• 문화기술의 융합
• /
• 제9권5호
• /
• pp.737-745
• /
• 2023

본 논문은 열화상 이미지를 활용하여 배전반 화재 발생을 감지하기 위한 인공지능 모델을 개발하는 연구에 대해 다룬다. 연구의 목표는 수집한 열화상 이미지를 전처리하여 객체 탐지 모델에 적합한 데이터로 가공하고, 이를 이용하여 배전반 내 화재 발생 여부를 판단하는 모델을 설계하는 것이다. 연구에서는 AI-HUB의 산업단지 내 학습용 열화상 이미지 데이터를 활용하였으며, CNN 기반 딥러닝 객체 검출 알고리즘 중 대표적인 모델인 Faster R-CNN과 RetinaNet을 사용하여 모델을 구축하고 두 개의 모델을 비교 분석하여 최적의 모델을 제안하고 있다.

• Journal of Korean Neurosurgical Society
• /
• 제60권5호
• /
• pp.597-603
• /
• 2017

Objective : Several surgical methods have been reported for treatment of ossification of the posterior longitudinal ligament (OPLL) in the thoracic spine. Despite rapid innovation of instruments and techniques for spinal surgery, the postoperative outcomes are not always favorable. This article reports a minimally invasive anterior decompression technique without instrumented fusion, which was modified from the conventional procedure. The authors present 2 cases of huge beak-type OPLL. Patients underwent minimally invasive anterior decompression without fusion. This method created a space on the ventral side of the OPLL without violating global thoracic spinal stability. Via this space, the OPLL and anterior lateral side of the dural sac can be seen and manipulated directly. Then, total removal of the OPLL was accomplished. No orthosis was needed. In this article, we share our key technique and concepts for treatment of huge thoracic OPLL. Methods : Case 1. 51-year-old female was referred to our hospital with right lower limb radiating pain and paresis. Thoracic OPLL at T6-7 had been identified at our hospital, and conservative treatment had been tried without success. Case 2. This 54-year-old female with a 6-month history of progressive gait disturbance and bilateral lower extremity radiating pain (right>left) was admitted to our institute. She also had hypoesthesia in both lower legs. Her symptoms had been gradually progressing. Computed tomography scans showed massive OPLL at the T9-10 level. Magnetic resonance imaging of the thoracolumbar spine demonstrated ventral bony masses with severe anterior compression of the spinal cord at the same level. Results : We used this surgical method in 2 patients with a huge beaked-type OPLL in the thoracic level. Complete removal of the OPLL via anterior decompression without instrumented fusion was accomplished. The 1st case had no intraoperative or postoperative complications, and the 2nd case had 1 intraoperative complication (dural tear) and no postoperative complications. There were no residual symptoms of the lower extremities. Conclusion : This surgical technique allows the surgeon to safely and effectively perform minimally invasive anterior decompression without instrumented fusion via a transthoracic approach for thoracic OPLL. It can be applied at the mid and lower level of the thoracic spine and could become a standard procedure for treatment of huge beak-type thoracic OPLL.

• 척추신경추나의학회지
• /
• 제16권2호
• /
• pp.79-86
• /
• 2021

Objectives This study aimed to assess the role of complex Korean medicinal treatment with Chuna manual therapy in two patients with chronic pain after posterior lumbar fusion surgery. Methods A retrospective analysis was performed on 2 patients postoperatively based on their medical records. The surgery regions were verified using T2-weighted axial magnetic resonance imaging. Patients with chronic pain after spondylolisthesis posterior lumbar fusion surgery received complex Korean medicinal treatment with Chuna manual therapy during hospitalization. Numeric rating scale (NRS) in the degree of 0-10 and Oswestry disability index (ODI) were measured before and after treatment. Results Case 1 had an improved NRS score from 7 to 4, and Case 2 had an improved NRS score from 7 to 5. In addition, ODI score improved in both cases. Conclusions Complex Korean medicinal treatment with Chuna manual therapy is effective for relief from chronic pain after posterior lumbar fusion surgery.

