• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.1-16
• /
• 2022

Despite recent breakthroughs in deep learning and computer vision fields, the pixel-wise identification of tiny objects in high-resolution images with complex disturbances remains challenging. This study proposes a modified U-net for tiny crack segmentation in real-world steel-box-girder bridges. The modified U-net adopts the common U-net framework and a novel Self-Attention-Self-Adaption (SASA) neuron as the fundamental computing element. The Self-Attention module applies softmax and gate operations to obtain the attention vector. It enables the neuron to focus on the most significant receptive fields when processing large-scale feature maps. The Self-Adaption module consists of a multiplayer perceptron subnet and achieves deeper feature extraction inside a single neuron. For data augmentation, a grid-based crack random elastic deformation (CRED) algorithm is designed to enrich the diversities and irregular shapes of distributed cracks. Grid-based uniform control nodes are first set on both input images and binary labels, random offsets are then employed on these control nodes, and bilinear interpolation is performed for the rest pixels. The proposed SASA neuron and CRED algorithm are simultaneously deployed to train the modified U-net. 200 raw images with a high resolution of 4928 × 3264 are collected, 160 for training and the rest 40 for the test. 512 × 512 patches are generated from the original images by a sliding window with an overlap of 256 as inputs. Results show that the average IoU between the recognized and ground-truth cracks reaches 0.409, which is 29.8% higher than the regular U-net. A five-fold cross-validation study is performed to verify that the proposed method is robust to different training and test images. Ablation experiments further demonstrate the effectiveness of the proposed SASA neuron and CRED algorithm. Promotions of the average IoU individually utilizing the SASA and CRED module add up to the final promotion of the full model, indicating that the SASA and CRED modules contribute to the different stages of model and data in the training process.

• Korean Journal of Radiology
• /
• v.22 no.3
• /
• pp.476-488
• /
• 2021

Objective: We aimed to develop a deep neural network for segmenting lung parenchyma with extensive pathological conditions on non-contrast chest computed tomography (CT) images. Materials and Methods: Thin-section non-contrast chest CT images from 203 patients (115 males, 88 females; age range, 31-89 years) between January 2017 and May 2017 were included in the study, of which 150 cases had extensive lung parenchymal disease involving more than 40% of the parenchymal area. Parenchymal diseases included interstitial lung disease (ILD), emphysema, nontuberculous mycobacterial lung disease, tuberculous destroyed lung, pneumonia, lung cancer, and other diseases. Five experienced radiologists manually drew the margin of the lungs, slice by slice, on CT images. The dataset used to develop the network consisted of 157 cases for training, 20 cases for development, and 26 cases for internal validation. Two-dimensional (2D) U-Net and three-dimensional (3D) U-Net models were used for the task. The network was trained to segment the lung parenchyma as a whole and segment the right and left lung separately. The University Hospitals of Geneva ILD dataset, which contained high-resolution CT images of ILD, was used for external validation. Results: The Dice similarity coefficients for internal validation were 99.6 ± 0.3% (2D U-Net whole lung model), 99.5 ± 0.3% (2D U-Net separate lung model), 99.4 ± 0.5% (3D U-Net whole lung model), and 99.4 ± 0.5% (3D U-Net separate lung model). The Dice similarity coefficients for the external validation dataset were 98.4 ± 1.0% (2D U-Net whole lung model) and 98.4 ± 1.0% (2D U-Net separate lung model). In 31 cases, where the extent of ILD was larger than 75% of the lung parenchymal area, the Dice similarity coefficients were 97.9 ± 1.3% (2D U-Net whole lung model) and 98.0 ± 1.2% (2D U-Net separate lung model). Conclusion: The deep neural network achieved excellent performance in automatically delineating the boundaries of lung parenchyma with extensive pathological conditions on non-contrast chest CT images.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.40 no.5
• /
• pp.535-546
• /
• 2020

