• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2010년 춘계학술발표회 논문집
• /
• pp.235-238
• /
• 2010

Since the mid 1990s airborne LiDAR data have been widely used, automation of building modeling is getting a central issue. LiDAR data processing for building modeling is involved with extracting surface patch elements by segmentation and surface fitting with optimal mathematical functions. In this study, simulation LiDAR data were generated with complex polyhedral roofs of buildings and an automatic modeling approach was proposed.

• 한국지반공학회논문집
• /
• 제37권11호
• /
• pp.107-118
• /
• 2021

Scan-to-BIM은 라이다(Light Detection And Ranging, LiDAR)로 구조물을 계측하고 이를 바탕으로 3D BIM(Building Information Modeling) 모델을 구축하는 방법으로 정밀한 모델링이 가능하지만 많은 인력과 시간, 비용이 소모된다는 한계를 가진다. 이러한 한계를 극복하기 위해 포인트 클라우드 데이터를 대상으로 딥러닝(Deep learning) 알고리즘을 적용하여 구조물의 객체 분할(Semantic segmentation)을 수행하는 연구들이 진행되고 있으나 학습 데이터에 따라 객체 분할 정확도가 어떻게 변화하는지에 대한 연구는 미흡한 실정이다. 본 연구에서는 딥러닝을 통한 철도 터널의 객체 분할에 학습 데이터를 구성하는 철도 터널의 크기, 선로 유형 등이 어떤 영향을 미치는지 확인하기 위해 매개변수 연구를 수행하였다. 매개변수 연구 결과, 학습과 테스트에 사용한 터널의 크기가 비슷할수록, 단선 터널보다는 복선 터널로 학습하는 경우에 더 높은 객체 분할 성능을 보였다. 또한, 학습 데이터를 두 가지 이상의 터널로 구성하면 전체 정확도(Overall Accuracy, OA)와 MIoU(Mean Intersection over Union)가 적게는 10%에서 많게는 50%가량 증가하였는데 이로부터 학습 데이터를 다양하게 구성하는 것이 효율적인 학습에 기여할 수 있음을 확인하였다.

• 대한의용생체공학회:의공학회지
• /
• 제29권5호
• /
• pp.348-354
• /
• 2008

Segmenting vessels in lower extremity CT images is very difficult because of gray level variation, connection to bones, and their small sizes. Instead of segmenting vessels, we propose an approach that segments bones and subtracts them from the original CT images. The subtracted images can contain not only connected vessel structures but also isolated vessels, which are very difficult to detect using conventional vessel segmentation methods. The proposed method initially grows a 3-dimensional (3D) volume with a seeded region growing (SRG) using an adaptive threshold and then detects junctions and forked branches. The forked branches are classified into either bone branches or vessel branches based on appearance, shape, size change, and moving velocity of the branch. The final volume is re-grown by collecting connected bone branches. The algorithm has produced promising results for segmenting bone structures in several tens of vessel-enhanced CT image data sets of lower extremities.

• 대한안전경영과학회지
• /
• 제7권1호
• /
• pp.199-210
• /
• 2005

Customer segmentation prediction has attracted a lot of research interests in previous literature, and recent studies have shown that artificial neural networks (ANN) method achieved better performance than traditional statistical ones. However, ANN approaches have suffered from difficulties with generalization, producing models that can overfit the data. This paper employs a relatively new machine learning technique, support vector machines (SVM), to the customer segmentation prediction problem in an attempt to provide a model with better explanatory power. To evaluate the prediction accuracy of SVM, we compare its performance with logistic regression analysis and ANN. The experiment results with real data of insurance company show that SVM superiors to them.

• ETRI Journal
• /
• 제29권5호
• /
• pp.641-648
• /
• 2007

In this study, we suggest a new segmentation algorithm for processing airborne laser point cloud data which is more memory efficient and faster than previous approaches. The main principle is the reading of data points along a scan line and their direct classification into homogeneous groups as a single process. The results of our experiments demonstrate that the algorithm runs faster and is more memory efficient than previous approaches. Moreover, the segmentation accuracy is generally acceptable.