• 방송공학회논문지
• /
• 제10권2호
• /
• pp.238-246
• /
• 2005

본 논문에서는 공간 적응적 제약조건과 정칙화 함수를 이용한 반복적 고해상도 영상보간 기법을 제안한다. 제안된 정칙화 영상보간 알고리듬은 에지 방향에 따라 제약조건들을 적응적으로 적용하고, 각각의 반복 연산 단계에서 에지 방향별 정칙화에 적합한 정칙화 함수를 최적화하여 고해상도 영상보간을 구현한다. 제안한 알고리즘은 기존의 비적응적 정칙화 보간 방법뿐만 아니라 적응적 보간 방법보다도 방향성 고주파 성분을 적절히 보존하는 동시에 잡음과 같은 바람직하지 못한 효과들을 억제할 수 있다. 마지막으로 본 논문에서 제안한 알고리듬의 성능평가를 위해서 기존에 제안된 여러 가지의 고해상도 영상보간 알고리듬과의 다양한 비교실험을 수행하였고, 이를 통하여 제안한 고해상도 영상보간 기법이 주관적으로나 객관적으로 우수함을 보였다.

• Investigative Magnetic Resonance Imaging
• /
• 제14권2호
• /
• pp.87-94
• /
• 2010

목적: 금속에 의한 영상 왜곡에 대한 정확한 계산하고 영상으로부터의 금속 물질의 위치 결정한다. 대상 및 방법: 주자기장과 일정 각도를 이루는 무한히 긴 비자성 금속 실린더에 대한 라플라스 방정식을 풀고, 이 결과를 이용하여 절편선택 경사자계와 주파수 부호화 경사자계에 의한 영상에 왜곡을 계산한다. 계산 결과를 바탕으로 하여 왜곡된 영상으로부터 원통형 보철물의 위치를 계산한다. 결과: Folded point와 금속 실린더의 중심 사이의 거리를 영상으로부터 측정하여 계산 결과와 비교한다. 측정 결과와 계산 결과 간의 퍼센트 오차는 한 경우를 제외하고 5% 이내였다. 결론: 금속 실린더가 자기장 하에 있을 때, 영상의 왜곡을 시뮬레이션 하였고, 이 기술은 생검술 또는 외과 수술 등을 자기공명영상법을 이용여 실시간 모니터링하는데 적용할 수 있을 것으로 기대한다.

• Journal of Korean Neurosurgical Society
• /
• 제60권5호
• /
• pp.485-497
• /
• 2017

Surgical treatment of the degenerative disc disease has evolved from traditional open spine surgery to minimally invasive spine surgery including endoscopic spine surgery. Constant improvement in the imaging modality especially with introduction of the magnetic resonance imaging, it is possible to identify culprit degenerated disc segment and again with the discography it is possible to diagnose the pain generator and pathological degenerated disc very precisely and its treatment with minimally invasive approach. With improvements in the optics, high resolution camera, light source, high speed burr, irrigation pump etc, minimally invasive spine surgeries can be performed with various endoscopic techniques for lumbar, cervical and thoracic regions. Advantages of endoscopic spine surgeries are less tissue dissection and muscle trauma, reduced blood loss, less damage to the epidural blood supply and consequent epidural fibrosis and scarring, reduced hospital stay, early functional recovery and improvement in the quality of life & better cosmesis. With precise indication, proper diagnosis and good training, the endoscopic spine surgery can give equally good result as open spine surgery. Initially, endoscopic technique was restricted to the lumbar region but now it also can be used for cervical and thoracic disc herniations. Previously endoscopy was used for disc herniations which were contained without migration but now days it is used for highly up and down migrated disc herniations as well. Use of endoscopic technique in lumbar region was restricted to disc herniations but gradually it is also used for spinal canal stenosis and endoscopic assisted fusion surgeries. Endoscopic spine surgery can play important role in the treatment of adolescent disc herniations especially for the persons who engage in the competitive sports and the athletes where less tissue trauma, cosmesis and early functional recovery is desirable. From simple chemonucleolysis to current day endoscopic procedures the history of minimally invasive spine surgery is interesting. Appropriate indications, clear imaging prior to surgery and preplanning are keys to successful outcome. In this article basic procedures of percutaneous endoscopic lumbar discectomy through transforaminal and interlaminar routes, percutaneous endoscopic cervical discectomy, percutaneous endoscopic posterior cervical foraminotomy and percutaneous endoscopic thoracic discectomy are discussed.

