• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.10B
• /
• pp.1986-1994
• /
• 1999

In this paper, a semi-automatic approach is adopted to extract a semantic object from real-world video sequences human-aided segmentation for the first frame and automatic tracking for the remaining frames. The proposed algorithm has a hierarchical structure using watershed algorithm. Each hierarchy consists of 3 basic steps: First, seeds are extracted from the simplified current frame. Second, region growing bv a modified watershed algorithm is performed to get over-segmented regions. Finally, the segmented regions are classified into 3 categories, i.e., inside, outside or uncertain regions according to region probability values, which are acquired by the probability map calculated from an estimated motion-vector field. Then, for the remaining uncertain regions, the above 3 steps are repeated at lower hierarchies with less simplified frames until every region is classified into a certain region. The proposed algorithm provides prospective results in studio-quality sequences such as 'Claire', 'Miss America', 'Akiyo', and 'Mother and daughter'.

• Smart Structures and Systems
• /
• v.31 no.4
• /
• pp.325-334
• /
• 2023

Computer vision-based damage detection enables non-contact, efficient and low-cost bridge health monitoring, which reduces the need for labor-intensive manual inspection or that for a large number of on-site sensing instruments. By leveraging recent semantic segmentation approaches, we can detect regions of critical structural components and identify damages at pixel level on images. However, existing methods perform poorly when detecting small and thin damages (e.g., cracks); the problem is exacerbated by imbalanced samples. To this end, we incorporate domain knowledge to introduce a hierarchical semantic segmentation framework that imposes a hierarchical semantic relationship between component categories and damage types. For instance, certain types of concrete cracks are only present on bridge columns, and therefore the noncolumn region may be masked out when detecting such damages. In this way, the damage detection model focuses on extracting features from relevant structural components and avoid those from irrelevant regions. We also utilize multi-scale augmentation to preserve contextual information of each image, without losing the ability to handle small and/or thin damages. In addition, our framework employs an importance sampling, where images with rare components are sampled more often, to address sample imbalance. We evaluated our framework on a public synthetic dataset that consists of 2,000 railway bridges. Our framework achieves a 0.836 mean intersection over union (IoU) for structural component segmentation and a 0.483 mean IoU for damage segmentation. Our results have in total 5% and 18% improvements for the structural component segmentation and damage segmentation tasks, respectively, compared to the best-performing baseline model.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.792-799
• /
• 2022

Building Information Modeling (BIM) technology is a key component of modern construction engineering and project management workflows. As-is BIM models that represent the spatial reality of a project site can offer crucial information to stakeholders for construction progress monitoring, error checking, and building maintenance purposes. Geometric methods for automatically converting raw scan data into BIM models (Scan-to-BIM) often fail to make use of higher-level semantic information in the data. Whereas, semantic segmentation methods only output labels at the point level without creating object level models that is necessary for BIM. To address these issues, this research proposes a hybrid semantic-geometric approach for clutter-resistant floorplan generation from laser-scanned building point clouds. The input point clouds are first pre-processed by normalizing the coordinate system and removing outliers. Then, a semantic segmentation network based on PointNet++ is used to label each point as ceiling, floor, wall, door, stair, and clutter. The clutter points are removed whereas the wall, door, and stair points are used for 2D floorplan generation. A region-growing segmentation algorithm paired with geometric reasoning rules is applied to group the points together into individual building elements. Finally, a 2-fold Random Sample Consensus (RANSAC) algorithm is applied to parameterize the building elements into 2D lines which are used to create the output floorplan. The proposed method is evaluated using the metrics of precision, recall, Intersection-over-Union (IOU), Betti error, and warping error.

• Smart Structures and Systems
• /
• v.30 no.5
• /
• pp.501-511
• /
• 2022

Three-dimensional (3D) models have become crucial for improving civil infrastructure analysis, and they can be used for various purposes such as damage detection, risk estimation, resolving potential safety issues, alarm detection, and structural health monitoring. 3D point cloud data is used not only to make visual models but also to analyze the states of structures and to monitor them using semantic data. This study proposes automating the generation of high-quality 3D point cloud data and removing noise using deep learning algorithms. In this study, large-format aerial images of civilian infrastructure, such as cut slopes and dams, which were captured by drones, were used to develop a workflow for automatically generating a 3D point cloud model. Through image cropping, downscaling/upscaling, semantic segmentation, generation of segmentation masks, and implementation of region extraction algorithms, the generation of the point cloud was automated. Compared with the method wherein the point cloud model is generated from raw images, our method could effectively improve the quality of the model, remove noise, and reduce the processing time. The results showed that the size of the 3D point cloud model created using the proposed method was significantly reduced; the number of points was reduced by 20-50%, and distant points were recognized as noise. This method can be applied to the automatic generation of high-quality 3D point cloud models of civil infrastructures using aerial imagery.

