• 한국멀티미디어학회논문지
• /
• 제25권5호
• /
• pp.685-694
• /
• 2022

The goal of few-shot semantic segmentation is to build a network that quickly adapts to novel classes with extreme data shortage regimes. Most existing few-shot segmentation methods leverage single or multiple prototypes from extracted support features. Although there have been promising results for natural images, these methods are not directly applicable to the aerial image domain. A key factor in few-shot segmentation on aerial images is to effectively exploit information that is robust against extreme changes in background and object scales. In this paper, we propose a Mask-Guided Attention module to extract more comprehensive support features for few-shot segmentation in aerial images. Taking advantage of the support ground-truth masks, the area correlated to the foreground object is highlighted and enables the support encoder to extract comprehensive support features with contextual information. To facilitate reproducible studies of the task of few-shot semantic segmentation in aerial images, we further present the few-shot segmentation benchmark iSAID-, which is constructed from a large-scale iSAID dataset. Extensive experimental results including comparisons with the state-of-the-art methods and ablation studies demonstrate the effectiveness of the proposed method.

• Journal of the Korean Wood Science and Technology
• /
• 제50권6호
• /
• pp.490-498
• /
• 2022

The current study aimed to verify the image segmentation ability of rays in tangential thin sections of conifers using artificial intelligence technology. The applied model was Mask region-based convolutional neural network (Mask R-CNN) and softwoods (viz. Picea jezoensis, Larix gmelinii, Abies nephrolepis, Abies koreana, Ginkgo biloba, Taxus cuspidata, Cryptomeria japonica, Cedrus deodara, Pinus koraiensis) were selected for the study. To take digital pictures, thin sections of thickness 10-15 ㎛ were cut using a microtome, and then stained using a 1:1 mixture of 0.5% astra blue and 1% safranin. In the digital images, rays were selected as detection objects, and Computer Vision Annotation Tool was used to annotate the rays in the training images taken from the tangential sections of the woods. The performance of the Mask R-CNN applied to select rays was as high as 0.837 mean average precision and saving the time more than half of that required for Ground Truth. During the image analysis process, however, division of the rays into two or more rays occurred. This caused some errors in the measurement of the ray height. To improve the image processing algorithms, further work on combining the fragments of a ray into one ray segment, and increasing the precision of the boundary between rays and the neighboring tissues is required.

• 로봇학회논문지
• /
• 제16권4호
• /
• pp.306-312
• /
• 2021

This paper describes localization of autonomous underwater vehicles(AUV), which can be used when some navigation sensor data are an outlier. In that situation, localization through existing navigation algorithms causes problems in long-range localization. Even if an outlier sensor data occurs once, problems of localization will continue. Also, if outlier sensor data is related to azimuth (direction of AUV), it causes bigger problems. Therefore, a parallel localization module, in which different algorithms are performed in a normal and abnormal situation should be designed. Before designing a parallel localization module, it is necessary to study an effective method in the abnormal situation. So, we propose a localization method through machine learning. For this method, a learning model consists of only Fully-Connected and trains through randomly contaminated real sea data. The ground truth of training is displacement between subsequent GPS data. As a result, average error in localization through the learning model is 0.4 times smaller than the average error in localization through the existing navigation algorithm. Through this result, we conclude that it is suitable for a component of the parallel localization module.

• 한국제4기학회지
• /
• 제18권2호통권23호
• /
• pp.105-106
• /
• 2004

The NDVI(normalized difference vegetation index) dataset is unique or main tool to assess the global, multi seasonal, multi annual, and multi spectral changes over the World. These features are useful for environmental studies in particular, for the vegetation coverage monitoring of the country as Mongolia, where are large pastureland and pastoral animal husbandry, which dependent on natural conditions. Pasture vegetation cover is changing accordingly with both of global climate change and anthropogenic effect or human impacts. Using past 20 years (1982-2001) NDVI derived from NOAA satellite, its dynamical trend has been decreased in all natural zones differently. Also applied the method named "Two Years Differences" which could calculate the number of years with increased or decreased NDVI values at the same place. From May to September have occurred the 9 years maximum decreases of NDVI over Mongolia, but it obtained differently in spatial and temporal scale. In 24.4 ? 32.7% of all territory occurred one year decrease of NDVI and in 18% occurred more than 3 years frequent decrease of NDVI. According to the linear trend of NDVI and in 18% occurred more than 3 years frequent decrease of NDVI dynamics over 69% of whole territory of Mongolia NDVI values had been decreased due to both natural and human induced impacts to the pasture condition. In this paper also included some results of the integrated analyses of NOAA/NDVI and ground truth data over Monglia separately by natural zones.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2021년도 하계학술대회
• /
• pp.101-104
• /
• 2021

