• The Journal of Korea Robotics Society
• /
• v.13 no.2
• /
• pp.79-85
• /
• 2018

This study focuses on autonomous exploration based on map expansion for an underwater robot equipped with acoustic sonars. Map expansion is applicable to large-area mapping, but it may affect localization accuracy. Thus, as the key contribution of this paper, we propose a method for underwater autonomous exploration wherein the robot determines the trade-off between map expansion ratio and position accuracy, selects which of the two has higher priority, and then moves to a mission step. An occupancy grid map is synthesized by utilizing the measurements of an acoustic range sonar that determines the probability of occupancy. This information is then used to determine a path to the frontier, which becomes the new search point. During area searching and map building, the robot revisits artificial landmarks to improve its position accuracy as based on imaging sonar-based recognition and EKF-SLAM if the position accuracy is above the predetermined threshold. Additionally, real-time experiments were conducted by using an underwater robot, yShark, to validate the proposed method, and the analysis of the results is discussed herein.

• Journal of Korea Multimedia Society
• /
• v.24 no.5
• /
• pp.642-650
• /
• 2021

Strabismus is one of the most common disease that might be associated with vision impairment. Especially in infants and children, it is critical to detect strabismus at an early age because uncorrected strabismus may go on to develop amblyopia. To this end, ophthalmologists usually perform the Hirschberg test, which observes corneal light reflex (CLR) to determine the presence and type of strabismus. However, this test is usually done manually in a hospital, which might be difficult for patients who live in a remote area with poor medical access. To address this issue, we propose an automatic strabismus screening method that calculates the CLR ratio to determine the presence of strabismus based on image processing. In particular, the method first employs a pre-trained face detection model and a 68 facial landmarks detector to extract the eye region image. The data points located in the limbus are then collected, and the least square method is applied to obtain the center coordinates of the iris. Finally, the coordinate of the reflective light point center within the iris is extracted and used to calculate the CLR ratio with the coordinate of iris edges. Experimental results with several images demonstrate that the proposed method can be a promising solution to provide strabismus screening for patients who cannot visit hospitals.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.49 no.1
• /
• pp.85-94
• /
• 2022

This retrospective study aimed to evaluate the difference in measurement between conventional orthodontic analysis and artificial intelligence orthodontic analysis in pediatric and adolescent patients aged 7 - 15 with the mixed and permanent dentition. A total of 60 pediatric and adolescent patients (30 mixed dentition, 30 permanent dentition) who underwent lateral cephalometric radiograph for orthodontic diagnosis were randomly selected. Seventeen cephalometric landmarks were identified, and 22 measurements were calculated by 1 examiner, using both conventional analysis method and deep learning-based analysis method. Errors due to repeated measurements were assessed by Pearson's correlation coefficient. For the mixed dentition group and the permanent dentition group, respectively, a paired t-test was used to evaluate the difference between the 2 methods. The difference between the 2 methods for 8 measurements were statistically significant in mixed dentition group: APDI, SNA, SNB, Mandibular plane angle, LAFH (p < 0.001), Facial ratio (p = 0.001), U1 to SN (p = 0.012), and U1 to A-Pg (p = 0.021). In the permanent dentition group, 4 measurements showed a statistically significant difference between the 2 methods: ODI (p = 0.020), Wits appraisal (p = 0.025), Facial ratio (p = 0.026), and U1 to A-Pg (p = 0.001). Compared with the time-consuming conventional orthodontic analysis, the deep learning-based cephalometric system can be clinically acceptable in terms of reliability and validity. However, it is essential to understand the limitations of the deep learning-based programs for orthodontic analysis of pediatric and adolescent patients and use these programs with the proper assessment.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.38 no.5_2
• /
• pp.206-213
• /
• 2010