• Korean Journal of Remote Sensing
• /
• v.34 no.4
• /
• pp.693-702
• /
• 2018

With the development of data analysis methods and data processing capabilities, semantic analysis of floorplans has been actively studied. Therefore, studies for extracting text information from drawings have been conducted for semantic analysis. However, existing research that separates rasterized text from floorplan has the problem of loss of text information, because when graphic and text components overlap, text information cannot be extracted. To solve this problem, this study defines the morphological characteristics of the text in the floorplan, and classifies the class of the corresponding region by applying the class of the SIFT key points through the SVM models. The algorithm developed in this study separated text components with a recall of 94.3% in five sample drawings.

• Korean Journal of Cognitive Science
• /
• v.13 no.1
• /
• pp.23-40
• /
• 2002

This study is to examine brain regions that are involved in picture encoding in normal adults using fMRI methods. In Scan 1, the picture encoding was studied during a semantic categorization task in comparison with word. In Scan 2 task type effects were studied both during a picture naming task and during a semantic categorization task with pictures. Subjects were asked to make decision either by pressing a mouse button (Scan 1) or by responding subvocally (naming or saying yes/no) (Scan 2). Regardless of stimulus type, left prefrontal, bilateral occipital, and parietal activations were observed during semantic processing in comparison with fixation baseline. Processing of word stimulus relative to picture resulted in activations in prefrontal and parieto-temporal regions in the left side while that of picture stimulus relative to word resultd in activations in bilateral extrastriatal visual cortices and parahippocampal regions. In spite of the same task demands, stimulus-specific information processings were involved and mediated by different neural substrates; the word encoding was associated with more semantic/lexical processings than pictures and the picture processing associated with more perceptual and novelty related information processings than word. Activations of dorsal part of inferior prefrontal region, i.e., Broca's areas were found both during the picture naming and during the semantic tasks subvocally performed Especially, during the picture naming task, greater occipital activations were found bilaterally relative to the semantic categorization task. indicating a possibility that greater and higher visual processing was involved in retrieving the name referred by picture stimuli.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10a
• /
• pp.301-303
• /
• 2001

현재 무선단말기 보급의 확대와 시간과 공간의 제약을 뛰어넘는 장점으로 무선 인터넷 환경이 급속도로 발전하고 있다. 그러나, 본 논문의 연구 분야인 모바일 지리정보 시스템(Mobile Geographic Information System)에서 무선인터넷을 통하여 실시간 지리 정보를 얻기 위해 사용자의 무선단말기와 서버 사이에 빈번한 데이터 송수신이 이뤄져야 하며 데이터의 빠른 변화를 수용해야 한다. 그러나, 아직 현저히 낮은 대역폭을 가진 채널을 통해 통신하며, 비싼 이용 요금과 오류로 인한 자발적 또는 비자발적 연결 끊김 현상 등은 서비스 제공에 한계를 가진다. 그러므로 본 논문에서는 이동 컴퓨팅 환경의 연구를 통해 연결 끊김 현상에서도 클라이언트의 지속적인 서비스 운영을 위한 비연결 연산으로 의미론적 캐시 기법과 캐시 교체 전략에 대해 알아보며, 본 논문에서는 Layer와 Region을 고려한 의미론적 캐싱 기법을 제안하여 무선 환경에서 동적인 지도서비스를 위한 기법을 제시하였다. 이 연구를 통해 아직 많은 한계를 지닌 무선인터넷 환경에서 지리정보뿐 아니라 위치기반의 다양한 서비스 분야에 응용될 수 있으리라 기대된다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.2C
• /
• pp.178-183
• /
• 2008

The videotext brings important semantic clues into video content analysis. In this paper, we propose an automatic binarization method of text region using a stroke filter. Proposed text binarization method consists of stroke filtering, text color polarity determination, and local region growing. By using the responses of dark and bright stroke filters, we can determine color polarity of text region automatically. And the method is robust against complex background, because it considers stroke information of videotexts by using a stroke filter. The effectiveness of our method is verified by experiments on a challenging database.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.9C
• /
• pp.834-839
• /
• 2007

The superimposed text in video brings important semantic clues into content analysis. In this paper, we present the new and fast superimposed text localization method in video segments. We detect the superimposed text by using temporal information contained in the video. To detect the superimposed text fast, we have minimized the candidate region of localizing superimposed texts by using the difference between consecutive frames. Experimental results are presented to demonstrate the good performance of the new superimposed text localization algorithm.

• Journal of Biomedical Engineering Research
• /
• v.10 no.3
• /
• pp.317-322
• /
• 1989

In this paper, brain CT images are automatically segmented to reconstruct the 3-D scene from consecutive CT sections. Contextual segmentation technique was applied to overcome the partial volume artifact and statistical fluctuation phenomenon of soft tissue images. Images are hierarchically analyzed by region growing and graph editing techniques. Segmented regions are discriptively decided to the final organs by using the semantic informations.