp.1089-1094
• /
• 2022

In this paper, a human coexistence-type companion robot that can communicate with people in daily life and alleviate the gap in care personnel was studied. Based on the voice recognition module, servo motor, and Arduino board, a companion robot equipped with a robot arm control function using voice recognition, a position movement function using RC cars, and a voice recognition function was tested and manufactured. As a result of the experiment, the speech recognition experiment according to distance showed the optimal recognition rate at a distance of 5 to 30 cm, and the speech recognition experiment according to gender showed a higher recognition rate in the first tone, monotonous tone. Through the evaluation results of these motion experiments, it was confirmed that a companion robot could be made.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.18 no.36
• /
• pp.71-82
• /
• 1995

The readability and the visuability are very significant when the letters or figures are displayed as static visual information. Not only is the beauty of the body type character(small letters) important but the display type character(large letters) should also be read easily, quickly and precisely. The issue regarding the readability in terms of perception of information has been raised continuously for all kinds of small signage and billboard, etc., which are written in display type within our everyday life. Among the various kinds of small signage and billboards the car licence plate is well known. Among all the possible factors that would have made an impact on the readability of licence plate, this paper focused on the effects of arrangement of character(letters and figures) and contrast of colors for the readability of licence plate using the within-subject analysis. The statistical analysis results in error reading rate, the character arrangement were significant but the color contrast(green/white, white/green, blue/white, white/blue, black/yellow) was not, No interaction was found.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.1
• /
• pp.93-101
• /
• 2023

In this paper, we propose a method of creating a 3D bounding box for an object using a vanishing point to increase the accuracy of object recognition in an image when recognizing an traffic object using a video camera. Recently, when vehicles captured by a traffic video camera is to be detected using artificial intelligence, this 3D bounding box generation algorithm is applied. The vertical vanishing point (VP1) and horizontal vanishing point (VP2) are derived by analyzing the camera installation angle and the direction of the image captured by the camera, and based on this, the moving object in the video subject to analysis is specified. If this algorithm is applied, it is easy to detect object information such as the location, type, and size of the detected object, and when applied to a moving type such as a car, it is tracked to determine the location, coordinates, movement speed, and direction of each object by tracking it. Able to know. As a result of application to actual roads, tracking improved by 10%, in particular, the recognition rate and tracking of shaded areas (extremely small vehicle parts hidden by large cars) improved by 100%, and traffic data analysis accuracy was improved.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.33 no.6
• /
• pp.595-603
• /
• 2015

With the advances of the big-data process technology, acquiring the real-time information from the massive image data taken by a mobile device inside a vehicle will be possible in the near future. Among the information that can be found around the vehicle, the route information is needed for safe driving. In this study, the automatic extraction of route information from the road sign imagery was dealt with. The scope of the route information in this study included the route number, route type, and their relationship with the driving direction. For the recognition of the route number, the modified Tesseract OCR (Optical Character Recognition) engine was used after extracting the rectangular-road-sign area with the Freeman chain code tracing algorithm. The route types (expressway, highway, rural highway, and municipal road) are recognized using the proposed algorithms, which are acquired from colour space analysis. Those road signs provide information about the route number as well as the roads that may be encountered along the way. In this study, such information was called “OTW (on the way)” or “TTW (to the way)” which between the two should be indicated is determined using direction information. Finally, the route number is matched with the direction information. Experiments are carried out with the road sign imagery taken inside a car. As a result, route numbers, route number type, OTW or TTW are successfully recognized, however some errors occurred in the process of matching TTW number with the direction.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.7 no.5
• /
• pp.53-63
• /
• 2008

In this paper, we propose the regional travel time measurement algorithm using the sequence pattern matching to the type of vehicles between the origin of the region and the end of the region, that could be able to overcome the limit of conventional method such as Probe Car Method or AVI Method by License Plate Recognition. This algorithm recognizes the vehicles as a sequence group with a definite length, and measures the regional travel time by searching the sequence of the origin which is the most highly similar to the sequence of the end. According to the assumption of similarity cost function, there are proposed three types of algorithm, and it will be able to estimate the average travel time that is the most adequate to the information providing period by eliminating the abnormal value caused by inflow and outflow of vehicles. In the result of computer simulation by the length of region, the number of passing cars, the length of sequence, and the average maximum error rate are measured within 3.46%, which means that this algorithm is verified for its superior performance.