This paper looks into how to preserve Gyeongju's natural environment and to restore its historic landscaping works, one of the greate factor that compose ancient city as a way of wisely preserving Gyeongju, one of the oldest cities of Korea. Gyeongju, a city based in its natural environment, is formated inside of a basin of mountains and streams. Mountains and streams are the major two factors when on thinks of preserving the ancient city of Gyeongju. Four mountains surrounding the city play a direct role in marking coordinates of major city landmarks, while streams influence the structure and formation of the city in a great deal. More precisely, mountains should be able to be seen from the center of the city and streams should be restored in a way that they can serve as scenic identities of their time. Efforts should also be put into restoring such elements as ancient gardens, royal forests and water ways. The research team believes that such efforts themselves will be a great methods in reclaiming historic values and significance of places of Gyeongju. Restoring an ancient city is not limited merely restoring a city in an artificial concept, it reaches to preserving natural environment as a backdrop of the city and traces of landscaping works. When it comes to restoring an ancient city, one must understand that preserving natural environment and historic landscaping works are as valuable as restoring city structure or constructional elements. We believe that defining subjects of ancient city restoration must be more precise, clear and detail down the road.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.12
• /
• pp.1167-1175
• /
• 2010

This paper presents the use of the inertial measurement unit information and the infrared sector information for getting the position of an object. Travel distance is usually calculated from the double integration of the accelerometer output with respect to time; however, the accumulated errors due to the drift are inevitable. The orientation change of the accelerometer also causes error because the gravity is added to the measured acceleration. Unless three axis orientations are completely identified, the accelerometer alone does not provide correct acceleration for estimating the travel distance. We propose a way of minimizing the error due to the change of the orientation. In order to reduce the accumulated error, the infrared sector information is fused with the inertial measurement unit information. Infrared sector information has highly deterministic characteristics, different from RFID. By putting several infrared emitters on the ceiling, the floor is divided into many different sectors and each sector is set to have a unique identification. Infrared light based sector information tells the sector the object is in, but the size of the uncertainty is too large if only the sector information is used. This paper presents an algorithm which combines both the inertial measurement unit information and the sector information so that the size of the uncertainty becomes smaller. It also introduces a framework which can be used with other types of the artificial landmarks. The characteristics of the developed infrared light based sector and the proposed algorithm are verified from the experiments.

• Journal of Dental Rehabilitation and Applied Science
• /
• v.19 no.3
• /
• pp.153-168
• /
• 2003

It is very important to arrange the artificial teeth correctly in bucco-lingual (labio- lingual) relation in reconstrcting dentition. Although many anatomic landmarks and techniques have been reported over the years, they are based on westerns. So this study was performd to examine the horizontal relations of mandibular teeth in Korean dentulous adults. 200 volunteers(mean age 22.9) who had natural dentition were selected. The impressions were taken with irreversible hydrocolloid impression material and mandibular study models were fabricated using class I dental stone. Then they were measured with 3-dimensional measuring device specially designed for this study. The results were as follows ; It is better to consider the lingual cusps of the lower posterior teeth as a guide than the linguoaxial surfaces of the lower posterior teeth, arranging the lower posterior teeth buccally to the line which starts from the mesial aspect of the lower canine and continue backward to the lingual aspect of the retromolar pad. It is better to arrange the fossae of the lower posterior teeth buccally to the line which starts from the cusp tip of the lower canine and continue backward to the top of the retromolar pad. The positions of the lower posterior teeth in the denture-bearing area ; considering the fossa as a guide, the 2nd premolar was positioned in center. considering the buccal cusp as a guide, the 1st molar and the 2nd molar were positioned in center. the distance ratio(d/a) was incresed constantly from the lower canine to the 2nd molar d ; the distance between the buccal vestibule(the lowest point) and the buccal cusp tips of the lower posterior teeth. a ; the distance between the buccal vestibule(the lowest point) and the lingual vestibule(the lowest point). The lower canine was positioned lingually($0.11{\pm}0.13$) than the labial vestibule, and the central incisor and the lateral incisor were positioned almost in the imaginary perpendicular plane of the labial vestibule(the lowest point).