Land cover maps are derived from satellite and aerial images by the Ministry of Environment for the entire Korea since 1998. Even with their wide application in many sectors, their usage in research community is limited. The main reason for this is the map compilation cycle varies too much over the different regions. The situation requires us a new and quicker methodology for generating land cover maps. This study was conducted to automatically generate land cover map using aerial ortho-images and Landsat 8 satellite images. The input aerial and Landsat 8 image data were trained by Residual U-Net, one of the deep learning-based segmentation techniques. Study was carried out by dividing three groups. First and second group include part of level-II (medium) categories and third uses group level-III (large) classification category defined in land cover map. In the first group, the results using all 7 classes showed 86.6 % of classification accuracy The other two groups, which include level-II class, showed 71 % of classification accuracy. Based on the results of the study, the deep learning-based research for generating automatic level-III classification was presented.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_2
• /
• pp.1709-1722
• /
• 2022

The rise in temperature induced by global warming caused in El Nino and La Nina, and abnormally changed the temperature of seawater. Rainfall concentrates in some locations due to abnormal variations in seawater temperature, causing frequent abnormal floods. It is important to rapidly detect flooded regions to recover and prevent human and property damage caused by floods. This is possible with synthetic aperture radar. This study aims to generate a model that directly derives flood-damaged areas by using modified U-NET and TerraSAR-X images based on Multi Kernel to reduce the effect of speckle noise through various characteristic map extraction and using two images before and after flooding as input data. To that purpose, two synthetic aperture radar (SAR) images were preprocessed to generate the model's input data, which was then applied to the modified U-NET structure to train the flood detection deep learning model. Through this method, the flood area could be detected at a high level with an average F1 score value of 0.966. This result is expected to contribute to the rapid recovery of flood-stricken areas and the derivation of flood-prevention measures.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_4
• /
• pp.1871-1877
• /
• 2022

In the past, satellite development required enormous budget and time, so only some developed countries possessed satellites. However, with the recent emergence of low-budget satellites such as micro-satellites, many countries around the world are participating in satellite development. Low-orbit and geostationary-orbit satellites are used in various fields such as environment and weather monitoring, precise change detection, and disasters. Recently, it has been actively used for monitoring through deep learning-based object-of-interest detection. Until now, Korea has developed satellites for national demand according to the space development plan, and the satellite image obtained through this is used for various purpose in the public and private sectors. Interest in satellite image is continuously increasing in Korea, and various contests are being held to discover ideas for satellite image application and promote technology development. In this special issue, we would like to introduce the topics that participated in the recently held 2022 Satellite Information Application Contest and research on the processing and utilization of KOMPSAT image data.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.5
• /
• pp.1-9
• /
• 2020

In this paper, we propose a model that performs more natural facial attribute editing by utilizing mask information in the hair and hat region. STGAN, one of state-of-the-art research of facial attribute editing, has shown results of naturally editing multiple facial attributes. However, editing hair-related attributes can produce unnatural results. The key idea of the proposed method is to additionally utilize information on the face regions that was lacking in the existing model. To do this, we apply three ideas. First, hair information is supplemented by adding hair ratio attributes through masks. Second, unnecessary changes in the image are suppressed by adding cycle consistency loss. Third, a hat segmentation network is added to prevent hat region distortion. Through qualitative evaluation, the effectiveness of the proposed method is evaluated and analyzed. The method proposed in the experimental results generated hair and face regions more naturally and successfully prevented the distortion of the hat region.

• Journal of Korea Multimedia Society
• /
• v.22 no.5
• /
• pp.535-546
• /
• 2019

Recently, there have been a lot of researches on the whole face replacement system, but it is not easy to obtain stable results due to various attitudes, angles and facial diversity. To produce a natural synthesis result when replacing the face shown in the video image, technologies such as face area detection, feature extraction, face alignment, face area segmentation, 3D attitude adjustment and facial transposition should all operate at a precise level. And each technology must be able to be interdependently combined. The results of our analysis show that the difficulty of implementing the technology and contribution to the system in facial replacement technology has increased in facial feature point extraction and facial alignment technology. On the other hand, the difficulty of the facial transposition technique and the three-dimensional posture adjustment technique were low, but showed the need for development. In this paper, we propose four facial replacement models such as 2-D Faceswap, OpenPose, Deekfake, and Cycle GAN, which are suitable for the Cox platform. These models have the following features; i.e. these models include a suitable model for front face pose image conversion, face pose image with active body movement, and face movement with right and left side by 15 degrees, Generative Adversarial Network.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.1
• /
• pp.111-118
• /
• 2022