영상에 새로운 광원을 추가하거나 기존의 광원을 변경하여 영상 내 오브젝트들에 적용된 조명을 변경하는 것을 영상 기반 재조명이라 한다. 하지만, 영상에는 재조명을 위해 필요한 광원과 오브젝트들의 3차원 기하 정보가 부재하다는 문제가 있다. 이를 해결하기 위해, 본 연구에서는 영상으로부터 재조명에 필요한 요소들을 추정하는 접근법을 취한다. 오브젝트 표면의 노말과 알베도는 조명의 주 요소이지만 광원에는 독립적이므로 새로운 광원에 대한 재조명을 가능케 한다. 따라서 본 연구는 영상으로부터 노말맵과 알베도맵을 추정한 뒤, 이를 이용하여 영상 기반 렌더링하는 영상 재조명 방법을 제안한다. 조건부 적대적 생성망을 다양한 조명 환경에서 렌더링된 3차원 오브젝트 영상들과 그에 대응하는 노말맵, 알베도맵을 이용해 학습함으로써, 임의의 영상에 대한 노말맵과 알베도맵 추정기를 생성한다. 이를 통해 추정된 노말맵과 알베도맵은 3차원 공간상에서 새로운 광원에 대해 렌더링됨으로써 재조명 영상을 생성한다. 마지막으로, 영상 기반으로 재조명된 영상과 ground truth와의 비교 실험을 통해 본 연구에서 제안한 방법이 유효함을 확인한다.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2021년도 제64차 하계학술대회논문집 29권2호
• /
• pp.313-315
• /
• 2021

Timely and accurate diagnosis of lung diseases using Chest X-ray images has been gained much attention from the computer vision and medical imaging communities. Although previous studies have presented the capability of deep convolutional neural networks by achieving competitive binary classification results, their models were seemingly unreliable to effectively distinguish multiple disease groups using a large number of x-ray images. In this paper, we aim to build an advanced approach, so-called Ensemble Knowledge Distillation (EKD), to significantly boost the classification accuracies, compared to traditional KD methods by distilling knowledge from a cumbersome teacher model into an ensemble of lightweight student models with parallel branches trained with ground truth labels. Therefore, learning features at different branches of the student models could enable the network to learn diverse patterns and improve the qualify of final predictions through an ensemble learning solution. Although we observed that experiments on the well-established ChestX-ray14 dataset showed the classification improvements of traditional KD compared to the base transfer learning approach, the EKD performance would be expected to potentially enhance classification accuracy and model generalization, especially in situations of the imbalanced dataset and the interdependency of 14 weakly annotated thorax diseases.

• 대한의용생체공학회:의공학회지
• /
• 제44권5호
• /
• pp.354-361
• /
• 2023

Most of spinal diseases are diagnosed based on the subjective judgment of a specialist, so numerous studies have been conducted to find objectivity by automating the diagnosis process using deep learning. In this paper, we propose a method that combines segmentation and feature extraction, which are frequently used techniques for diagnosing spinal diseases. Four models, U-Net, U-Net++, DeepLabv3+, and M-Net were trained and compared using 1000 X-ray images, and key-points were derived using Douglas-Peucker algorithms. For evaluation, Dice Similarity Coefficient(DSC), Intersection over Union(IoU), precision, recall, and area under precision-recall curve evaluation metrics were used and U-Net++ showed the best performance in all metrics with an average DSC of 0.9724. For the average Euclidean distance between estimated key-points and ground truth, U-Net was the best, followed by U-Net++. However the difference in average distance was about 0.1 pixels, which is not significant. The results suggest that it is possible to extract key-points based on segmentation and that it can be used to accurately diagnose various spinal diseases, including spondylolisthesis, with consistent criteria.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권1호
• /
• pp.105-125
• /
• 2024

