• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권11호
• /
• pp.4426-4442
• /
• 2020

Since scene segmentation is becoming a hot topic in the field of autonomous driving and medical image analysis, researchers are actively trying new methods to improve segmentation accuracy. At present, the main issues in image semantic segmentation are intra-class inconsistency and inter-class indistinction. From our analysis, the lack of global information as well as macroscopic discrimination on the object are the two main reasons. In this paper, we propose a Densely connected residual Attention network (DA-Res2Net) which consists of a dense residual network and channel attention guidance module to deal with these problems and improve the accuracy of image segmentation. Specifically, in order to make the extracted features equipped with stronger multi-scale characteristics, a densely connected residual network is proposed as a feature extractor. Furthermore, to improve the representativeness of each channel feature, we design a Channel-Attention-Guide module to make the model focusing on the high-level semantic features and low-level location features simultaneously. Experimental results show that the method achieves significant performance on various datasets. Compared to other state-of-the-art methods, the proposed method reaches the mean IOU accuracy of 83.2% on PASCAL VOC 2012 and 79.7% on Cityscapes dataset, respectively.

• 한국멀티미디어학회논문지
• /
• 제23권5호
• /
• pp.625-632
• /
• 2020

In the diagnosis of lung cancer, the tumor size is measured by the longest diameter of the tumor in the entire slice of the CT. In order to accurately estimate the size of the tumor, it is better to measure the volume, but there are some limitations in calculating the volume in the clinic. In this study, we propose an algorithm to segment lung cancer by applying a custom loss function that combines focal loss and dice loss to a U-Net model that shows high performance in segmentation problems in chest CT images. The combination of values of the various parameters in custom loss function was compared to the results of the model learned. The purposed loss function showed F1 score of 88.77%, precision of 87.31%, recall of 90.30% and average precision of 0.827 at α=0.25, γ=4, β=0.7. The performance of the proposed custom loss function showed good performance in lung cancer segmentation.

• 한국멀티미디어학회논문지
• /
• 제23권3호
• /
• pp.468-475
• /
• 2020

In this paper, we proposed a three-dimensional visualization system for medical images in augmented reality based on deep learning. In the proposed system, the artificial neural network model performed fully automatic segmentation of the region of lung and pulmonary nodule from chest CT images. After applying the three-dimensional volume rendering method to the segmented images, it was visualized in augmented reality devices. As a result of the experiment, when nodules were present in the region of lung, it could be easily distinguished with the naked eye. Also, the location and shape of the lesions were intuitively confirmed. The evaluation was accomplished by comparing automated segmentation results of the test dataset to the manual segmented image. Through the evaluation of the segmentation model, we obtained the region of lung DSC (Dice Similarity Coefficient) of 98.77%, precision of 98.45%, recall of 99.10%. And the region of pulmonary nodule DSC of 91.88%, precision of 93.05%, recall of 90.94%. If this proposed system will be applied in medical fields such as medical practice and medical education, it is expected that it can contribute to custom organ modeling, lesion analysis, and surgical education and training of patients.

• 로봇학회논문지
• /
• 제15권4호
• /
• pp.316-322
• /
• 2020

Endoscopic spine surgery is an advanced surgical technique for spinal surgery since it minimizes skin incision, muscle damage, and blood loss compared to open surgery. It requires, however, accurate positioning of an endoscope to avoid spinal nerves and to locate the endoscope near the target disk. Before the insertion of the endoscope, a guide needle is inserted to guide it. Also, the result of the surgery highly depends on the surgeons' experience and the patients' CT or MRI images. Thus, for the training, a number of haptic simulators for spinal needle insertion have been developed. But, still, it is difficult to be used in the medical field practically because previous studies require manual segmentation of vertebrae from CT images, and interaction force between the needle and soft tissue has not been considered carefully. This paper proposes AI-based automatic vertebrae CT-image segmentation and haptic rendering method using the proposed need-tissue interaction model. For the segmentation, U-net structure was implemented and the accuracy was 93% in pixel and 88% in IoU. The needle-tissue interaction model including puncture force and friction force was implemented for haptic rendering in the proposed spinal needle insertion simulator.

