• 한국컴퓨터정보학회논문지
• /
• 제28권3호
• /
• pp.25-33
• /
• 2023

CT 영상의 획득 및 전송 등의 과정에서 발생하는 잡음은 영상의 질을 저하시키는 요소로 작용한다. 따라서 이를 해결하기 위한 잡음제거는 영상처리에서 중요한 전처리 과정이다. 본 논문에서는 딥러닝의 convolutional autoencoder (CAE) 모형에서 기존 컨볼루션 연산 대신 deformable 컨볼루션 연산을 적용한 deformable convolutional autoencoder (DeCAE) 모형을 이용하여 잡음을 제거하고자 한다. 여기서 deformable 컨볼루션 연산은 기존 컨볼루션 연산보다 유연한 영역에서 영상의 특징들을 추출할 수 있다. 제안된 DeCAE 모형은 기존 CAE 모형과 같은 인코더-디코더 구조로 되어있으나 효율적인 잡음제거를 위해 인코더는 deformable 컨볼루션 층으로 구성하고, 디코더는 기존 컨볼루션 층으로 구성하였다. 본 논문에서 제안된 DeCAE 모형의 성능 평가를 위해 다양한 잡음, 즉, 가우시안 잡음, 임펄스 잡음 그리고 포아송 잡음에 의해 훼손된 CT 영상을 대상으로 실험하였다. 성능 실험 결과, DeCAE 모형은 전통적인 필터 즉, Mean 필터, Median 필터와 이를 개선한 Bilateral 필터, NL-means 방법 뿐만 아니라 기존의 CAE 모형보다 정성적이고, 정량적인 척도 즉, MAE (Mean Absolute Error), PSNR (Peak Signal-to-Noise Ratio) 그리고 SSIM (Structural Similarity Index Measure) 면에서 우수한 결과를 보였다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 추계학술발표대회
• /
• pp.11-13
• /
• 2023

의미론적 분할(Semantic Segmentation)은 이미지 내의 객체 및 배경을 픽셀 단위로 분류하는 작업으로 정밀한 탐지가 요구되는 분야에서 활발히 연구되고 있다. 기존 어텐션 기법은 의미론적 분할의 다운샘플링(Downsampling) 과정에서 발생하는 정보손실을 완화하기 위해 널리 사용됐지만 고정된 Convolution 필터의 형태 때문에 객체의 형태에 따라 유동적으로 대응하지 못했다. 본 논문에서는 이를 보완하고자 Deformable Convolution과 셀프어텐션(Self-attention) 구조기반 어텐션 모듈을 사용한 의미론적 분할 모델을 제안한다.

• 한국멀티미디어학회논문지
• /
• 제25권7호
• /
• pp.895-902
• /
• 2022

Building segmentation using satellite imagery such as EO (Electro-Optical) and SAR (Synthetic-Aperture Radar) images are widely used due to their various uses. EO images have the advantage of having color information, and they are noise-free. In contrast, SAR images can identify the physical characteristics and geometrical information that the EO image cannot capture. This paper proposes a learning framework for efficient building segmentation that consists of a teacher-student-based privileged knowledge distillation and deformable convolution block. The teacher network utilizes EO and SAR images simultaneously to produce richer features and provide them to the student network, while the student network only uses EO images. To do this, we present objective functions that consist of Kullback-Leibler divergence loss and knowledge distillation loss. Furthermore, we introduce deformable convolution to avoid pixel-level noise and efficiently capture hard samples such as small and thin buildings at the global level. Experimental result shows that our method outperforms other methods and efficiently captures complex samples such as a small or narrow building. Moreover, Since our method can be applied to various methods.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2021년도 추계학술대회
• /
• pp.41-44
• /
• 2021

In this paper, we propose an efficient reference-based compression artifact reduction network for 360-degree images in an equi-rectangular projection (ERP) domain. In our insight, conventional image restoration methods cannot be applied straightforwardly to 360-degree images due to the spherical distortion. To address this problem, we propose an adaptive disparity estimator using a deformable convolution to exploit correlation among 360-degree images. With the help of the proposed convolution, the disparity estimator establishes the spatial correspondence successfully between the ERPs and extract matched textures to be used for image restoration. The experimental results demonstrate that the proposed algorithm provides reliable high-quality textures from the reference and improves the quality of the restored image as compared to the state-of-the-art single image restoration methods.

• International Journal of Naval Architecture and Ocean Engineering
• /
• 제9권3호
• /
• pp.266-281
• /
• 2017

Hydroelastic interactions of a deformable floating body with random waves are investigated in time domain. Both hydroelastic motion and structural dynamics are solved by expansion of elastic modes and Fourier transform for the random waves. A direct and efficient structural analysis in time domain is developed. In particular, an efficient way of obtaining distributive loads for the hydrodynamic integral terms including convolution integral by using Fubini theory is explained. After confirming correctness of respective loading components, calculations of full distributions of loads in random waves are expedited by reformulating all the body loading terms into distributed forms. The method is validated by extensive convergence tests and comparisons against the counterparts of the frequency-domain analysis. Characteristics of motion/deformation responses and stress resultants are investigated through a parametric study with varying bending rigidity and types of random waves. Relative contributions of componential loads are identified. The consequence of elastic-mode resonance is underscored.

• 전산구조공학
• /
• 제7권4호
• /
• pp.85-101
• /
• 1994

적층판의 동적거동에 대한 유한요소해석모델개발을 목적으로 전단변형을 적합하게 고려한 적층판이론에 대한 변분원리를 유도하였다. 유도방법은 Sandhu 등에 의해 개발된 다변수 경계치문제의 변분원리이론을 따랐으며, 지배방정식의 미분연산자 매트릭스를 self-adjoint로 만들기 위하여 convolution을 이중선형사상으로 사용하였다. 유도된 적층판의 범함수에는 경계조건, 초기조건뿐만 아니라 유한요소해석모델에서 생길 수 있는 요소간 불연속조건도 포함시킬 수 있다. 상태변수의 적합함수공간을 확장하거나 특정조건을 적용하므로서 다양한 형태의 범함수를 유도할 수 있으며, 이를 통해 다양한 유한요소해석모델의 개발이 가능함을 논하였다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2022년도 추계학술발표대회
• /
• pp.625-627
• /
• 2022

In the construction and development of modern industrial production technology, the traditional technology management mode is faced with many problems such as low qualification rates and high application costs. In the research, an improved workpiece defect detection method based on deep learning is proposed, which can control the application cost and improve the detection efficiency of irregular defects. Based on the research of the current situation of deep learning applications, this paper uses the improved Faster R-CNN network structure model as the core detection algorithm to automatically locate and classify the defect areas of the workpiece. Firstly, the robustness of the model was improved by appropriately changing the depth and the number of channels of the backbone network, and the hyperparameters of the improved model were adjusted. Then the deformable convolution is added to improve the detection ability of irregular defects. The final experimental results show that this method's average detection accuracy (mAP) is 4.5% higher than that of other methods. The model with anchor size and aspect ratio (65,129,257,519) and (0.2,0.5,1,1) has the highest defect recognition rate, and the detection accuracy reaches 93.88%.