• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권2호
• /
• pp.544-564
• /
• 2022

Underwater images often suffer from color distortion, blurring and low contrast, which is caused by the propagation of light in the underwater environment being affected by the two processes: absorption and scattering. To cope with the poor quality of underwater images, this paper proposes a multiscale fusion underwater image enhancement method based on channel attention mechanism and local binary pattern (LBP). The network consists of three modules: feature aggregation, image reconstruction and LBP enhancement. The feature aggregation module aggregates feature information at different scales of the image, and the image reconstruction module restores the output features to high-quality underwater images. The network also introduces channel attention mechanism to make the network pay more attention to the channels containing important information. The detail information is protected by real-time superposition with feature information. Experimental results demonstrate that the method in this paper produces results with correct colors and complete details, and outperforms existing methods in quantitative metrics.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권1호
• /
• pp.16-37
• /
• 2022

Accurate liver segment segmentation based on radiological images is indispensable for the preoperative analysis of liver tumor resection surgery. However, most of the existing segmentation methods are not feasible to be used directly for this task due to the challenge of exact edge prediction with some tiny and slender vessels as its clinical segmentation criterion. To address this problem, we propose a novel deep learning based segmentation model, called Boundary-Aware Dual Attention Liver Segment Segmentation Model (BADA). This model can improve the segmentation accuracy of liver segments with enhancing the edges including the vessels serving as segment boundaries. In our model, the dual gated attention is proposed, which composes of a spatial attention module and a semantic attention module. The spatial attention module enhances the weights of key edge regions by concerning about the salient intensity changes, while the semantic attention amplifies the contribution of filters that can extract more discriminative feature information by weighting the significant convolution channels. Simultaneously, we build a dataset of liver segments including 59 clinic cases with dynamically contrast enhanced MRI(Magnetic Resonance Imaging) of portal vein stage, which annotated by several professional radiologists. Comparing with several state-of-the-art methods and baseline segmentation methods, we achieve the best results on this clinic liver segment segmentation dataset, where Mean Dice, Mean Sensitivity and Mean Positive Predicted Value reach 89.01%, 87.71% and 90.67%, respectively.

• Current Photovoltaic Research
• /
• 제10권1호
• /
• pp.1-5
• /
• 2022

Bifacial photovoltaic (PV) technology has received considerable attention in recent years due to the potential to achieve a higher annual energy yield compared to its monofacial PV systems. In this study, we fabricated the bifacial c-Si PV module with a shingled design using the conventional patterned bifacial solar cells. The shingled design PV module has recently attracted attention as a high-power module. Compared to the conventional module, it can have a much more active area due to the busbar-free structure. We employed the transparent backsheet for a light reception at the rear side of the PV module. Finally, we achieved a conversion power of 453.9 W for a 1300 mm × 2000 mm area. Moreover, we perform reliability tests to verify the durability of our Shingled Design Bifacial c-Si Photovoltaic module.

• 전기학회논문지P
• /
• 제67권2호
• /
• pp.75-81
• /
• 2018

In this paper for developing and implementing the car driver's front lane attention enhancement developed system using the car camera. The developed system automatically alarm the car driver when front cars make the dangerous situation. We use Raspberry Pi camera module V2 as car camera module, Raspberry Pi 3 board as hardware main board of implementing embedded system and develop the application library module which can be operated on the Raspberry situation. The application library module widely consist of two part, front car recognition part and dangerous situation distinguish part. Our developed system satisfy the performance test of the target system at the software test certification laboratory of TTA(Telecommunication Technology Association). We test four items as attentive car recognition ability at day and night, system performance, response time. We get the performance of developed system based on the four goal. The car driver's front lane attention enhancement system in this paper will be widely used at the ADAS(Advanced Driving Assistance System) because of the better performance and function.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권8호
• /
• pp.2552-2570
• /
• 2022

Underwater images usually have various problems, such as the color cast of underwater images due to the attenuation of different lights in water, the darkness of image caused by the lack of light underwater, and the haze effect of underwater images because of the scattering of light. To address the above problems, the channel attention mechanism, strengthen-operate-subtract (SOS) boosting mechanism and gated fusion module are introduced in our paper, based on which, an underwater image recovery network is proposed. First, for the color cast problem of underwater images, the channel attention mechanism is incorporated in our model, which can well alleviate the color cast of underwater images. Second, as for the darkness of underwater images, the similarity between the target underwater image after dehazing and color correcting, and the image output by our model is used as the loss function, so as to increase the brightness of the underwater image. Finally, we employ the SOS boosting module to eliminate the haze effect of underwater images. Moreover, experiments were carried out to evaluate the performance of our model. The qualitative analysis results show that our method can be applied to effectively recover the underwater images, which outperformed most methods for comparison according to various criteria in the quantitative analysis.

• 말소리와 음성과학
• /
• 제10권1호
• /
• pp.39-48
• /
• 2018

A typical statistical parametric speech synthesis (text-to-speech, TTS) system consists of separate modules, such as a text analysis module, an acoustic modeling module, and a speech synthesis module. This causes two problems: 1) expert knowledge of each module is required, and 2) errors generated in each module accumulate passing through each module. An end-to-end TTS system could avoid such problems by synthesizing voice signals directly from an input string. In this study, we implemented an end-to-end Korean TTS system using Google's Tacotron, which is an end-to-end TTS system based on a sequence-to-sequence model with attention mechanism. We used 4392 utterances spoken by a Korean female speaker, an amount that corresponds to 37% of the dataset Google used for training Tacotron. Our system obtained mean opinion score (MOS) 2.98 and degradation mean opinion score (DMOS) 3.25. We will discuss the factors which affected training of the system. Experiments demonstrate that the post-processing network needs to be designed considering output language and input characters and that according to the amount of training data, the maximum value of n for n-grams modeled by the encoder should be small enough.