• Journal of Dental Rehabilitation and Applied Science
• /
• v.35 no.2
• /
• pp.55-63
• /
• 2019

The aim of this article was to review various methods used to evaluate the accuracy of digital dental models. When evaluating the accuracy of digital models, the errors can be reduced by educating examiners and using artificial landmarks. The accuracy evaluation methods of digital dental models are divided into linear measurement, 2-dimensional cross-sectional analysis, and 3-dimensional best fit measurement. As the technology of scanners develops, many studies have been conducted to compare the accuracy of digital impression and conventional impression. According to improvement of scan technologies and development of 3-dimensional model analysis software, the ability to evaluate the accuracy of digital models is becoming more efficient. In this article, we describe the methods for evaluating the accuracy of a digital model and investigate effective accuracy analysis methods for each situation.

• Journal of Internet of Things and Convergence
• /
• v.9 no.6
• /
• pp.125-134
• /
• 2023

The purpose of this paper is to propose a method to improve the performance of the previous research is characterized by recognizing facial gestures from the 3D coordinates of seven landmarks selected from the MediaPipe Face Mesh model, generating corresponding user events, and executing corresponding commands. The proposed method applied adaptive moving average processing to the cursor positions in the process to stabilize the cursor by alleviating microtremor, and improved performance by blocking temporary opening/closing discrepancies between both eyes when opening and closing both eyes simultaneously. As a result of the usability evaluation of the proposed facial gesture interface, it was confirmed that the average recognition rate of facial gestures was increased to 98.7% compared to 95.8% in the previous research.

• The korean journal of orthodontics
• /
• v.52 no.4
• /
• pp.287-297
• /
• 2022

Objective: To investigate the pattern of accuracy change in artificial intelligence-assisted landmark identification (LI) using a convolutional neural network (CNN) algorithm in serial lateral cephalograms (Lat-cephs) of Class III (C-III) patients who underwent two-jaw orthognathic surgery. Methods: A total of 3,188 Lat-cephs of C-III patients were allocated into the training and validation sets (3,004 Lat-cephs of 751 patients) and test set (184 Lat-cephs of 46 patients; subdivided into the genioplasty and non-genioplasty groups, n = 23 per group) for LI. Each C-III patient in the test set had four Lat-cephs: initial (T0), pre-surgery (T1, presence of orthodontic brackets [OBs]), post-surgery (T2, presence of OBs and surgical plates and screws [S-PS]), and debonding (T3, presence of S-PS and fixed retainers [FR]). After mean errors of 20 landmarks between human gold standard and the CNN model were calculated, statistical analysis was performed. Results: The total mean error was 1.17 mm without significant difference among the four time-points (T0, 1.20 mm; T1, 1.14 mm; T2, 1.18 mm; T3, 1.15 mm). In comparison of two time-points ([T0, T1] vs. [T2, T3]), ANS, A point, and B point showed an increase in error (p < 0.01, 0.05, 0.01, respectively), while Mx6D and Md6D showeda decrease in error (all p < 0.01). No difference in errors existed at B point, Pogonion, Menton, Md1C, and Md1R between the genioplasty and non-genioplasty groups. Conclusions: The CNN model can be used for LI in serial Lat-cephs despite the presence of OB, S-PS, FR, genioplasty, and bone remodeling.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.3
• /
• pp.164-173
• /
• 2014

In underwater robotics, vision would be a key element for recognition in underwater environments. However, due to turbidity an underwater optical camera is rarely available. An underwater imaging sonar, as an alternative, delivers low quality sonar images which are not stable and accurate enough to find out natural objects by image processing. For this, artificial landmarks based on the characteristics of ultrasonic waves and their recognition method by a shape matrix transformation were proposed and were proven in Part 1. But, this is not working properly in undulating and dynamically noisy sea-bottom. To solve this, we propose a framework providing a selection phase of likelihood candidates, a selection phase for final candidates, recognition phase and tracking phase in sequence images, where a particle filter based selection mechanism to eliminate fake candidates and a mean shift based tracking algorithm are also proposed. All 4 steps are running in parallel and real-time processing. The proposed framework is flexible to add and to modify internal algorithms. A pool test and sea trial are carried out to prove the performance, and detail analysis of experimental results are done. Information is obtained from tracking phase such as relative distance, bearing will be expected to be used for control and navigation of underwater robots.