• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.195-206
• /
• 2022

Crack detection is essential for inspection of existing structures and crack segmentation based on deep learning is a significant solution. However, datasets are usually one of the key issues. When building a new dataset for deep learning, laborious and time-consuming annotation of a large number of crack images is an obstacle. The aim of this study is to develop an approach that can automatically select a small portion of the most informative crack images from a large pool in order to annotate them, not to label all crack images. An active learning method with difficulty learning mechanism for crack segmentation tasks is proposed. Experiments are carried out on a crack image dataset of a steel box girder, which contains 500 images of 320×320 size for training, 100 for validation, and 190 for testing. In active learning experiments, the 500 images for training are acted as unlabeled image. The acquisition function in our method is compared with traditional acquisition functions, i.e., Query-By-Committee (QBC), Entropy, and Core-set. Further, comparisons are made on four common segmentation networks: U-Net, DeepLabV3, Feature Pyramid Network (FPN), and PSPNet. The results show that when training occurs with 200 (40%) of the most informative crack images that are selected by our method, the four segmentation networks can achieve 92%-95% of the obtained performance when training takes place with 500 (100%) crack images. The acquisition function in our method shows more accurate measurements of informativeness for unlabeled crack images compared to the four traditional acquisition functions at most active learning stages. Our method can select the most informative images for annotation from many unlabeled crack images automatically and accurately. Additionally, the dataset built after selecting 40% of all crack images can support crack segmentation networks that perform more than 92% when all the images are used.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.04a
• /
• pp.787-790
• /
• 2002

의미 기반 영상 검색은 Color, Texture, Region 정보, Spatial Color Distribution등의 저차원 특징 정보와 이미지 데이터에 의미를 부여하기 위해 주서 처리하는 것이 일반적이다. 그리고 부여된 키워드나 시소러스와 같은 어휘 사전을 이용하여 의미기반 정보검색을 수행하고 있지만, 기존의 키워드기반 텍스트 정보검색의 한계를 벗어나지 못하는 문제를 야기 시킨다. 이에 본 논문에서는 시각 데이터에 존재하는 객체들과 그 객체 사이의 개념관계를 Ontology의 한 형태인 WordNet을 이용하여 의미 정보로 표현할 수 있도록 한다. 이를 활용하면 영상 데이터의 자동 주석 시스템이나 검색 시스템에서 인간이 인식하는 개념적인 사고방식에 더욱 접근할 수 있는 결과물을 얻을 수 있을 것이다.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2005.11a
• /
• pp.331-337
• /
• 2005

현재 인터넷과 멀티미디어 데이터배이스 상에서 부딪치는 검색 문제의 해결 방안으로서 명시적 배경지식의 사용을 지향하는 시맨틱 웹과 새로운 표준 기술 등은 이미지 데이터에 대한 배경 지식을 규정하는 구문론 등을 지원한다. 따라서 본 연구에서는 이미지의 주제(양)에 대한 배경지식을 표현한 도메인 온톨로지를 이용하여 사용자에게 검색어의 정확한 선택이 이루어지도록 제공하고 이미지의 내용과 기술 특정에 대한 시맨틱 주석을 이용하여 검색 용어의 일반화와 다의어, 이미지 대상물의 행위와 같은 고수준의 메타데이터 스키마를 제공함으로써 이미지의 검색에 있어 내용에 기반한 시맨틱 주석과 도메인 온톨로지의 구현과 검색 방법을 제안하고자 한다.

• KIISE Transactions on Computing Practices
• /
• v.22 no.6
• /
• pp.290-295
• /
• 2016

Recently, folksonomy-based image-sharing sites where users cooperatively make and utilize tags of image annotation have been gaining popularity. Typically, these sites retrieve images for a user request using simple text-based matching and display retrieved images in the form of photo stream. However, these tags are personal and subjective and images are not categorized, which results in poor retrieval accuracy and low user satisfaction. In this paper, we propose a categorization scheme for folksonomy images which can improve the retrieval accuracy in the tag-based image retrieval systems. Consequently, images are classified by the semantic similarity using text-information and image-information generated on the folksonomy. To evaluate the performance of our proposed scheme, we collect folksonomy images and categorize them using text features and image features. And then, we compare its retrieval accuracy with that of existing systems.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.2
• /
• pp.95-111
• /
• 2021

As the population decreases in an aging society, the average age of drivers increases. Accordingly, the elderly at high risk of being in an accident need autonomous-driving vehicles. In order to secure driving safety on the road, several technologies to respond to various obstacles are required in those vehicles. Among them, technology is required to recognize static obstacles, such as poor road conditions, as well as dynamic obstacles, such as vehicles, bicycles, and people, that may be encountered while driving. In this study, we propose a deep neural network algorithm capable of simultaneously detecting these two types of obstacle. For this algorithm, we used 1,418 road images and produced annotation data that marks seven categories of dynamic obstacles and labels images to indicate road damage. As a result of training, dynamic obstacles were detected with an average accuracy of 46.22%, and road surface damage was detected with a mean intersection over union of 74.71%. In addition, the average elapsed time required to process a single image is 89ms, and this algorithm is suitable for personal mobility vehicles that are slower than ordinary vehicles. In the future, it is expected that driving safety with personal mobility vehicles will be improved by utilizing technology that detects road obstacles.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_3
• /
• pp.1679-1692
• /
• 2023

South Korea is a country that emits a large amount of pollutants as a result of population growth and industrial development and is also severely affected by transboundary air pollution due to its geographical location. As pollutants from both domestic and foreign sources contribute to air pollution in Korea, the location of air pollutant emission sources is crucial for understanding the movement and distribution of pollutants in the atmosphere and establishing national-level air pollution management and response strategies. Based on this background, this study aims to effectively acquire spatial information on domestic and international air pollutant emission sources, which is essential for analyzing air pollution status, by utilizing high-resolution optical satellite images and deep learning-based image segmentation models. In particular, industrial parks and quarries, which have been evaluated as contributing significantly to transboundary air pollution, were selected as the main research subjects, and images of these areas from multi-purpose satellites 3 and 3A were collected, preprocessed, and converted into input and label data for model training. As a result of training the U-Net model using this data, the overall accuracy of 0.8484 and mean Intersection over Union (mIoU) of 0.6490 were achieved, and the predicted maps showed significant results in extracting object boundaries more accurately than the label data created by course annotations.