• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.85-92
• /
• 2023

In this paper, we propose a method for automatically generating story-based abbreviated summaries from long-form dramas and movies. From the shooting stage, the basic premise was to compose a frame with illusion of depth considering the golden division as well as focus on the object of interest to focus the viewer's attention in terms of content delivery. To consider how to extract the appropriate frames for this purpose, we utilized elemental techniques that have been utilized in previous work on scene and shot detection, as well as work on identifying focus-related blur. After converting the videos shared on YouTube to frame-by-frame, we divided them into a entire frame and three partial regions for feature extraction, and calculated the results of applying Laplacian operator and FFT to each region to choose the FFT with relative consistency and robustness. By comparing the calculated values for the entire frame with the calculated values for the three regions, the target frames were selected based on the condition that relatively sharp regions could be identified. Based on the selected results, the final frames were extracted by combining the results of an offline change point detection method to ensure the continuity of the frames within the shot, and an edit decision list was constructed to produce an abbreviated summary of 62.77% of the footage with F1-Score of 75.9%

• Tunnel and Underground Space
• /
• v.33 no.4
• /
• pp.281-298
• /
• 2023

Continuous research efforts are being devoted to unmanned mobile platforms for lunar exploration. There is an ongoing demand for real-time information processing to accurately determine the positioning and mapping of areas of interest on the lunar surface. To apply deep learning processing and analysis techniques to practical rovers, research on software integration and optimization is imperative. In this study, a foundational investigation has been conducted on real-time analysis of virtual lunar base construction site images, aimed at automatically quantifying spatial information of key objects. This study involved transitioning from an existing region-based object recognition algorithm to a boundary box-based algorithm, thus enhancing object recognition accuracy and inference speed. To facilitate extensive data-based object matching training, the Batch Hard Triplet Mining technique was introduced, and research was conducted to optimize both training and inference processes. Furthermore, an improved software system for object recognition and identical object matching was integrated, accompanied by the development of visualization software for the automatic matching of identical objects within input images. Leveraging satellite simulative captured video data for training objects and moving object-captured video data for inference, training and inference for identical object matching were successfully executed. The outcomes of this research suggest the feasibility of implementing 3D spatial information based on continuous-capture video data of mobile platforms and utilizing it for positioning objects within regions of interest. As a result, these findings are expected to contribute to the integration of an automated on-site system for video-based construction monitoring and control of significant target objects within future lunar base construction sites.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.9 no.5
• /
• pp.183-189
• /
• 2009

Recently, PCS, PDA and mobile devices, such as the proliferation of spread, GPS (Global Positioning System) the use of, the rapid development of wireless network and a regular user even images, audio, video, multimedia data, such as increased use is for. In particular, video data among multimedia data, unlike the moving object, text or image data that contains information about the movements and changes in the space of time, depending on the kinds of changes that have sigongganjeok attributes. Spatial location of objects on the flow of time, changing according to the moving object (Moving Object) of the continuous movement trajectory of the meeting is called, from the user from the database that contains a given query trajectory and data trajectory similar to the finding of similar trajectory Search (Similar Sub-trajectory Retrieval) is called. To search for the trajectory, and these variations, and given the similar trajectory of the user query (Tolerance) in the search for a similar trajectory to approximate data matching (Approximate Matching) should be available. In addition, a large multimedia data from the database that you only want to be able to find a faster time-effective ways to search different from the existing research is required. To this end, in this paper effectively divided into a grid to search for the trajectory to the trajectory of moving objects, similar to the effective support of the search trajectory offers a new grid-based search techniques.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.1
• /
• pp.61-69
• /
• 2012

