• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.195-206
• /
• 2022

Crack detection is essential for inspection of existing structures and crack segmentation based on deep learning is a significant solution. However, datasets are usually one of the key issues. When building a new dataset for deep learning, laborious and time-consuming annotation of a large number of crack images is an obstacle. The aim of this study is to develop an approach that can automatically select a small portion of the most informative crack images from a large pool in order to annotate them, not to label all crack images. An active learning method with difficulty learning mechanism for crack segmentation tasks is proposed. Experiments are carried out on a crack image dataset of a steel box girder, which contains 500 images of 320×320 size for training, 100 for validation, and 190 for testing. In active learning experiments, the 500 images for training are acted as unlabeled image. The acquisition function in our method is compared with traditional acquisition functions, i.e., Query-By-Committee (QBC), Entropy, and Core-set. Further, comparisons are made on four common segmentation networks: U-Net, DeepLabV3, Feature Pyramid Network (FPN), and PSPNet. The results show that when training occurs with 200 (40%) of the most informative crack images that are selected by our method, the four segmentation networks can achieve 92%-95% of the obtained performance when training takes place with 500 (100%) crack images. The acquisition function in our method shows more accurate measurements of informativeness for unlabeled crack images compared to the four traditional acquisition functions at most active learning stages. Our method can select the most informative images for annotation from many unlabeled crack images automatically and accurately. Additionally, the dataset built after selecting 40% of all crack images can support crack segmentation networks that perform more than 92% when all the images are used.

• 한국통신학회논문지
• /
• 제29권11C호
• /
• pp.1527-1540
• /
• 2004

본 논문은 트래픽 정보취득을 위하여 영상의 라인 샘플링을 이용한 고속이동물체 속도 측정 알고리즘을 제안하였다. 이동물체의 트래픽 정보 취득을 위한 속도 측정은 도로에 제 1 샘플라인과 제 2 샘플라인을 설정해 놓고, 물체가 샘플라인을 통과할 때 취득된 영상의 시변환 색조 데이터와 기준영상 색조 데이터 사이에서 차영상 기법으로 자동차를 검출하고, 자동차가 두 샘플라인 사이에 거리를 통과할 때 점유하는 프레임수로 속도를 측정하였다. 제 1 샘플라인과 제 2 샘플라인에서 각각 검출된 자동차의 색조로 동일성 판별을 하였다. 제안된 방법의 타당성을 검토하기 위하여 주행하는 자동차를 대상으로 동일성 판별 및 속도 측정을 한 결과, 동일성 판별은 두 개의 샘플링 라인을 통과하는 자동차의 색조 데이터로 판별됨을 보였고, 자동차의 속도 측정은 X-밴드 속도 측정 시스템과 비교한 결과 3% 이내임을 보였다.

• Korean Journal of Radiology
• /
• 제21권1호
• /
• pp.77-87
• /
• 2020

Objective: To assess the feasibility of simultaneous multislice-accelerated diffusion-weighted imaging (SMS-DWI) of the rectum in comparison with conventional DWI (C-DWI) in rectal cancer patients. Materials and Methods: This study included 65 patients with initially-diagnosed rectal cancer. All patients underwent C-DWI and SMS-DWI with acceleration factors of 2 and 3 (SMS2-DWI and SMS3-DWI, respectively) using a 3T scanner. Acquisition times of the three DWI sequences were measured. Image quality in the three DWI sequences was reviewed by two independent radiologists using a 4-point Likert scale and subsequently compared using the Friedman test. Apparent diffusion coefficient (ADC) values for rectal cancer and the normal rectal wall were compared among the three sequences using repeated measures analysis of variance. Results: Acquisition times using C-DWI, SMS2-DWI, and SMS3-DWI were 173 seconds, 107 seconds, (38.2% shorter than C-DWI), and 77 seconds (55.5% shorter than C-DWI), respectively. For all image quality parameters other than distortion (margin sharpness, artifact, lesion conspicuity, and overall image quality), C-DWI and SMS2-DWI yielded better results than did SMS3-DWI (Ps < 0.001), with no significant differences observed between C-DWI and SMS2-DWI (Ps ≥ 0.054). ADC values of rectal cancer (p = 0.943) and normal rectal wall (p = 0.360) were not significantly different among C-DWI, SMS2-DWI, and SMS3-DWI. Conclusion: SMS-DWI using an acceleration factor of 2 is feasible for rectal MRI resulting in substantial reductions in acquisition time while maintaining diagnostic image quality and similar ADC values to those of C-DWI.

