• Journal of KIISE
• /
• v.45 no.1
• /
• pp.94-98
• /
• 2018

We propose Wide Inception ResNet (WIR Net) an optimized neural network architecture as a real-time semantic segmentation method for autonomous driving. The neural network architecture consists of an encoder that extracts features by applying a residual connection and inception module, and a decoder that increases the resolution by using transposed convolution and a low layer feature map. We also improved the performance by applying an ELU activation function and optimized the neural network by reducing the number of layers and increasing the number of filters. The performance evaluations used an NVIDIA Geforce GTX 1080 and TX1 boards to assess the class and category IoU for cityscapes data in the driving environment. The experimental results show that the accuracy of class IoU 53.4, category IoU 81.8 and the execution speed of $640{\times}360$, $720{\times}480$ resolution image processing 17.8fps and 13.0fps on TX1 board.

• Journal of Digital Contents Society
• /
• v.18 no.5
• /
• pp.911-921
• /
• 2017

The purpose of this study was to investigate the semantic network analysis to understand image contents and to examine the degree to which words, word clusters contributed to the formation of semantic map within image contents. For this research, from 1993 until 2016 the field of the image contents were collected for a total of 2,624 cases papers. The word appeared in Title analyzed the social network by using the R program of Big Data. The results were as follows: First, Research on 'education' in the field of image contents has decreased. Second, the role of 'media' in the field of image contents is changing. Finally, It is a change in the status of 'contents' in the field of image contents.

• Journal of Information Science Theory and Practice
• /
• v.12 no.3
• /
• pp.49-62
• /
• 2024

Strategy monitoring is essential for business management and for administrators, including managers and executives, to build a data-driven organization. Having a tool that is able to visualize strategic data is significant for business intelligence. Unfortunately, there are gaps between business users and information technology departments or business intelligence experts that need to be filled to meet user requirements. For example, business users want to be self-reliant when using business intelligence systems, but they are too inexperienced to deal with the technical difficulties of the business intelligence systems. This research aims to create an automatic matching framework between the key performance indicators (KPI) formula and the data in database systems, based on ontology concepts, in the case study of Prince of Songkla University. The mapping data schema with ontology (MapDSOnto) framework is created through knowledge adaptation from the literature review and is evaluated using sample data from the case study. String similarity methods are compared to find the best fit for this framework. The research results reveal that the "fuzz.token_set_ratio" method is suitable for this study, with a 91.50 similarity score. The two main algorithms, database schema mapping and domain schema mapping, present the process of the MapDS-Onto framework using the "fuzz.token_set_ratio" method and database structure ontology to match the correct data of each factor in the KPI formula. The MapDS-Onto framework contributes to increasing self-reliance by reducing the amount of database knowledge that business users need to use semantic business intelligence.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.1
• /
• pp.19-30
• /
• 2014

For the expansion of the Semantic Web, studies in converting the data stored in the relational database into the ontology are actively in process. Such studies mainly use an RDB to RDF mapping model, the model to map relational database components to RDF components. However, pre-proposed mapping models have got different expression modes and these damage the accessibility and reusability of the users. As a consequence, the necessity of the standardized mapping language was raised and the W3C suggested the R2RML as the standard mapping language for the RDB to RDF model. The R2RML has a characteristic that converts only the relational database schema data to RDF. For the same reasons above, the ontology about the relation data between table name and column name of the relational database cannot be added. In this paper, we propose an RDB to RDF mapping system considering semantic relations of RDB components in order to solve the above issue. The proposed system generates the mapping data by adding the RDFS attribute data into the schema data defined by the R2RML in the relational database. This mapping data converts the data stored in the relational database into RDF which includes the RDFS attribute data. In this paper, we implement the proposed system as a Java-based prototype, perform the experiment which converts the data stored in the relational database into RDF for the comparison evaluation purpose and compare the results against D2RQ, RDBToOnto and Morph. The proposed system expresses semantic relations which has richer converted ontology than any other studies and shows the best performance in data conversion time.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.4
• /
• pp.412-417
• /
• 2015

Kinect sensor has two output data which are produced from red green blue (RGB) sensor and depth sensor, it is called color image and depth map, respectively. Although this device's prices are cheapest than the other devices for three-dimensional (3D) reconstruction, we need extra work for reconstruct a smooth 3D data and also have semantic meaning. It happened because the depth map, which has been produced from depth sensor usually have a coarse and empty value. Consequently, it can be make artifact and holes on the surface, when we reconstruct it to 3D directly. In this paper, we present a method for solving this problem by using implicit surface representation. The key idea for represent implicit surface is by using radial basis function (RBF) and to avoid the trivial solution that the implicit function is zero everywhere, we need to defined on-surface point and off-surface point. Based on our simulation results using captured face as an input, we can produce smooth 3D face and fill the holes on the 3D face surface, since RBF is good for interpolation and holes filling. Modified anisotropic diffusion is used to produced smoothed surface.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.6 no.4
• /
• pp.195-200
• /
• 2013