• Journal of Korean Academy of Nursing
• /
• v.3 no.3
• /
• pp.36-49
• /
• 1973

This study was carried out for the objectives to collect the basic informations on the health behaviors of the elementary school children in an urban area in Korea. Seven hundred students were drawn to fill in the designed questionnaire which carries variety of Questions on health re-lated behaviors in general, eating habits, disease history, mental health, and sex education. Questionnaire were filled in by their parents. Major findings are as follows: ① 55.7% had habits of washing the hands before eating whereas 59.8% trashing their hands after toilet. The others had no idea of washing hands before eating and after toilet. ② 26,5% had habits of brushing the teeth twice a day 54.7% only once in the morning, and 2.6% once only in the evening. Thus, the idea of prevention from decayed teeth seems to be lacking among the school children. ③ Bathing habits were also inquired to get 40.3% of bathing more than once a week, 43.1% once every two weeks, and the rest of 16.6% once every one to three months. ④ 41.7% keep the regular bedding time whereas 58.3% irregular. Physical exercises were con-ducted by 76.6% on the ground while 23.5% did not practice any physical exercises at all. Of those physical exercises, rope skipping occupied 37.5%, and the other 66.9% consisted of 14 different kinds of individual type physical exercises such as gymnastic exercise. The main reasons for not enjoying exercises were different by sex; boys largely complained the inadequacy and lack of gymnastic facilities and girls felt in short of friends who could join the exercises. ⑤ 31.9% of the school children had been taking not much of food while 28.3% had unbalanced diets. Of these unbalanced diets, meat occupied 33.2% to be the priority to have an order of the following items such as vegetables, bread or noodle, and fishes as next to each. For eating habits, 88.5% take simple snack such as bread (38.4%, cookies, fruits, and candies in order. 25.8% of the children were provided such snacks or their parents regularly. Breakfast was sufficiently taken by 45.0% whereas 8.4% had never sufficiently. As to the lunch, 63.6% had sufficiently while 16.8% insufficiently. 70.6% take breakfast with all family members together and 30.4% separately. Correlation of sufficient taking of breakfast and eating together of tile family member's seems to be significant when we compare 72.5% of sufficient takers who enjoy breakfast together with the family members with 55.6% of insufficient takers who enjoy it with the family. This finding allows the investigator to point out the importance of table circumstances for children's eating. ⑥ The most common disease was catching a cold (38.8%), and the second was stomach trouble to be followed by the frequency of car sickness, headache, and skin infection. Doctors are consulted only by 23.9% when they are sick whereas 59.7% resorted to the drug stores. The lower the educational attainment of the parents, the lower the rate of visiting clinics. ⑦ 36.7% of their parents pointed out the problems of personality guidance as the most difficult thing at home 71.3% of their parents worried about and unsatisfied with their children's personality traits. Of these complains of the parents, impatience stood at the top to be tabulated at 24.1%, and 21.1% indicated narrow-mindedness. In line with this primary socialization at home, the most crucial problem seems to be related with the lack or recognition of the parents'own role when we find only 43.1% of the parents understood the importance of their own role for the home education of children; the latter group attributed tile responsibility of personality formation to the children themselves. ⑧ As to the sex educational aspects, 30.9% of children have ever asked about the physiology of reproduction or sexual matters to their parents, of those parents only 17.0% could give the constructive responses to the inquiries of the children. In companies on with these data, 25.6% recognized their own role in sex education for their own children while the large segments of the parents (51.1%) attributed the responsibility of sex education to tile low level of 38.3% who recognized the importance of sex education in the school curriculum and 25.1% of the parents insisted to wait until they get to know naturally about sex. 38.1% of the parents said they had some knowledge on sex from books while 16.9% through mass media. The next groups had common senses of sex from their own parents, school friends and other sources.