• 전자공학회논문지C
• /
• 제36C권9호
• /
• pp.66-75
• /
• 1999

영상분할은 입력된 영상을 처리하여 유사한 화소들의 집합인 영역들로 화소들을 구분하는 작업이다. 영상분할의 결과는 영상인식의 정확성에 큰 영향을 미친다. 본 논문에서는 유전자 알고리즘을 이용하여 마르코프 랜덤 필드(Markov random field)에 기반한 영상분할 방법을 제안한다. 제안한 방법에서는 잡음과 흔들림(blurring)에 강한 MRF를 이용하여 영상을 모델링 한다. HRF기반 영상분할 방법은 왜곡에 강한 반면, 정확한 파라미터의 추정이 요구된다. 그래서 , 추정방법으로 많은 파라미터를 포함하는 문제를 다루는데 효율적인 유전자 알고리즘을 사용한다. 실 영상을 가지고 수행된 실험 결과와 자동 차량 추출 시스템에의 응용결과는 제안된 방법의 효율성을 보여준다.

• Journal of Information Processing Systems
• /
• 제10권4호
• /
• pp.503-522
• /
• 2014

In the cursive handwriting recognition process, script trajectory segmentation and modeling represent an important task for large or open lexicon context that becomes more complicated in multi-writer applications. In this paper, we will present a developed system of Arabic online handwriting modeling based on graphemes segmentation and the extraction of its geometric features. The main contribution consists of adapting the Fourier descriptors to model the open trajectory of the segmented graphemes. To segment the trajectory of the handwriting, the system proceeds by first detecting its baseline by checking combined geometric and logic conditions. Then, the detected baseline is used as a topologic reference for the extraction of particular points that delimit the graphemes' trajectories. Each segmented grapheme is then represented by a set of relevant geometric features that include the vector of the Fourier descriptors for trajectory shape modeling, normalized metric parameters that model the grapheme dimensions, its position in respect to the baseline, and codes for the description of its associated diacritics.

• 한국정보통신학회논문지
• /
• 제25권12호
• /
• pp.1777-1783
• /
• 2021

대단위 신재생 에너지 발전단지의 효율적인 유지관리를 위해 드론의 활용이 점차 증가하고 있다. 오래전부터 태양광 패널을 드론으로 촬영하여 패널의 유실 및 오염 등을 관리하고 있다. 본 논문에서는 열화상카메라를 장착한 드론을 이용하여 획득된 태양광패널 이미지에서 아크, 단선, 크랙 등의 고장 유무를 판별하기 위해 시멘틱세그멘테이션 기법을 이용한 분류모델을 제안한다. 또한 적은 데이터셋으로도 강인한 분류 성능을 보이는 U-Net의 튜닝을 통해 효율적인 분류모델을 구현하였다.

• 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.

• 국제학술발표논문집
• /
• The 6th International Conference on Construction Engineering and Project Management
• /
• pp.496-500
• /
• 2015

International construction projects are inherently more risky than domestic projects with multi-dimensional uncertainties that require complementary risk management at both the country and project levels. However, despite a growing need for systematic country evaluations, most studies have focused on project-level decisions and lack country-based approaches for firms in the construction industry. Accordingly, this study suggests data-driven approaches for evaluating countries using two quantitative models. The first is a two-stage country segmentation model that not only screens negative countries based on country attractiveness (macro-segmentation) but also identifies promising countries based on the level of past project performance in a given country (micro-segmentation). The second is a multi-criteria country segmentation model that combines a firm's business objective with the country evaluation process based on Kraljic's matrix and fuzzy preference relations (FPR). These models utilize not only secondary data from internationally reputable institutions but also performance data on Korean firms from 1990 to 2014 to evaluate 29 countries. The proposed approaches enable firms to enhance their decision-making capacity for evaluating and selecting countries at the early stage of corporate strategy development.

• ETRI Journal
• /
• 제45권5호
• /
• pp.795-810
• /
• 2023

Unmanned aerial vehicles (UAV) and ground vehicles (UGV) require advanced video analytics for various tasks, such as moving object detection and segmentation; this has led to increasing demands for these methods. We propose a zero-shot video object segmentation method specifically designed for UAV and UGV applications that focuses on the discovery of moving objects in challenging scenarios. This method employs a background memory model that enables training from sparse annotations along the time axis, utilizing temporal modeling of the background to detect moving objects effectively. The proposed method addresses the limitations of the existing state-of-the-art methods for detecting salient objects within images, regardless of their movements. In particular, our method achieved mean J and F values of 82.7 and 81.2 on the DAVIS'16, respectively. We also conducted extensive ablation studies that highlighted the contributions of various input compositions and combinations of datasets used for training. In future developments, we will integrate the proposed method with additional systems, such as tracking and obstacle avoidance functionalities.