Smart Grid is the next-generation intelligent power grid that maximizes energy efficiency with the convergence of IT technologies and the existing power grid. Smart Grid is created solution for standardization and interoperability. Smart Grid industry enables consumers to check power rates in real time for active power consumption. It also enables suppliers to measure their expected power generation load, which stabilizes the operation of the power system. Smart industy was ecolved actively cause Wireless communication is being considered for AMI system and wireless communication using ZigBee sensor has been applied in various industly. In this paper, we proposed efficient addressing scheme for improving the performance of the routing algorithm using ZigBee in Smart Grid environment. A distributed address allocation scheme used an existing algorithm has wasted address space. Therefore proposing x, y coordinate axes from divide address space of 16 bit to solve this problem. Each node was reduced not only bitwise but also multi hop using the coordinate axes while routing than Cskip algorithm. I compared the performance between the standard and the proposed mechanism through the numerical analysis. Simulation verify performance about decrease averaging multi hop count that compare proposing algorithm and another. The numerical analysis results show that proposed algorithm reduce multi hop than ZigBee distributed address assignment and another.

• Journal of Service Research and Studies
• /
• v.3 no.2
• /
• pp.53-60
• /
• 2013

Datamining from the large data in the form of various techniques for obtaining information have been developed. In recent years one of the most sought areas of pattern recognition and machine learning method is created with most of existing learning algorithms based on categorical attributes to a rule or decision model. However, the real-world data, it may consist of numeric attributes in many cases. In addition it contains attributes with numerical values to the normal categorical attribute. In this case, therefore, it is required processes in order to use the data to learn an appropriate value for the type attribute. In this paper, the domain of the numeric attributes are divided into several segments using learning algorithm techniques of discritization. It is described Clustering with other data mining techniques. Large amount of first cluster with characteristics is similar records from the database into smaller groups that split multiple given finite patterns in the pattern space. It is close to each other of a set of patterns that together make up a bunch. Among the set without specifying a particular category in a given data by extracting a pattern. It will be described similar grouping of data clustering technique to classify the data.

• Journal of Broadcast Engineering
• /
• v.23 no.1
• /
• pp.45-52
• /
• 2018

The virtual reality (VR) cartoon is a format of VR contents that leverage the characteristics of webtoons that provides the simple story line and graphical storytelling tools to strategically surmount limitations of VR contents design. The VR cartoon enables people to experience the imaginary three-dimensional space in the webtoon as a real space by the transformation of webtoon contents through VR prototyping. The VR cartoon successfully presents focused environment where people can readily pay attention to the contents without notable motion sickness. People have been familiar with the storytelling strategy in the context of published cartoons and webtoons, likely we've understood the narrative of a movie through the continuous scenes projected in the screen. Indeed, it has been recognized as a popular toolset of communication, where visual images are sequentially delivered by replacing multiple planar spaces to tell a story narrative. While there are discrete panels with the time and space resolution in the graphical cartoons, people can distill a commit closure based on their past experiences. This is a typical "grammar" of the cartoon, which can be extrapolated to the VR cartoon that provides a seminal storytelling strategy. In this article, we review how the storytelling strategy in webtoons has been transformed into that in VR cartoons, and analyze the key components of VR cartoons. We envision that our research can potentially create keystones to produce variety of new VR contents by reflecting various narrative media including cartoon as a 'sequential art'.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_2
• /
• pp.1579-1590
• /
• 2020

In this paper, spatially-adaptive denormalization (SPADE) based U-Net is proposed to detect changes by using high-resolution satellite images. The proposed network is to preserve spatial information using SPADE. Change detection methods using high-resolution satellite images can be used to resolve various urban problems such as city planning and forecasting. For using pixel-based change detection, which is a conventional method such as Iteratively Reweighted-Multivariate Alteration Detection (IR-MAD), unchanged areas will be detected as changing areas because changes in pixels are sensitive to the state of the environment such as seasonal changes between images. Therefore, in this paper, to precisely detect the changes of the objects that consist of the city in time-series satellite images, the semantic spatial objects that consist of the city are defined, extracted through deep learning based image segmentation, and then analyzed the changes between areas to carry out change detection. The semantic objects for analyzing changes were defined as six classes: building, road, farmland, vinyl house, forest area, and waterside area. Each network model learned with KOMPSAT-3A satellite images performs a change detection for the time-series KOMPSAT-3 satellite images. For objective assessments for change detection, we use F1-score, kappa. We found that the proposed method gives a better performance compared to U-Net and UNet++ by achieving an average F1-score of 0.77, kappa of 77.29.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.13 no.3
• /
• pp.165-173
• /
• 2010