• 대한임베디드공학회논문지
• /
• 제17권5호
• /
• pp.265-272
• /
• 2022

As the risk of lung cancer has increased, early-stage detection and treatment of cancers have received a lot of attention. Among various medical imaging approaches, computer tomography (CT) has been widely utilized to examine the size and growth rate of lung nodules. However, the process of manual examination is a time-consuming task, and it causes physical and mental fatigue for medical professionals. Recently, many computer-aided diagnostic methods have been proposed to reduce the workload of medical professionals. In recent studies, encoder-decoder architectures have shown reliable performances in medical image segmentation, and it is adopted to predict lesion candidates. However, localizing nodules in lung CT images is a challenging problem due to the extremely small sizes and unstructured shapes of nodules. To solve these problems, we utilize atrous spatial pyramid pooling (ASPP) to minimize the loss of information for a general U-Net baseline model to extract rich representations from various receptive fields. Moreover, we propose mixed-up attention mechanism of reverse, boundary and convolutional block attention module (CBAM) to improve the accuracy of segmentation small scale of various shapes. The performance of the proposed model is compared with several previous attention mechanisms on the LIDC-IDRI dataset, and experimental results demonstrate that reverse, boundary, and CBAM (RB-CBAM) are effective in the segmentation of small nodules.

• 한국인터넷방송통신학회논문지
• /
• 제21권6호
• /
• pp.155-161
• /
• 2021

최근, 실시간으로 카메라를 통해 동작을 인식하는 기술의 연구가 많이 진행되고 있다. 기존의 연구들에서는 사람의 관절로부터 특징을 추출하는 개수가 적기 때문에 동작 분류의 정확도가 낮은 한계점들이 있다. 본 논문에서는 이러한 한계점들을 해결하기 위해 움직일 때 변하는 관절의 각도를 특징 추출하여 계산하는 알고리즘과 이미지 분류 시에 정확도가 높은 CBAM(Convolutional Block Attention Module)을 사용한 분류모델을 제안한다. AI Hub에서 제공하는 피트니스 자세 이미지로부터 5가지 운동 동작 이미지를 인용하여 분류 모델에 적용한다. 구글에서 제공하는 그래프 기반 프레임워크인 MediaPipe 기법을 사용하여, 이미지로부터 운동 동작 분류에 중요한 8가지 관절 각도 정보를 추가적으로 추출한다. 추출한 특징들을 모델의 입력으로 설정하여, 분류 모델을 학습시킨다. 시뮬레이션 결과로부터 제안한 모델은 높은 정확도로 운동 동작을 구분하는 것을 확인할 수 있다.

• 정보보호학회논문지
• /
• 제30권6호
• /
• pp.1053-1065
• /
• 2020

최근 하드웨어의 성능과 인공지능 기술이 발달함에 따라 육안으로 구분하기 어려운 정교한 가짜 동영상들이 증가하고 있다. 인공지능을 이용한 얼굴 합성 기술을 딥페이크라고 하며 약간의 프로그래밍 능력과 딥러닝 지식만 있다면 누구든지 딥페이크를 이용하여 정교한 가짜 동영상을 제작할 수 있다. 이에 무분별한 가짜 동영상이 크게 증가하였으며 이는 개인 정보 침해, 가짜 뉴스, 사기 등에 문제로 이어질 수 있다. 따라서 사람의 눈으로도 진위를 가릴 수 없는 가짜 동영상을 탐지할 수 있는 방안이 필요하다. 이에 본 논문에서는 Bidirectional Convolutional LSTM과 어텐션 모듈(Attention module)을 적용한 딥페이크 탐지 모델을 제안한다. 본 논문에서 제안하는 모델은 어텐션 모듈과 신경곱 합성망 모델을 같이 사용되어 각 프레임의 특징을 추출하고 기존의 제안되어왔던 시간의 순방향만을 고려하는 LSTM과 달리 시간의 역방향도 고려하여 학습한다. 어텐션 모듈은 합성곱 신경망 모델과 같이 사용되어 각 프레임의 특징 추출에 이용한다. 실험을 통해 본 논문에서 제안하는 모델은 93.5%의 정확도를 갖고 기존 연구의 결과보다 AUC가 최대 50% 가량 높음을 보였다.

• 대한원격탐사학회지
• /
• 제38권6_1호
• /
• pp.1091-1100
• /
• 2022

딥러닝 기술의 진보와 함께 다양한 국내외 고해상도 원격탐사 영상의 활용이 가능함에 따라 딥러닝 기술과 원격탐사 빅데이터를 활용하여 도심 지역 건물 검출과 변화탐지에 활용하고자 하는 관심이 크게 증가하고 있다. 본 논문에서는 고해상도 원격탐사 영상의 의미론적 건물 분할을 위해서 건물 분할에 우수한 성능을 보이는 DeepResUNet 모델을 기본 구조로 하고 잔차 학습 단위를 개선하고 Convolutional Block Attention Module(CBAM)을 결합한 새로운 건물 분할 모델인 CBAM-DRUNet을 제안한다. 제안한 건물 분할 모델은 WHU 데이터셋과 INRIA 데이터셋을 이용한 성능 평가에서 UNet을 비롯하여 ResUNet, DeepResUNet 대비 F1 score, 정확도, 재현율 측면에서 모두 우수한 성능을 보였다.