• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2019년도 춘계학술발표대회
• /
• pp.515-518
• /
• 2019

Semantic segmentation has remained as a challenging problem in the field of computer vision. Given the immense power of Convolution Neural Network (CNN) models, many complex problems have been solved in computer vision. Semantic segmentation is the challenge of classifying several pixels of an image into one category. With the help of convolution neural networks, we have witnessed prolific results over the time. We propose a convolutional neural network model which uses Fully CNN with deconvolutional pixel layers. The goal is to create a hierarchy of features while the fully convolutional model does the primary learning and later deconvolutional model visually segments the target image. The proposed approach creates a direct link among the several adjacent pixels in the resulting feature maps. It also preserves the spatial features such as corners and edges in images and hence adding more accuracy to the resulting outputs. We test our algorithm on Karlsruhe Institute of Technology and Toyota Technologies Institute (KITTI) street view data set. Our method achieves an mIoU accuracy of 92.04 %.

• 대한원격탐사학회지
• /
• 제19권2호
• /
• pp.149-157
• /
• 2003

본 연구에서는 향후 지속적으로 제공되어질 고해상도 위성영상의 효율적인 대체 센서모델링을 위하여 SPOT-3호의 위성영상으로부터 대상영역에 영상분할을 실시하고 분할된 영상으로부터 분모항이 없는 RFM 즉, 3차 다항식 모델의 적용성을 고찰하였다. 대상영역 전체에 적용한 분모항이 있는 기존 RFM의 적합도와 비교한 결과, 평면오차는 3차 다항식 모델링 방법이 0.8m 정도 낮게 산출된 반면 표고오차는 기존의 RFM이 1.0m 정도 낮게 산출되었다.

• 한국의학물리학회지:의학물리
• /
• 제32권4호
• /
• pp.172-178
• /
• 2021

Purpose: This study aimed to develop a deep learning architecture combining two task models to generate synthetic computed tomography (sCT) images from low-tesla magnetic resonance (MR) images to improve metallic marker visibility. Methods: Twenty-three patients with cervical cancer treated with intracavitary radiotherapy (ICR) were retrospectively enrolled, and images were acquired using both a computed tomography (CT) scanner and a low-tesla MR machine. The CT images were aligned to the corresponding MR images using a deformable registration, and the metallic dummy source markers were delineated using threshold-based segmentation followed by manual modification. The deformed CT (dCT), MR, and segmentation mask pairs were used for training and testing. The sCT generation model has a cascaded three-dimensional (3D) U-Net-based architecture that converts MR images to CT images and segments the metallic marker. The performance of the model was evaluated with intensity-based comparison metrics. Results: The proposed model with segmentation loss outperformed the 3D U-Net in terms of errors between the sCT and dCT. The structural similarity score difference was not significant. Conclusions: Our study shows the two-task-based deep learning models for generating the sCT images using low-tesla MR images for 3D ICR. This approach will be useful to the MR-only workflow in high-dose-rate brachytherapy.

• 방송공학회논문지
• /
• 제3권1호
• /
• pp.50-60
• /
• 1998

본 논문에서는 콤팩트한 동영상 표현과 객체기반의 generic한 동영상압축을 위한 파라미터릭 움직임 모델의 파라미터 추정과 세그맨테이션 기법에 관해서 기술한다. 동영상의 optical flow와 같은 국소적 움직임 정보와 파라미터 움직임 모델의 특징을 이용해서 영상의 콤팩트한 구조적 표현을 추출하기 위해, 본 논문에서는 2 스템의 과정 즉, 초기영역을 추출하는 과정과, 파라미터릭 움직임 파라미터의 추정과 세그맨테이션을 동시에 수행하는 과정으로 구성된 새로운 알고리즘을 제안한다. 혼합 모델이 ML 추정에 의거한 확률적 클러스터링에 의해 움직임 물체의 움직임과 형상을 반영한 초기영역을 추출하고, 파라미터릭 움직임 모델을 사용해서 각각의 초기 영역마다 움직임 파라미터를 추정하고 세그맨테이션을 수행한다. 또한, CIF 표준 동영상을 사용한 모의 실험을 통해 본 제안 알고리즘의 유효성을 평가한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권12호
• /
• pp.3180-3199
• /
• 2013

While non-predefined object segmentation (NDOS) distinguishes an arbitrary self-assumed object from its background, predefined object segmentation (DOS) pre-specifies the target object. In this paper, a new and novel method to segment predefined objects is presented, by globally optimizing an orientation-based objective function that measures the fitness of the object boundary, in a discretized parameter space. A specific object is explicitly described by normalized discrete sets of boundary points and corresponding normal vectors with respect to its plane shape. The orientation factor provides robust distinctness for target objects. By considering the order of transformation elements, and their dependency on the derived over-segmentation outcome, the domain of translations and scales is efficiently discretized. A branch and bound algorithm is used to determine the transformation parameters of a shape model corresponding to a target object in an image. The results tested on the PASCAL dataset show a considerable achievement in solving complex backgrounds and unclear boundary images.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권8호
• /
• pp.1843-1859
• /
• 2013

The continuous increase of the spatial resolution of remote sensing images brings great challenge to image analysis and processing. Traditional prior knowledge-based region detection and target recognition algorithms for processing high resolution remote sensing images generally employ a global searching solution, which results in prohibitive computational complexity. In this paper, a more efficient region of interest (ROI) detection algorithm based on visual attention and threshold segmentation (VA-TS) is proposed, wherein a visual attention mechanism is used to eliminate image segmentation and feature detection to the entire image. The input image is subsampled to decrease the amount of data and the discrete moment transform (DMT) feature is extracted to provide a finer description of the edges. The feature maps are combined with weights according to the amount of the "strong points" and the "salient points". A threshold segmentation strategy is employed to obtain more accurate region of interest shape information with the very low computational complexity. Experimental statistics have shown that the proposed algorithm is computational efficient and provide more visually accurate detection results. The calculation time is only about 0.7% of the traditional Itti's model.