A cloud detection method is introduced to improve the reliability of NOAA/AVHRR Sea Surface Temperature (SST) data processed during the daytime and nighttime in the TeraScan System. In daytime, the channels 2 and 4 are used to detect a cloud using the three tests, which are spatial uniformity tests of brightness temperature (infrared channel 4) and channel 2 albedo, and reflectivity threshold test for visible channel 2. Meanwhile, the nighttime cloud detection tests are performed by using the channels 3 and 4, because the channel 2 data are not available in nighttime. This process include the dual channel brightness temperature difference (ch3 - ch4) and infrared channel brightness temperature threshold tests. For a comparison of daytime and nighttime SST images, two data used here are obtained at 0:28 (UTC) and 21:00 (UTC) on May 13, 2009. 6 parameters was tested to understand the factors that affect a cloud masking in and around Korean Peninsula. In daytime, the thresholds for ch2_max cover a range 3 through 8, and ch4_delta and ch2_delta are fixed on 5 and 2, respectively. In nighttime, the threshold range of ch3_minus_ch4 is from -1 to 0, and ch4_delta and min_ch4_temp have the fixed thresholds with 3.5 and 0, respectively. It is acceptable that the resulted images represent a reliability of SST according to the change of cloud masking area by each level. In the future, the accuracy of SST will be verified, and an assimilation method for SST data should be tested for a reliability improvement considering an atmospheric characteristic of research area around Korean Peninsula.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.33 no.1
• /
• pp.45-52
• /
• 2015

The interoperability of multi-source data has become more important due to various digital maps, produced from public institutions and enterprises. In this study, the automatic matching algorithm of multi-source building data using hierarchical matching was proposed. At first, we divide digital maps into blocks and perform the primary geometric registration of buildings with the ICP algorithm. Then, corresponding building pairs were determined by evaluating the similarity of overlap area, and the matching threshold value of similarity was automatically derived by the Otsu binary thresholding. After the first matching, we extracted error matching candidates buildings which are similar with threshold value to conduct the secondary ICP matching and to make a matching decision using turning angle function analysis. For the evaluation, the proposed method was applied to representative public digital maps, road name address map and digital topographic map 2.0. As a result, the F measures of matching and non-matching buildings increased by 2% and 17%, respectively. Therefore, the proposed method is efficient for the matching of building polygons from multi-source digital maps.

• KIPS Transactions on Computer and Communication Systems
• /
• v.5 no.10
• /
• pp.293-302
• /
• 2016

Since the electricity is produced and consumed simultaneously, predicting the electric load and securing affordable electric power are necessary for reliable electric power supply. In particular, a university campus is one of the highest power consuming institutions and tends to have a wide variation of electric load depending on time and environment. For these reasons, an accurate electric load forecasting method that can predict power consumption in real-time is required for efficient power supply and management. Even though various influencing factors of power consumption have been discovered for the educational institutions by analyzing power consumption patterns and usage cases, further studies are required for the quantitative prediction of electric load. In this paper, we build an electric load forecasting model by implementing and evaluating various machine learning algorithms. To do that, we consider three building clusters in a campus and collect their power consumption every 15 minutes for more than one year. In the preprocessing, features are represented by considering periodic characteristic of the data and principal component analysis is performed for the features. In order to train the electric load forecasting model, we employ both artificial neural network and support vector machine. We evaluate the prediction performance of each forecasting model by 5-fold cross-validation and compare the prediction result to real electric load.