• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.5
• /
• 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.

• Nuclear Engineering and Technology
• /
• v.55 no.8
• /
• pp.2854-2863
• /
• 2023

Objective: To present a hybrid approach that incorporates a constrained beam-hardening estimator (CBHE) and deep learning (DL)-based post-refinement for metal artifact reduction in dental cone-beam computed tomography (CBCT). Methods: Constrained beam-hardening estimator (CBHE) is derived from a polychromatic X-ray attenuation model with respect to X-ray transmission length, which calculates associated parameters numerically. Deep-learning-based post-refinement with an artifact disentanglement network (ADN) is performed to mitigate the remaining dark shading regions around a metal. Artifact disentanglement network (ADN) supports an unsupervised learning approach, in which no paired CBCT images are required. The network consists of an encoder that separates artifacts and content and a decoder for the content. Additionally, ADN with data normalization replaces metal regions with values from bone or soft tissue regions. Finally, the metal regions obtained from the CBHE are blended into reconstructed images. The proposed approach is systematically assessed using a dental phantom with two types of metal objects for qualitative and quantitative comparisons. Results: The proposed hybrid scheme provides improved image quality in areas surrounding the metal while preserving native structures. Conclusion: This study may significantly improve the detection of areas of interest in many dentomaxillofacial applications.

• Korean Journal of Artificial Intelligence
• /
• v.11 no.3
• /
• pp.17-22
• /
• 2023

In this paper, we propose a black ice detection system using Convolutional Neural Networks (CNNs). Black ice poses a serious threat to road safety, particularly during winter conditions. To overcome this problem, we introduce a CNN-based architecture for real-time black ice detection with an encoder-decoder network, specifically designed for real-time black ice detection using thermal images. To train the network, we establish a specialized experimental platform to capture thermal images of various black ice formations on diverse road surfaces, including cement and asphalt. This enables us to curate a comprehensive dataset of thermal road black ice images for a training and evaluation purpose. Additionally, in order to enhance the accuracy of black ice detection, we propose a multi-scale dilation convolution feature fusion (MsDC-FF) technique. This proposed technique dynamically adjusts the dilation ratios based on the input image's resolution, improving the network's ability to capture fine-grained details. Experimental results demonstrate the superior performance of our proposed network model compared to conventional image segmentation models. Our model achieved an mIoU of 95.93%, while LinkNet achieved an mIoU of 95.39%. Therefore, it is concluded that the proposed model in this paper could offer a promising solution for real-time black ice detection, thereby enhancing road safety during winter conditions.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.185-185
• /
• 2021

기후변화로 인한 돌발 강우 등 이상 기후 현상이 증가함에 따라 정확한 강우예측의 중요성은 더 증가하는 추세이다. 전통적인 강우예측의 경우 기상수치모델 또는 외삽법을 이용한 레이더 기반 강우예측 기법을 이용하며, 최근 머신러닝 기술의 발달에 따라 이를 활용한 레이더 자료기반 강우예측기법이 개발되고 있다. 기존 머신러닝을 이용한 강우예측 모델의 경우 주로 시계열 이미지 예측에 적합한 2차원 순환 신경망 기반 기법(Convolutional Long Short-Term Memory, ConvLSTM) 또는 합성곱 신경망 기반 기법(Convolutional Neural Network(CNN) Encoder-Decoder) 등을 이용한다. 본 연구에서는 생성적 적대 신경망 기반 기법(Generative Adversarial Network, GAN)을 이용해 미래 강우예측을 수행하도록 하였다. GAN 방법론은 이미지를 생성하는 생성자와 이를 실제 이미지와 구분하는 구별자가 경쟁하며 학습되어 현재 이미지 생성 분야에서 높은 성능을 보여주고 있다. 본 연구에서 개발한 GAN 기반 모델은 기상청에서 제공된 2016년~2019년까지의 레이더 이미지 자료를 이용하여 초단기, 단기 강우예측을 수행하도록 학습시키고, 2020년 레이더 이미지 자료를 이용해 단기강우예측을 모의하였다. 또한, 기존 머신러닝 기법을 기반으로 한 모델들의 강우예측결과와 GAN 기반 모델의 강우예측결과를 비교분석한 결과, 본 연구를 통해 개발한 강우예측모델이 단기강우예측에 뛰어난 성능을 보이는 것을 확인할 수 있었다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.1191-1194
• /
• 2022

인터넷의 발전으로 수많은 이미지와 비디오를 손쉽게 이용할 수 있게 되었다. 이미지와 비디오 데이터의 양이 기하급수적으로 증가함에 따라, JPEG, HEVC, VVC 등 이미지와 비디오를 효율적으로 저장하기 위한 부호화 기술들이 등장했다. 최근에는 인공신경망을 활용한 학습 기반 모델이 발전함에 따라, 이를 활용한 이미지 및 비디오 압축 기술에 관한 연구가 빠르게 진행되고 있다. NNIC (Neural Network based Image Coding)는 이러한 학습 가능한 인공신경망 기반 이미지 부호화 기술을 의미한다. 본 논문에서는 NNIC 모델과 인공신경망 기반의 초해상화(Super Resolution) 모델을 합동훈련하여 기존 NNIC 모델보다 더 높은 성능을 보일 수 있는 방법을 제시한다. 먼저 NNIC 인코더(Encoder)에 이미지를 입력하기 전 다운 스케일링(Down Scaling)으로 쌍삼차보간법을 사용하여 이미지의 화소를 줄인 후 부호화(Encoding)한다. NNIC 디코더(Decoder)를 통해 부호화된 이미지를 복호화(Decoding)하고 업 스케일링으로 초해상화를 통해 복호화된 이미지를 원본 이미지로 복원한다. 이때 NNIC 모델과 초해상화 모델을 합동훈련한다. 결과적으로 낮은 비트량에서 더 높은 성능을 볼 수 있는 가능성을 보았다. 또한 합동훈련을 함으로써 전체 성능의 향상을 보아 학습 시간을 늘리고, 압축 잡음을 위한 초해상화 모델을 사용한다면 기존의 NNIC 보다 나은 성능을 보일 수 있는 가능성을 시사한다.

