• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.12
• /
• pp.1919-1925
• /
• 2022

In this paper, we propose an image-to-image translation approach based on the conditional generative adversarial network for semantic segmentation. Semantic segmentation is the task of clustering parts of an image together which belong to the same object class. Unlike the traditional pixel-wise classification approach, the proposed method parses an input RGB image to its corresponding semantic segmentation mask using a pixel regression approach. The proposed method is based on the Pix2Pix image synthesis method. We employ residual connections-based convolutional neural network architectures for both the generator and discriminator architectures, as the residual connections speed up the training process and generate more accurate results. The proposed method has been trained and tested on the NYU-depthV2 dataset and could achieve a good mIOU value (49.5%). We also compare the proposed approach to the current methods in semantic segmentation showing that the proposed method outperforms most of those methods.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10a
• /
• pp.269-271
• /
• 2000

이동 컴퓨팅 환경은 분산 컴퓨팅 환경과는 달리 네트웍의 낮은 신뢰성과 제한된 대역폭을 가지고, 이동 호스트 또한 제한된 저장장치와 배터리만을 사용할 수 있으며 트랜잭션(transaction)은 장시간에 결쳐 수행되는 특성을 가진다. 이동 컴퓨팅 환경에서는 전통적인 트랜잭션의 동시성 제어 기법 대신, 트랜잭션의 시맨틱스(semantics)를 이용하여 동시성을 향상시킬 수 있다. 본 연구에서는 중첩된 트랜잭션의 구조를 단순화시킨 단계분할(step- decomposition) 기법을 사용하여, 서브트랜잭션(sub-transaction)의 시맨틱 타입(semantic type) 별로 인터리빙(interleaving)을 제어함으로써 트랜잭션의 동시성을 향상시키는 기법을 제안하고자 한다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.4
• /
• pp.34-40
• /
• 2018

This paper presents a new method to estimate the pose of a moving object accurately using a monocular camera and a low-end GPS+IMU sensor system. For this goal, we adopted a deep neural network for the semantic segmentation of input images and compared the results with a semantic map of a neighborhood. In this map matching, we use weight tables to deal with label inconsistency effectively. Signals from a low-end GPS+IMU sensor system are used to limit search spaces and minimize the proposed function. For the evaluation, we added noise to the signals from a high-end GPS-IMU system. The results show that the pose can be recovered from the noisy signals. We also show that the proposed method is effective in handling non-open-sky situations.

• Korean Chemical Engineering Research
• /
• v.57 no.2
• /
• pp.274-282
• /
• 2019

In recent years, big data analysis has been expanded to include automatic control through reinforcement learning as well as prediction through modeling. Research on the utilization of image data is actively carried out in various industrial fields such as chemical, manufacturing, agriculture, and bio-industry. In this paper, we applied NASNet, which is an AutoML reinforced learning algorithm, to DeepU-Net neural network that modified U-Net to improve image semantic segmentation performance. We used BRATS2015 MRI data for performance verification. Simulation results show that DeepU-Net has more performance than the U-Net neural network. In order to improve the image segmentation performance, remove dropouts that are typically applied to neural networks, when the number of kernels and filters obtained through reinforcement learning in DeepU-Net was selected as a hyperparameter of neural network. The results show that the training accuracy is 0.5% and the verification accuracy is 0.3% better than DeepU-Net. The results of this study can be applied to various fields such as MRI brain imaging diagnosis, thermal imaging camera abnormality diagnosis, Nondestructive inspection diagnosis, chemical leakage monitoring, and monitoring forest fire through CCTV.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07b
• /
• pp.223-225
• /
• 2005

시맨틱 웹의 구현을 위한 수단으로 RDF 및 기타 기반 기술이 사용되고 있다. 이에 따라, 방대한 RDF 데이터의 효율적인 관리를 위한 연구들이 최근 활발하게 국내외에서 진행 중이다. 기존의 많은 연구들은 관계형 데이터베이스 시스템을 이용하여 트리플 형태의 RDF 데이터의 저장하는 방법을 제안하였다. 이러한 방법은 하나의 대규모 테이블상에 RDF 데이터를 저장하므로 데이터 관리측면에서 장점이 있으나 질의 처리 측면에서 볼 때 항상 테이블 전체를 접근해야 하므로 검색 성능이 저하될 수 있는 문제점이 있다. 본 논문에서는 질의 처리 성능을 높이기 위해 프로퍼티를 기반으로 RDF 데이터를 절러 개의 테이블로 분할 저장하는 기법을 제안한다.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.5
• /
• pp.1-11
• /
• 2010

