• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.207-220
• /
• 2022

Structural health monitoring (SHM) plays a vital role in the maintenance and operation of constructions. In recent years, autonomous inspection has received considerable attention because conventional monitoring methods are inefficient and expensive to some extent. To develop autonomous inspection, a potential approach of crack identification is needed to locate defects. Therefore, this study exploits two deep learning-based segmentation models, DeepLabv3+ and Mask R-CNN, for crack segmentation because these two segmentation models can outperform other similar models on public datasets. Additionally, impacts of label quality on model performance are explored to obtain an empirical guideline on the preparation of image datasets. The influence of image cropping and label refining are also investigated, and different strategies are applied to the dataset, resulting in six alternated datasets. By conducting experiments with these datasets, the highest mean Intersection-over-Union (mIoU), 75%, is achieved by Mask R-CNN. The rise in the percentage of annotations by image cropping improves model performance while the label refining has opposite effects on the two models. As the label refining results in fewer error annotations of cracks, this modification enhances the performance of DeepLabv3+. Instead, the performance of Mask R-CNN decreases because fragmented annotations may mistake an instance as multiple instances. To sum up, both DeepLabv3+ and Mask R-CNN are capable of crack identification, and an empirical guideline on the data preparation is presented to strengthen identification successfulness via image cropping and label refining.

• 대한치과보철학회지
• /
• 제58권4호
• /
• pp.363-368
• /
• 2020

적절하지 않은 위치에 식립된 임플란트의 보철물은 심미적, 기능적 문제를 나타낼 수 있으나 이를 해결하기는 어려운 때가 많다. 이러한 경우에 재식립 혹은 연조직 및 경조직 이식을 포함하는 외과적 방법을 고려해 볼 수 있지만 결과 예측이 힘들며 긴 치유 기간 및 술 후 불편감과 추가적인 수술 비용이 동반된다. 반면, 보철적 방법으로는 치은 색상의 세라믹이 포함된 고정성 보철물을 제작하거나 가철성 보철물인 gingival mask 제작 등을 생각해볼 수있다. 본 증례에서는 80세의 남환이 과도하게 구개측으로 식립된 임플란트로 인한 상순과 보철물 사이의 음식물 저류에 대한 불편감 및 심미적인 부분에 대한 불만족을 주소로 내원하였고, gingival mask를 제작하여 단 기간 내에 만족스러운 결과를 얻었기에 이를 보고하고자 한다.

• 대한두개안면성형외과학회지
• /
• 제9권2호
• /
• pp.77-80
• /
• 2008

Purpose: The majority of nasal fractures have been treated by closed reduction. And they were manipulated under local anesthesia or general anesthesia. Under the local anesthesia, patients can feel the pain and fear, so general anesthesia through the endotracheal intubation became popularized recently to treat the nasal fracture. But it has still the drawbacks of postanesthetic complication. Therefore, under the mask ventilation anesthesia using oral airway, we tried to manipulate the nasal fracture. Methods: From July 2007 to November 2007, we worked with fifty patients that were manipulated the nasal fracture. Fifty patients were divided into two groups, general anesthesia with the endotracheal intubation group(n=25) and the mask ventilation using oral airway group(n=25). We checked up the anesthesia time, postanesthetic complication, postoperative aesthetic & functional problem of nose in two groups. Results: In total operation time and sore throat frequency among the postoperative anesthetic complications, there was statistically significant difference between the mask ventilation group and the endotracheal intubation group(p<0.05). But there was no difference statistically in nausea frequency(p>0.05). And no patients complained of postoperative nasal complication such as septal deviation, septal perforation, nasal obstruction and hump nose in two groups. Conclusion: Through the mask ventilation using oral airway, we could reach satisfactory results in the anesthetic time and postanesthetic complication.

• 한국정보처리학회논문지
• /
• 제7권2호
• /
• pp.542-551
• /
• 2000

본 논문에서는 MR 영상의 3차원 가시화 및 분석을 위한 단일 채널 MR 영상의 자동 뇌영역 분할 방법을 제안한다. 이 방법은 4단계의 2차원 및 3차원 처리에 의하여 뇌윤곽을 찾아낸다. 1,2단계에서는 곡선 적합을 이용한 자동 문턱치화에 의하여 머리마스크와 초기 뇌마스크를 생성한다. 3단계에서 입방보간으로 초기 뇌마스크의 3차원 볼륨을 생성하여 형태학적 연산, 연결부위 레이블링에 의하여 중기 뇌마스크를 생성한다. 최종적으로 곡선 적합에 의한 자동 문턱치화를 이용하여 뇌마스크를 정련한다. 제안한 알고리즘은 영상의 슬라이스 방향을 고려할 필요가 없고 영상이 뇌 전체를 포함하지 않아도 되며, T1, T2, PD, SPGR등 다양한 종류의 MR 영상의 자동적인 뇌영역의 분할에 유용하다. 실험에서 20세트 MR 영상에 대하여 수동분할을 기준으로 0.97 이상의 유지도를 보였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권11호
• /
• pp.5419-5435
• /
• 2017

The construction of panoramic images on smartphones and low-powered devices is a challenging task. In this paper, we propose a new approach for smoothly stitching images on mobile phones in the presence of moving objects in the scene. Our main contributions include handling moving object problems, reducing processing time, and generating rectangular panoramic images. First, unique and robust feature points are extracted using fast ORB method and a feature matching technique is applied to match the extracted feature points. After obtaining good matched feature points, we employ the non-deterministic RANSAC algorithm to discard wrong matches, and the hommography transformation matrix parameters are estimated with the algorithm. Afterward, we determine precise overlap regions of neighboring images and calculate their absolute differences. Then, thresholding operation and noise removal filtering are applied to create a mask of possible moving object regions. Sequentially, an optimal seam is estimated using dynamic programming algorithm, and a combination of linear blending with the mask information is applied to avoid seam transition and ghosting artifacts. Finally, image-cropping operation is utilized to obtain a rectangular boundary image from the stitched image. Experiments demonstrate that our method is able to produce panoramic images quickly despite the existence of moving objects.