In computer vision research, the two-dimensional human pose is a very extensive research direction, especially in pose tracking and behavior recognition, which has very important research significance. The acquisition of human pose targets, which is essentially the study of how to accurately identify human targets from pictures, is of great research significance and has been a hot research topic of great interest in recent years. Human pose recognition is used in artificial intelligence on the one hand and in daily life on the other. The excellent effect of pose recognition is mainly determined by the success rate and the accuracy of the recognition process, so it reflects the importance of human pose recognition in terms of recognition rate. In this human body gesture recognition, the human body is divided into 17 key points for labeling. Not only that but also the key points are segmented to ensure the accuracy of the labeling information. In the recognition design, use the comprehensive data set MS COCO for deep learning to design a neural network model to train a large number of samples, from simple step-by-step to efficient training, so that a good accuracy rate can be obtained.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.2-2
• /
• 2023

기후변화가 가속화로 인해 수재해의 빈도와 강도 예측이 어려워짐에 따라 실시간 홍수 모니터링에 대한 수요가 증가하고 있다. 합성개구레이다는 광원과 날씨에 무관하게 촬영이 가능하여 수재해 발생시에도 영상을 확보할 수 있다. 합성개구레이다를 활용한 수체 탐지 알고리즘 개발이 활발히 연구되어 왔고, 딥러닝의 발달로 CNN을 활용하여 높은 정확도로 수체 탐지가 기능해졌다. 하지만, CNN 기반 수체 탐지 모델은 훈련시 높은 정량적 정확성 지표를 달성하여도 추론 후 정성적 평가시 경계와 소하천에 대한 탐지 정확성이 떨어진다. 홍수 모니터링에서 특히 중요한 정보인 경계와 좁은 하천에 대해서 정확성이 떨어짐에 따라 실생활 적용이 어렵다. 이에 경계를 강화한 적대적 학습 기반의 수체 탐지 모델을 개발하여 더 세밀하고 정확하게 탐지하고자 한다. 적대적 학습은 생성적 적대 신경망(GAN)의 두 개의 모델인 생성자와 판별자가 서로 관여하며 더 높은 정확도를 달성할 수 있도록 학습이다. 이러한 적대적 학습 개념을 수체 탐지 모델에 처음으로 도입하여, 생성자는 실제 라벨 데이터와 유사하게 수체 경계와 소하천까지 탐지하고자 학습한다. 반면 판별자는 경계 거리 변환 맵과 합성개구레이다 영상을 기반으로 라벨데이터와 수체 탐지 결과를 구분한다. 경계가 강화될 수 있도록, 면적과 경계를 모두 고려할 수 있는 손실함수 조합을 구성하였다. 제안 모델이 경계와 소하천을 정확히 탐지하는지 판단하기 위해, 정량적 지표로 F1-score를 사용하였으며, 육안 판독을 통해 정성적 평가도 진행하였다. 기존 U-Net 모델이 탐지하지 못하던 영역에 대해 제안한 경계 강화 적대적 수체 탐지 모델이 수체의 세밀한 부분까지 탐지할 수 있음을 증명하였다.

• Smart Media Journal
• /
• v.12 no.9
• /
• pp.28-37
• /
• 2023

The main factor affecting the decline in rice yield is damage caused by localized heavy rains or typhoons. The method of analyzing the rice lodging area is difficult to obtain objective results based on visual inspection and judgment based on field surveys visiting the affected area. it requires a lot of time and money. In this paper, we propose the method of estimation and diagnosis for rice lodging areas using a Vision Transformer-based Segformer for RGB images, which are captured by unmanned aerial vehicles. The proposed method estimates the lodging, normal, and background area using the Segformer model, and the lodging rate is diagnosed through the rice field inspection criteria in the seed industry Act. The diagnosis result can be used to find the distribution of the rice lodging areas, to show the trend of lodging, and to use the quality management of certified seed in government. The proposed method of rice lodging area estimation shows 98.33% of mean accuracy and 96.79% of mIoU.