• 한국인터넷방송통신학회논문지
• /
• 제16권1호
• /
• pp.221-225
• /
• 2016

본 논문은 자동차용 퓨즈 및 릴레이 박스의 취부상태를 검사하기 위한 비전시스템의 구현 예를 보여준다. 검사를 위한 vision system은 영상 취득부와 검사 알고리즘, 그리고 사용자 인터페이스의 세 부분으로 구성된다. 영상 취득부는 box의 영상을 grabbing하는 부분으로 조명부와 광학부로 이루어진다. 검사 알고리즘은 영상을 이용하여 검사작업을 수행하는 부분이다. 사용자 인터페이스는 fuse & relay box의 모양과 부착되는 fuse와 relay를 등록하기 위한 사용자 인터페이스와 검사 작업을 수행하기 위한 사용자 인터페이스 두 부분으로 이루어진다. 본 연구에서 제시하는 검사 알고리즘은 신뢰도가 높아 실제 생산 현장에 사용이 가능하다.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1997년도 추계학술대회
• /
• pp.294-298
• /
• 1997

In the magnetic resonance imaging, the fast spin echo imaging technique is a widely used clinical imaging method, since its scanning time is much shorter than the conventional spin echo imaging and it gives the almost same image quality. However, the fast spin echo technique has two times longer imaging time or the dual echo acquisition which can obtain a spin density image and a $T_2$-weighted image simultaneously. To overcome such a drawback, this paper proposes a new fast dual echo imaging technique which can give the same quality images at the single echo imaging time. The proposed technique reduces the imaging time by overlapping most of echo train data for each image reconstruction. In order to verify its validity and usability the human head experimental results which were obtained at the 0.3T permanent MRI system are presented.

• 융합신호처리학회논문지
• /
• 제5권1호
• /
• pp.13-17
• /
• 2004

망막 촬영 및 다채널 고속 영상 획득 시스템을 개발하였다. 망막 두께 측정은 망막을 3차원으로 촬영하고 고속으로 신호처리를 할 수 있는 시스템을 요구한다. 망막에 레이저를 투사한 후에 반사되어 돌아오는 레이저의 양을 array photo diode를 이용하여 감지하며 이를 3차원 영상화하여 망막의 두께를 측정할 수 있다. 망막에 레이저를 투사하는 장치, APD 광센서를 이용한 망막 영상화 장치, 다채널 고속 A/D 변환장치 및 PCI 인터페이스를 개발하였다. polygon mirror와 galvano mirror를 이용하여 HeNe 레이저 빔을 각각 수평방향과 수직방향으로 주사하여 이미지 평면을 만들어 망막에 투사하였다. APD 어레이 광센서를 이용하여 각 층별로 나타나는 망막영상을 획득하였으며, 이를 실시간으로 A/D 변환하여 PCI 버스를 통해 컴퓨터로 전송하였다.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2004년도 춘계종합학술대회
• /
• pp.154-157
• /
• 2004

본 논문은 무지향성 영상획득을 용이하게 하기 위해 임베디드 웹서버의 무선랜을 이용한 CMOS 영상의 무선전송시스템 구현에 관한 연구이다. 시스템은 영상획득부와 임베디드 웹서버부, 클라이언트부로 구성한다. 영상획득부는 CMOS 센서 카메라와 프래임그래버로 구성하고, 임베디드 웹서버부는 무선랜을 구현한 타겟보드로 구성 하며, 클라이언트부는 서버에서 받은 영상을 모니터링 하기 위한 PC로 구성한다. 실험결과 8bit, 320$\times$240 크기의 4:2:2(YCbCr)비율에서 12.7fps 를 얻었으며, 구현된 시스템은 약1.9Mbyte의 전송 되어 시각적으로 원활한 영상이 모니터링 되였다.