This paper proposes an SNS and Web Data Analytics System which can utilize a business marketing strategy by analyzing negative SNS and Web Data that can do great damage to a business image. It consists of the Data Collection Module collecting SNS and Web Data, the Hbase Module storing the collected data, the Data Analysis Module estimating and classifying the meaning of data after an semantic analysis of the collected data, and the PHS Module accomplishing an optimized Map Reduce by using SNS and Web data involved a Businesse. This paper can utilize this analysis result for a business marketing strategy by efficiently managing SNS and Web data with these modules.

• The Journal of the Korea Contents Association
• /
• v.11 no.5
• /
• pp.50-56
• /
• 2011

This paper proposes 3D visualization method of compound knowledge which will be able to identify and search easily compound knowledge objects based the multidimensional relationship. For this, we structurized a compound knowledge with link and node which become the semantic network. and we suggested 3D visualization method using SOM. Also, to arrange compound knowledge from 3D space and to provide the chance of realistic and intuitional information retrieval to the user, we proposed compound knowledge 3D clustering methods using object similarity. Compound knowledge 3D visualization and clustering using SOM will be the optimum method to appear context of compound knowledge and connectivity in space-time.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.5
• /
• pp.436-443
• /
• 2011

Recognition of structures in urban environments is a fundamental ability for unmanned ground vehicles. In this paper we propose the geometrical featured voxel which has not only 3-D coordinates but also the type of geometrical properties of point cloud. Instead of dealing with a huge amount of point cloud collected by range sensors in urban, the proposed voxel can efficiently represent and save 3-D urban structures without loss of geometrical properties. We also provide an urban structure classification algorithm by using the proposed voxel and machine learning techniques. The proposed method enables to recognize urban environments around unmanned ground vehicles quickly. In order to evaluate an ability of the proposed map representation and the urban structure classification algorithm, our vehicle equipped with the sensor system collected range data and pose data in campus and experimental results have been shown in this paper.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_3
• /
• pp.939-951
• /
• 2022

The most important factor in designing autonomous driving systems is to recognize the exact location of the vehicle within the surrounding environment. To date, various sensors and navigation systems have been used for autonomous driving systems; however, all have limitations. Therefore, the need for high-definition (HD) maps that provide high-precision infrastructure information for safe and convenient autonomous driving is increasing. HD maps are drawn using three-dimensional point cloud data acquired through a mobile mapping system (MMS). However, this process requires manual work due to the large numbers of points and drawing layers, increasing the cost and effort associated with HD mapping. The objective of this study was to improve the efficiency of HD mapping by segmenting semantic information in an MMS point cloud into six classes: roads, curbs, sidewalks, medians, lanes, and other elements. Segmentation was performed using various machine learning techniques including random forest (RF), support vector machine (SVM), k-nearest neighbor (KNN), and gradient-boosting machine (GBM), and 11 variables including geometry, color, intensity, and other road design features. MMS point cloud data for a 130-m section of a five-lane road near Minam Station in Busan, were used to evaluate the segmentation models; the average F1 scores of the models were 95.43% for RF, 92.1% for SVM, 91.05% for GBM, and 82.63% for KNN. The RF model showed the best segmentation performance, with F1 scores of 99.3%, 95.5%, 94.5%, 93.5%, and 90.1% for roads, sidewalks, curbs, medians, and lanes, respectively. The variable importance results of the RF model showed high mean decrease accuracy and mean decrease gini for XY dist. and Z dist. variables related to road design, respectively. Thus, variables related to road design contributed significantly to the segmentation of semantic information. The results of this study demonstrate the applicability of segmentation of MMS point cloud data based on machine learning, and will help to reduce the cost and effort associated with HD mapping.

• The KIPS Transactions:PartB
• /
• v.11B no.1
• /
• pp.1-6
• /
• 2004

Motion Information in a video clip often plays an important role in characterizing the content of the clip. A number of methods have been developed to analyze and retrieve video contents using motion information. However, most of these methods focused more on the analysis of direction or trajectory of motion but less on the analysis of the movement of an object. In this paper, we introduce the shape variation descriptor for describing shape variation caused by object movement along time, and propose a method to describe and retrieve the shape variation of the object using shape variation map. The experimental results shows that the proposed method performed much better than the previous method by l1％ and is very effective for describing the shape variation which is applicable to semantic retrieval applications.