• 전자공학회논문지S
• /
• 제34S권3호
• /
• pp.97-107
• /
• 1997

Image segmentation is teh important step in image infromation extraction for computer vison sytems. Fuzzy clustering methods have been used extensively in color image segmentation. Most analytic fuzzy clustering approaches are derived from the fuzzy c-means (FCM) algorithm. The FCM algorithm uses th eprobabilistic constraint that the memberships of a data point across classes sum to 1. However, the memberships resulting from the FCM do not always correspond to the intuitive concept of degree of belongingor compatibility. moreover, the FCM algorithm has considerable trouble above under noisy environments in the feature space. Recently, the possibilistic C-mean (PCM) for solving growing for color image segmentation. In the PCM, the membersip values may be interpreted as degrees of possibility of the data points belonging to the classes. So, the problems in the FCM can be solved by the PCM. The clustering results by just PCM are not smoothly bounded, and they often have holes. So, the region growing was used as a postprocessing. In our experiments, we illustrated that the proposed method is reasonable than the FCM in noisy enviironments.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권12호
• /
• pp.4763-4775
• /
• 2020

This research aims to develop a deep learning-based method that automatically detects and segments the defects on railroad surfaces to reduce the cost of visual inspection of the railroad. We developed our segmentation model by modifying a fully convolutional network model [1], a well-known segmentation model used for machine learning, to detect and segment railroad surface defects. The data used in this research are images of the railroad surface with one or more defect regions. Railroad images were cropped to a suitable size, considering the long height and relatively narrow width of the images. They were also normalized based on the variance and mean of the data images. Using these images, the suggested model was trained to segment the defect regions. The proposed method showed promising results in the segmentation of defects. We consider that the proposed method can facilitate decision-making about railroad maintenance, and potentially be applied for other analyses.

• International Journal of Internet, Broadcasting and Communication
• /
• 제15권1호
• /
• pp.269-274
• /
• 2023

In this paper, we proposed a new UNet 3+ model for medical image segmentation. The proposed ensemble(E) UNet 3+ model consists of UNet 3+s of varying depths into one unified architecture. UNet 3+s of varying depths have same encoder, but have their own decoders. They can bridge semantic gap between encoder and decoder nodes of UNet 3+. Deep supervision was used for learning on a total of 8 nodes of the E-UNet 3+ to improve performance. The proposed E-UNet 3+ model shows better segmentation results than those of the UNet 3+. As a result of the simulation, the E-UNet 3+ model using deep supervision was the best with loss function values of 0.8904 and 0.8562 for training and validation data. For the test data, the UNet 3+ model using deep supervision was the best with a value of 0.7406. Qualitative comparison of the simulation results shows the results of the proposed model are better than those of existing UNet 3+.

• 대한공간정보학회지
• /
• 제18권2호
• /
• pp.119-129
• /
• 2010

라이다데이터를 이용한 다양한 활용알고리즘이 개발되고 있지만, 대부분의 제안된 알고리즘은 정성적인 검증만이 수행되고 있다. 알고리즘의 객관적이고 정량적인 검증을 위해서는 대상에 대한 참값(true value)을 알아야 하지만, 라이다데이터는 데이터 특성상 참값을 알기 어렵다. 본 연구에서는 모의 라이다데이터는 분할 알고리즘의 성능을 평가할 수 있는 참값을 가지고 있다는 점에 착안하여, 모의 라이다데이터를 이용하여 분할 알고리즘의 성능을 보다 객관적/정량적으로 평가해보고자 하였다. 이를 위해 먼저, 1) 분할 알고리즘의 결과를 객관적으로 가늠할 수 있는 정량적인 평가요소들을 정의하고, 2) 3차원 도시모델을 입력 데이터로 모의 라이다데이터를 생성한 후, 3) 분할알고리즘을 적용하여 객체표면을 나타내는 평면패치를 생성하였다. 마지막으로 4) 성능평가지표를 기준으로 생성된 패치에 대한 분석을 자동화하여 수행하였다.

• 디지털산업정보학회논문지
• /
• 제11권4호
• /
• pp.89-97
• /
• 2015

In this paper, a method of color image segmentation based on DBSCAN(Density Based Spatial Clustering of Applications with Noise) using compactness of superpixels and texture information is presented. The DBSCAN algorithm can generate clusters in large data sets by looking at the local density of data samples, using only two input parameters which called minimum number of data and distance of neighborhood data. Superpixel algorithms group pixels into perceptually meaningful atomic regions, which can be used to replace the rigid structure of the pixel grid. Each superpixel is consist of pixels with similar features such as luminance, color, textures etc. Superpixels are more efficient than pixels in case of large scale image processing. In this paper, superpixels are generated by SLIC(simple linear iterative clustering) as known popular. Superpixel characteristics are described by compactness, uniformity, boundary precision and recall. The compactness is important features to depict superpixel characteristics. Each superpixel is represented by Lab color spaces, compactness and texture information. DBSCAN clustering method applied to these feature spaces to segment a color image. To evaluate the performance of the proposed method, computer simulation is carried out to several outdoor images. The experimental results show that the proposed algorithm can provide good segmentation results on various images.