• 한국의학물리학회:학술대회논문집
• /
• 한국의학물리학회 2002년도 Proceedings
• /
• pp.450-453
• /
• 2002

In radiotherapy treatment planning, it is critical to deliver the radiation dose to tumor and protect surrounding normal tissue. Recent developments in functional imaging and radiotherapy treatment technology have been raising chances to control tumor saving normal tissues. A brain phantom which could be used for image registration technique of CT-MR and CT-SPECT images using surface matching was developed. The brain phantom was specially designed to obtain imaging dataset of CT, MR, and SPECT. The phantom had an external frame with 4 N-shaped pipes filled with acryl rods, Pb rods for CT, MR, and SPECT imaging, respectively. 8 acrylic pipes were inserted into the empty space of the brain phantom to be imaged for geometric evaluation of the matching. For an optimization algorithm of image registration, we used Downhill simplex algorithm suggested as a fast surface matching algorithm. Accuracy of image fusion was assessed by the comparison between the center points of the section of N-shaped bars in the external frame and the inserted pipes of the phantom and minimized cost functions of the optimization algorithm. Technique with partially transparent, mixed images using color on gray was used for visual assessment of the image registration process. The errors of image registration of CT-MR and CT-SPECT were within 2mm and 4mm, respectively. Since these errors were considered within a reasonable margin from the phantom study, the phantom is expected to be used for conventional image registration between multimodal image datasets..

• Smart Structures and Systems
• /
• 제33권1호
• /
• pp.55-64
• /
• 2024

This paper proposes a fusion imaging-based coating-defect classification method for steel structures that uses zero-shot learning. In the proposed method, a halogen lamp generates heat energy on the coating surface of a steel structure, and the resulting heat responses are measured by an infrared (IR) camera, while photos of the coating surface are captured by a charge-coupled device (CCD) camera. The measured heat responses and visual images are then analyzed using zero-shot learning to classify the coating defects, and the estimated coating defects are visualized throughout the inspection surface of the steel structure. In contrast to older approaches to coating-defect classification that relied on visual inspection and were limited to surface defects, and older artificial neural network (ANN)-based methods that required large amounts of data for training and validation, the proposed method accurately classifies both internal and external defects and can classify coating defects for unobserved classes that are not included in the training. Additionally, the proposed model easily learns about additional classifying conditions, making it simple to add classes for problems of interest and field application. Based on the results of validation via field testing, the defect-type classification performance is improved 22.7% of accuracy by fusing visual and thermal imaging compared to using only a visual dataset. Furthermore, the classification accuracy of the proposed method on a test dataset with only trained classes is validated to be 100%. With word-embedding vectors for the labels of untrained classes, the classification accuracy of the proposed method is 86.4%.

• 한국정밀공학회지
• /
• 제29권8호
• /
• pp.853-862
• /
• 2012

The present study develops a method for directly measuring the temperature field in the primary deformation zone with a high spatial resolution during 2-D orthogonal machining. This is enabled by the use of a high-speed, charge-coupled device (CCD) based, infra-red (IR) imaging system which allows characteristics of the temperature field such as the location and magnitude of the highest temperature and temperature gradient in the primary deformation zone to be identified. Based on these data, the relation between the machining temperature and the cutting conditions is investigated.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제13권1호
• /
• pp.1-11
• /
• 2013

The determination of the pose of the imaging camera is a fundamental problem in computer vision. In the monocular case, difficulties in determining the scene scale and the limitation to bearing-only measurements increase the difficulty in estimating camera pose accurately. Many mobile phones now contain inertial measurement devices, which may lend some aid to the task of determining camera pose. In this study, by means of simulation and real-world experimentation, we explore an approach to monocular camera localization that incorporates both observations of the environment and measurements from accelerometers and gyroscopes. The unscented Kalman filter was implemented for this task. Our main contribution is a novel approach to landmark initialization in a Kalman filter; we characterize the tolerance to noise that this approach allows.