The success of semantic web depends largely on the semantic annotation which systematizes knowledge for the construction and production of ontology. Therefore, the efficiency of semantic annotation is very important in order to change many knowledge expressions and generate into ontology instances. In this paper, we presents a generation system of rule-based ontology instances which are produced accurately and efficiently via semantic annotation in conventional web sites. In conventional studies, the manual process is necessary for finding relevant information, comparing it with ontology, and entering information. We propose a new method that manages keyword data regarding extracted information and rule information separately. Thus, it is quite practical to extract information efficiently from various web documents by adding a small number of keywords and rules. The proposed method shows the possibility of ontology instance generation which reuses the rules and keywords from the various websites.

• Journal of the Korean Society for information Management
• /
• v.20 no.1
• /
• pp.417-455
• /
• 2003

Ontologies are formal theories that are suitable for implementing the semantic web. which is a new technology that attempts to achieve effective retrieval, integration, and reuse of web resources. Ontologies provide a way of sharing and reusing knowledge among people and heterogeneous applications systems. The role of ontologies is that of making explicit specified conceptualizations. In this context, domain and generic ontologies can be shared, reused, and integrated in the analysis and design stage of information and knowledge systems. This study aims to design an ontology for international organizations. and build an Internet web retrieval system based on the proposed ontology. and finally conduct an experiment to compare the system performance of the proposed system with that of internet search engines focusing relevance and searching time. This study found that average relevance of ontology-based searching and Internet search engines are 4.53 and 2.51, and average searching time of ontology-based searching and Internet search engines are 1.96 minutes and 4.74 minutes.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.8
• /
• pp.243-252
• /
• 2023

Satellite imageries are at a greatest importance for land cover examining. Numerous studies have been conducted with satellite images and uses semantic segmentation techniques to extract information which has higher altitude viewpoint. The device which is taking these images must employee wireless communication links to send them to receiving ground stations. Wireless communications from a satellite are inevitably affected due to transmission errors. Evidently images which are being transmitted are distorted because of the information loss. Current semantic segmentation techniques are not made for segmenting distorted images. Traditional image enhancement methods have their own limitations when they are used for satellite images enhancement. This paper proposes an auto-encoder based image pre-enhancing method for satellite images. As a distorted satellite images dataset, images received from a real radio transmitter were used. Training process of the proposed auto-encoder was done by letting it learn to produce a proper approximation of the source image which was sent by the image transmitter. Unlike traditional image enhancing methods, the proposed method was able to provide more applicable image to a segmentation model. Results showed that by using the proposed pre-enhancing technique, segmentation results have been greatly improved. Enhancements made to the aerial images are contributed the correct assessment of land resources.

• Journal of the Semiconductor & Display Technology
• /
• v.19 no.2
• /
• pp.88-91
• /
• 2020

Image segmentation is the task of partitioning an image into multiple sets of pixels based on some characteristics. The objective is to simplify the image into a representation that is more meaningful and easier to analyze. In this paper, we apply deep-learning to pre-train the learning model, and implement an algorithm that performs image segmentation in real time by extracting frames for the stream input from the Android device. Based on the open source of DeepLab-v3+ implemented in Tensorflow, some convolution filters are modified to improve real-time operation on the Android platform.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.3
• /
• pp.141-148
• /
• 2021

This paper presents a method to detect zebra-crossing using deep learning which combines SegNet and ResNet. For the blind, a safe crossing system is important to know exactly where the zebra-crossings are. Zebra-crossing detection by deep learning can be a good solution to this problem and robotic vision-based assistive technologies sprung up over the past few years, which focused on specific scene objects using monocular detectors. These traditional methods have achieved significant results with relatively long processing times, and enhanced the zebra-crossing perception to a large extent. However, running all detectors jointly incurs a long latency and becomes computationally prohibitive on wearable embedded systems. In this paper, we propose a model for fast and stable segmentation of zebra-crossing from captured images. The model is improved based on a combination of SegNet and ResNet and consists of three steps. First, the input image is subsampled to extract image features and the convolutional neural network of ResNet is modified to make it the new encoder. Second, through the SegNet original up-sampling network, the abstract features are restored to the original image size. Finally, the method classifies all pixels and calculates the accuracy of each pixel. The experimental results prove the efficiency of the modified semantic segmentation algorithm with a relatively high computing speed.