• 한국통신학회논문지
• /
• 제27권3A호
• /
• pp.221-230
• /
• 2002

본 논문에서는 마코프 랜덤 필드를 이용해 움직이는 객체를 분할하는 새로운 방법을 제안하였다. 제안된 방법은 신호 탐지 이론에 기반을 두고 있다. 즉, 영상에서의 모션의 존재 유무는 binary decision rule에 의해 결정되고 잘못된 결정은 마코프 랜덤 필드 모델에 의해 수정된다. 전체적인 분할 과정은 2단계로 나뉘어진다. 첫 단계는 '모션탐지' 단계이며, 두번째 단계는 '객체분할' 단계이다. '모션탐지' 단계에서는 optical flow에 의해 발생하는 속도 벡터들에 대하여 binary decision rule을 적용하여 모tus의 존재 유무를 결정하는 과정이다. '객체분할' 단계에서는 첫 단계에서 원치 않게 발생하는 잡음을 제거한다. 이때 마코프 랜덤 필드로 가정하고 베이스 규칙에 의해 잡음을 제거한다. 실험결과, 연속영상에서 움직이는 객체의 영역을 효율적으로 분할함을 확인할 수 있었다.

• 정보과학회 논문지
• /
• 제43권7호
• /
• pp.812-819
• /
• 2016

본 논문에서는 기존의 영상분할에서 발생하는 초기값 배정문제와 영상분할 가능여부를 확인할 수 있는 방법에 대한 이론적 근거를 분석하고 제시한다. 본 논문의 앞 부분에서는 위상수학의 이론에 근거한 수학적 논증을 바탕으로 적절한 초기값 배정의 대한 위상적 근거와 방법론을 제시한다. 이어서 위상수학의 분리공리 이론에 근거하여 영상이 영역 분할되기 위한 최소의 위상조건을 확인하고 해당 조건을 이용하여 영상분할을 위해 사용된 모델의 유효성을 검증하는 방법론을 제시한다. 즉, 본 논문은 기존의 통계적 분석과 달리, 위상적 분석을 통해 영상 영역 분할의 수학적 근거를 제시한 것에 그 특징이 있다. 마지막으로 기존의 가우시안 랜덤 필드 모델 기반 영상 분할에 본 논문에서 제시한 이론과 방법론을 적용하여 가우시안 랜덤 필드 모델의 유효성을 확인한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권2호
• /
• pp.945-961
• /
• 2019

Tongue diagnosis is one of the most important diagnostic methods in Traditional Chinese Medicine (TCM). Tongue image segmentation aims to extract the image object (i.e., tongue body), which plays a key role in the process of manufacturing an automated tongue diagnosis system. It is still challenging, because there exists the personal diversity in tongue appearances such as size, shape, and color. This paper proposes an innovative segmentation method that uses image thresholding, gray projection and active contour model (ACM). Specifically, an initial object region is first extracted by performing image thresholding in HSI (i.e., Hue Saturation Intensity) color space, and subsequent morphological operations. Then, a gray projection technique is used to determine the upper bound of the tongue body root for refining the initial object region. Finally, the contour of the refined object region is smoothed by ACM. Experimental results on a dataset composed of 100 color tongue images showed that the proposed method obtained more accurate segmentation results than other available state-of-the-art methods.

• 대한원격탐사학회지
• /
• 제37권1호
• /
• pp.111-122
• /
• 2021

Building footprint extraction is an active topic in the domain of remote sensing, since buildings are a fundamental unit of urban areas. Deep convolutional neural networks successfully perform footprint extraction from optical satellite images. However, semantic segmentation produces coarse results in the output, such as blurred and rounded boundaries, which are caused by the use of convolutional layers with large receptive fields and pooling layers. The objective of this study is to generate visually enhanced building objects by directly extracting the vertices of individual buildings by combining instance segmentation and keypoint detection. The target keypoints in building extraction are defined as points of interest based on the local image gradient direction, that is, the vertices of a building polygon. The proposed framework follows a two-stage, top-down approach that is divided into object detection and keypoint estimation. Keypoints between instances are distinguished by merging the rough segmentation masks and the local features of regions of interest. A building polygon is created by grouping the predicted keypoints through a simple geometric method. Our model achieved an F1-score of 0.650 with an mIoU of 62.6 for building footprint extraction using the OpenCitesAI dataset. The results demonstrated that the proposed framework using keypoint estimation exhibited better segmentation performance when compared with Mask R-CNN in terms of both qualitative and quantitative results.