• 방송공학회논문지
• /
• 제27권7호
• /
• pp.999-1010
• /
• 2022

The increase in vehicle purchases worldwide is having a very significant impact on the availability of parking spaces. In particular, since it is difficult to secure a parking space in an urban area, it may be of great help to the driver to check vehicle parking information in advance. However, the current parking lot information is still operated semi-manually, such as notifications. Therefore, in this study, we propose a system for detecting a parking space using a relatively simple image processing method based on an image taken from the sky and evaluate its performance. The proposed method first converts the captured RGB image into a black-and-white binary image. This is to simplify the calculation for detection using discrete information. Next, a morphological operation is applied to increase the clarity of the binary image, and a template mask in the form of a bounding box indicating a parking space is applied to check the parking state. Twelve image samples and 2181 total of test, were used for the experiment, and a threshold of 40% was used to detect each parking space. The experimental results showed that information on the availability of parking spaces for parking users was provided with an accuracy of 95%. Although the number of experimental images is somewhat insufficient to address the generality of accuracy, it is possible to confirm the possibility of parking space detection with a simple image processing method.

• 대한전자공학회논문지
• /
• 제18권4호
• /
• pp.34-42
• /
• 1981

PMOS집적기술을 이용하여 512-Bit mask programmable ROM을 설계하고 제작하였다. ROM의 내용은 제작공정에서 gate pattern으로 기억시켰으며 chip의 출력을 512(32×16)개의 점의 행렬로써 오실로스코프에 나타내어 확인하였다. 제작된 chip은 -6V와 - l2V의 범위에서 정상적으로 동작하였다 소모전력과 전달지연시간은 -6V에서 각각 3mW와 13μsec였다. -12V에서는 소모전력이 27mW로 증가하였으며 전달지연시간은 3μsec로 감소하였다. Chip의 출력은 TTL gate의 인력을 직접 구동시킬 수 있었으며 chip select에 의하여 출력을 disable 시켰을 때는 높은 임피던스 상태를 유지하였다.

• 한국정보통신학회논문지
• /
• 제10권2호
• /
• pp.308-314
• /
• 2006

수 마이크로 단위로 계측되는 반도체 COG의 검사 정밀도를 높이기 위해서 라인스캔 카메라가 이용된다. 여러 가지 불량 요인 중 이물질 검출은 COG 패턴이 미세하고 복잡하기 때문에 불량 자동 검사 단계에서 가장 어려운 기술이었다. 본 논문에서는 매칭 속도를 높이기 위하여 2단계 영역분할 템플릿 매칭 방법을 제안하였다. 아울러 수 마이크로 단위의 이물짙 검출을 위하여 그라디언트 마스크와 AND 연산을 이용한 새로운 방법을 제안하였다. 제안된 2단계 템플릿 매칭을 사용한 방법은 기존의 상관 계수 이용법 에 비해 0.3-0.4초 매칭 속도를 향상시켰다. 그리고 제안된 마스크 적용 이물질 검출방법은 기존 마스크를 이용하지 않은 방법에 비해 불량 검출률을 $5-8\%$ 향상시켰다.

• 한국항공운항학회지
• /
• 제30권2호
• /
• pp.55-60
• /
• 2022

A PSU (passenger service unit) is mounted on passenger seats in a cabin on an aircraft and consists of a crew call lamp, a reading lights, an information display lamp, an emergency oxygen generator, and an emergency oxygen mask. It is a safety device for providing convenience to passengers and providing oxygen to passengers in an emergency. This paper is a study on emergency oxygen supply systems and light systems of aircraft PSUs and a control device was developed to operate the system by analyzing the B767-300 aircraft's PSU circuit diagram. And the temperature generated by the B777-200ER aircraft's emergency oxygen generator was also measured by operating it directly. Through this, precautions for explaining the operation of an oxygen mask in an emergency were described and improvements were presented. Data acquired in these research processes can be used in the future to develop aircraft PSU (passenger service unit) and emergency oxygen generators.

• 산업경영시스템학회지
• /
• 제35권1호
• /
• pp.79-86
• /
• 2012

This study focuses on the problem of scheduling wafer lots of several recipe(operation condition) types in the photolithography workstation in a semiconductor wafer fabrication facility, and sequence-dependent recipe set up times may be required at the photolithography machines. In addition, a lot is able to be operated at a machine when the reticle(mask) corresponding to the recipe type is set up in the photolithography machine. We suggest various heuristic algorithms, in which developed recipe selection rules and lot selection rules are used to generate reasonable schedules to minimizing the total weighted flowtime. Results of computational tests on randomly generated test problems show that the suggested algorithms outperform a scheduling method used in a real manufacturing system in terms of the total weighted flowtime of the wafer lots with ready times.