• ETRI Journal
• /
• v.45 no.5
• /
• pp.822-835
• /
• 2023

Recent semantic segmentation frameworks usually combine low-level and high-level context information to achieve improved performance. In addition, postlevel context information is also considered. In this study, we present a Context ReFinement Network (CRFNet) and its training method to improve the semantic predictions of segmentation models of the encoder-decoder structure. Our study is based on postprocessing, which directly considers the relationship between spatially neighboring pixels of a label map, such as Markov and conditional random fields. CRFNet comprises two modules: a refiner and a combiner that, respectively, refine the context information from the output features of the conventional semantic segmentation network model and combine the refined features with the intermediate features from the decoding process of the segmentation model to produce the final output. To train CRFNet to refine the semantic predictions more accurately, we proposed a sequential training scheme. Using various backbone networks (ENet, ERFNet, and HyperSeg), we extensively evaluated our model on three large-scale, real-world datasets to demonstrate the effectiveness of our approach.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.3
• /
• pp.528-550
• /
• 2024

Warehousing demand prediction is an essential part of the supply chain, providing a fundamental basis for product manufacturing, replenishment, warehouse planning, etc. Existing forecasting methods cannot produce accurate forecasts since warehouse demand is affected by external factors such as holidays and seasons. Some aspects, such as consumer psychology and producer reputation, are challenging to quantify. The data can fluctuate widely or do not show obvious trend cycles. We introduce a new model for warehouse demand prediction called MAGRU, which stands for Multi-layer Attention with GRU. In the model, firstly, we perform the embedding operation on the input sequence to quantify the external influences; after that, we implement an encoder using GRU and the attention mechanism. The hidden state of GRU captures essential time series. In the decoder, we use attention again to select the key hidden states among all-time slices as the data to be fed into the GRU network. Experimental results show that this model has higher accuracy than RNN, LSTM, GRU, Prophet, XGboost, and DARNN. Using mean absolute error (MAE) and symmetric mean absolute percentage error(SMAPE) to evaluate the experimental results, MAGRU's MAE, RMSE, and SMAPE decreased by 7.65%, 10.03%, and 8.87% over GRU-LSTM, the current best model for solving this type of problem.

• Journal of KIBIM
• /
• v.14 no.2
• /
• pp.1-12
• /
• 2024

The paper proposes a methodology that combines the Random Sample Consensus (RANSAC) algorithm and the Point Cloud Encoder-Decoder Network (PCEDNet) algorithm to automatically extract the length of infrastructure elements from point cloud data acquired through 3D LiDAR scans of retaining walls. This methodology is expected to significantly improve time and cost efficiency compared to traditional manual measurement techniques, which are crucial for the data-driven analysis required in the precision-demanding construction sector. Additionally, the extracted positional and dimensional data can contribute to enhanced accuracy and reliability in Scan-to-BIM processes. The results of this study are anticipated to provide important insights that could accelerate the digital transformation of the construction industry. This paper provides empirical data on how the integration of digital technologies can enhance efficiency and accuracy in the construction industry, and offers directions for future research and application.

• Journal of Broadcast Engineering
• /
• v.14 no.2
• /
• pp.144-153
• /
• 2009

Recently, as the necessity of a light-weighted video encoding technique has been rising for applications such as UCC(User Created Contents) or Multiview Video, Distributed Video Coding(DVC) where a decoder, not an encoder, performs the motion estimation/compensation taking most of computational complexity has been vigorously investigated. Wyner-Ziv coding reconstructs an image by eliminating the noise on side information which is decoder-side prediction of original image using channel code. Generally the side information of Wyner-Ziv coding is generated by using frame interpolation between key frames. The channel code such as Turbo code or LDPC code which shows a performance close to the Shannon's limit is employed. The noise model of Wyner-Ziv coding for channel decoding is called Virtual Channel Noise and is generally modeled by Laplacian or Gaussian distribution. In this paper, we propose a Wyner-Ziv coding method based on the frequency-adaptive channel noise modeling in transform domain. The experimental results with various sequences prove that the proposed method makes the channel noise model more accurate compared to the conventional scheme, resulting in improvement of the rate-distortion performance by up to 0.52dB.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.47 no.1
• /
• pp.20-27
• /
• 2010

This paper describes a design of 5-stage pipelined de-blocking filter with power reduction scheme and proposes a efficient memory architecture and filter order for high performance H.264/AVC Decoder. Generally the de-blocking filter removes block boundary artifacts and enhances image quality. Nevertheless filter has a few disadvantage that it requires a number of memory access and iterated operations because of filter operation for 4 time to one edge. So this paper proposes a optimized filter ordering and efficient hardware architecture for the reduction of memory access and total filter cycles. In proposed filter parallel processing is available because of structured 5-stage pipeline consisted of memory read, threshold decider, pre-calculation, filter operation and write back. Also it can reduce power consumption because it uses a clock gating scheme which disable unnecessary clock switching. Besides total number of filtering cycle is decreased by new filter order. The proposed filter is designed with Verilog-HDL and functionally verified with the whole H.264/AVC decoder using the Modelsim 6.2g simulator. Input vectors are QCIF images generated by JM9.4 standard encoder software. As a result of experiment, it shows that the filter can make about 20% total filter cycles reduction and it requires small transposition buffer size.