• 한국항공우주학회지
• /
• 제47권8호
• /
• pp.590-598
• /
• 2019

현대 사회에서 인공위성은 통신, 영상 등의 분야에서 널리 이용되고 있다. 이 중에서도 인공위성을 통해 획득한 영상은 넓은 지역에 대한 다양한 정보를 담고 있어 농업, 자원개발 및 활용, 군사적 목적 등으로 활용되고 있다. 인공위성의 특성상 영상을 획득할 수 있는 시간이 매우 제한적이므로 주어진 시간 내에 최대한 효율적인 영상획득을 수행하는 것이 중요하다. 이를 위해서 본 연구에서는 인공위성이 영상을 획득하는 데 소요되는 시간 및 자세 기동에 대한 모델링을 수행하고 이를 바탕으로 휴리스틱 평가함수를 이용한 임무설계 알고리즘을 제안하고 수치 시뮬레이션을 통하여 해당 알고리즘의 성능을 검증하였다.

• Nuclear Engineering and Technology
• /
• 제55권10호
• /
• pp.3844-3853
• /
• 2023

Although radiation and chemotherapy methods for cancer therapy have advanced significantly, surgical resection is still recommended for most cancers. Therefore, intraoperative imaging studies have emerged as a surgical tool for identifying tumor margins. Intraoperative imaging has been examined using conventional imaging devices, such as optical near-infrared probes, gamma probes, and ultrasound devices. However, each modality has its limitations, such as depth penetration and spatial resolution. To overcome these limitations, hybrid imaging modalities and tracer studies are being developed. In a previous study, a multi-modal laparoscope with silicon photo-multiplier (SiPM)-based gamma detection acquired a 1 s interval gamma image. However, improvements in the near-infrared fluorophore (NIRF) signal intensity and gamma image central defects are needed to further evaluate the usefulness of multi-modal systems. In this study, an attempt was made to change the NIRF image acquisition method and the SiPM-based gamma detector to improve the source detection ability and reduce the image acquisition time. The performance of the multi-modal system using a complementary metal oxide semiconductor and modified SiPM gamma detector was evaluated in a phantom test. In future studies, a multi-modal system will be further optimized for pilot preclinical studies.

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 2000년도 THE THIRD INTERNATIONAL CONFERENCE ON AGRICULTURAL MACHINERY ENGINEERING. V.II
• /
• pp.318-324
• /
• 2000

Ultrasonic and magnetic resonance imaging systems are used to visualize the interior states of biological objects. These nondestructive methods have many advantages but too much expensive. And they do not give exact color information and may miss some details. If it is allowed to destruct some biological objects to get the interior and exterior information, constructing 3D image from the series of the sliced sectional images gives more useful information with relatively low cost. In this paper, PC based automatic 3D model generator was developed. The system was composed of three modules. One is the object handling and image acquisition module, which feeds and slices objects sequentially and maintains the paraffin cool to be in solid state and captures the sectional image consecutively. The second is the system control and interface module, which controls actuators for feeding, slicing, and image capturing. And the last is the image processing and visualization module, which processes a series of acquired sectional images and generates 3D graphic model. The handling module was composed of the gripper, which grasps and feeds the object and the cutting device, which cuts the object by moving cutting edge forward and backward. Sliced sectional images were acquired and saved in the form of bitmap file. The 3D model was generated to obtain the volumetric information using these 2D sectional image files after being segmented from the background paraffin. Once 3-D model was constructed on the computer, user could manipulate it with various transformation methods such as translation, rotation, scaling including arbitrary sectional view.