Gliomas are the most common malignant brain tumor and cause the most deaths. Manual brain tumor segmentation is expensive, time-consuming, error-prone, and dependent on the radiologist's expertise and experience. Manual brain tumor segmentation outcomes by different radiologists for the same patient may differ. Thus, more robust, and dependable methods are needed. Medical imaging researchers produced numerous semi-automatic and fully automatic brain tumor segmentation algorithms using ML pipelines and accurate (handcrafted feature-based, etc.) or data-driven strategies. Current methods use CNN or handmade features such symmetry analysis, alignment-based features analysis, or textural qualities. CNN approaches provide unsupervised features, while manual features model domain knowledge. Cascaded algorithms may outperform feature-based or data-driven like CNN methods. A revolutionary cascaded strategy is presented that intelligently supplies CNN with past information from handmade feature-based ML algorithms. Each patient receives manual ground truth and four MRI modalities (T1, T1c, T2, and FLAIR). Handcrafted characteristics and deep learning are used to segment brain tumors in a Global Convolutional Neural Network (GCNN). The proposed GCNN architecture with two parallel CNNs, CSPathways CNN (CSPCNN) and MRI Pathways CNN (MRIPCNN), segmented BraTS brain tumors with high accuracy. The proposed model achieved a Dice score of 87% higher than the state of the art. This research could improve brain tumor segmentation, helping clinicians diagnose and treat patients.

• Applied Microscopy
• /
• 제50권
• /
• pp.23.1-23.9
• /
• 2020

We propose an effective deep learning model to denoise scanning transmission electron microscopy (STEM) image series, named Noise2Atom, to map images from a source domain 𝓢 to a target domain 𝓒, where 𝓢 is for our noisy experimental dataset, and 𝓒 is for the desired clear atomic images. Noise2Atom uses two external networks to apply additional constraints from the domain knowledge. This model requires no signal prior, no noise model estimation, and no paired training images. The only assumption is that the inputs are acquired with identical experimental configurations. To evaluate the restoration performance of our model, as it is impossible to obtain ground truth for our experimental dataset, we propose consecutive structural similarity (CSS) for image quality assessment, based on the fact that the structures remain much the same as the previous frame(s) within small scan intervals. We demonstrate the superiority of our model by providing evaluation in terms of CSS and visual quality on different experimental datasets.

• 한국심리학회지 : 문화 및 사회문제
• /
• 제14권4호
• /
• pp.1-18
• /
• 2008

본 연구에서는 실체적 진실을 알지 못하는 상황에서 두 가지의 통계적인 방법을 이용하여 폴리그라프 검사의 정확도를 추정하였다. 한 가지는 대검찰청과 지방검찰청에서 2000년부터 2004년까지 범죄피의자를 대상으로 수행한 폴리그라프 검사와 검찰처분(기소여부)의 일치율을 이용하여 폴리그라프 검사의 정확도를 추정하였으며, 다른 한 가지는 대검찰청과 지방검찰청에서 2006년에 수행한 폴리그라프 검사결과와 검찰처분의 빈도분포를 가지고 잠재계층분석을 이용하여 정확도를 추정하였다. 판단불능으로 결정된 사례를 제외하고 산출한 일치율로 폴리그라프 검사의 정확도를 추정한 결과, 2000-2004년 자료의 경우는 정확도가 .914(SE=.004)로 산출되었으며, 2006년 자료의 경우는 정확도가 .885(SE=.021)인 것으로 산출되었다. 2006년 자료에 판단불능 사례를 포함한 후 잠재계층분석을 이용하여 폴리그라프 검사의 정확도를 추정한 결과, 정확도가 .707~.734(SE=.027~.031)인 것으로 산출되었으며, 오류긍정율과 오류부정율은 각각 .078~.087(SE=.019~.023)과 .029~.078(SE=.010~.023)으로 추정되었다. 거짓을 말하는 사람을 정확하게 판별할 확률은 .912~.925(SE=.013~.016)로 높게 나타났고, 진실을 말하는 사람을 정확하게 판별할 확률은 .867~.955(SE=.011~.040)이었다.