• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.10
• /
• pp.3668-3684
• /
• 2021

Video action recognition is widely used in video surveillance, behavior detection, human-computer interaction, medically assisted diagnosis and motion analysis. However, video action recognition can be disturbed by many factors, such as background, illumination and so on. Two-stream convolutional neural network uses the video spatial and temporal models to train separately, and performs fusion at the output end. The multi segment Two-Stream convolutional neural network model trains temporal and spatial information from the video to extract their feature and fuse them, then determine the category of video action. Google Xception model and the transfer learning is adopted in this paper, and the Xception model which trained on ImageNet is used as the initial weight. It greatly overcomes the problem of model underfitting caused by insufficient video behavior dataset, and it can effectively reduce the influence of various factors in the video. This way also greatly improves the accuracy and reduces the training time. What's more, to make up for the shortage of dataset, the kinetics400 dataset was used for pre-training, which greatly improved the accuracy of the model. In this applied research, through continuous efforts, the expected goal is basically achieved, and according to the study and research, the design of the original dual-flow model is improved.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.27-27
• /
• 2023

To analyze the evolution of water resources in Qiandao Lake Basin under the condition of climate change, a WEP-L distributed hydrological model was established to simulate the water cycle process in the basin during 1960-2020. The Mann-Kendall non-parametric test method and Hurst index method were used to analyze the inter-annual variation and annual distribution characteristics of the total water resources in the basin. The multi-scale temporal and spatial distribution and evolution trend of water resources in Qiandao Lake Basin were evaluated. The results show that: (1) The WEP-L model has good simulation results in the Qiandao Lake basin, and the Nash coefficient rate is above 0.83 in the periodic period and above 0.85 in the verification period. (2) The water yield coefficient of the whole basin ranges from 0.436 to 0.630. The annual average total water resource is 12.25 billion m³, equivalent to 1176.4mm of water depth. The annual distribution process shows a unimodal structure, and the water depth of each sub-basin ranges from 742 mm to 1266 mm, and the spatial distribution is higher in the west and lower in the east. (3) The annual water resources series in the basin showed an insignificant upward trend, and the Hurst index was 0.86, indicating a continuous upward trend. From the perspective of monthly water resources, January and February increased significantly, the other months were not significant changes.

• Water Engineering Research
• /
• v.5 no.4
• /
• pp.157-176
• /
• 2004

This research presents a prototype development and implementation of Decision Support System (DSS) for integrated river basin water management for the flood control. The DSS consists of Relational Database Management System, Hydrologic Data Monitoring System, Spatial Analysis Module, Spatial and Temporal Analysis for Rainfall Event Tool, Flood Forecasting Module, Real-Time Operation of Multi Reservoir System, and Dialog Module with Graphical User Interface and Graphic Display Systems. The developed DSS provides an automated process of alternative evaluation and selection within a flexible, fully integrated, interactive, centered relational database management system in a user-friendly computer environment. The river basin decision-maker for the flood control should expect that she or he could manage the flood events more effectively by fully grasping the hydrologic situation throughout the basin.

• Journal of Korean Society for Geospatial Information Science
• /
• v.21 no.2
• /
• pp.93-98
• /
• 2013

Multi-temporal high resolution satellite images are essential data for efficient city analysis and monitoring. Yet even when acquired from the same location, identical sensors as well as different sensors, these multi-temporal images have a geometric inconsistency. Matching points between images, therefore, must be extracted to match the images. With images of an urban area, however, it is difficult to extract matching points accurately because buildings, trees, bridges, and other artificial objects cause shadows over a wide area, which have different intensities and directions in multi-temporal images. In this study, we analyze a shadow effect on image matching of high resolution satellite images in urban area using Scale-Invariant Feature Transform(SIFT), the representative matching points extraction method, and automatic shadow extraction method. The shadow segments are extracted using spatial and spectral attributes derived from the image segmentation. Also, we consider information of shadow adjacency with the building edge buffer. SIFT matching points extracted from shadow segments are eliminated from matching point pairs and then image matching is performed. Finally, we evaluate the quality of matching points and image matching results, visually and quantitatively, for the analysis of shadow effect on image matching of high resolution satellite image.

• Cartoon and Animation Studies
• /
• s.48
• /
• pp.69-84
• /
• 2017

In order to display various art works such as media art in a multi-display environment, it is necessary to consider contents arrangement. The advantage of having a 1: N or N: N layout instead of a 1: 1 or N: 1 layout between display and content, but a more complex scheme of how to do spatial and temporal layout in multi-display Is required. In order to distribute contents, existing media server solution or programming-based multimedia production software is used. However, it takes much time to rearrange or modify the contents, and it is not easy to modify the contents. Therefore, It is difficult to place content in the environment. In order to solve this problem, various approaches are needed from research on content placement method to development of content placement software that improves the existing method. However, analysis on systematic content placement type supporting it, or interface There is also no access to. In this study, we have summarized the requirements for designing the interface for each type with the aim of making it possible to utilize previously analyzed content layout types in various display activities such as media art in multi - display environment. The requirements of each type of interface were derived based on spatial arrangement and temporal layout type which are most distinguished when content is placed. The contents of the interface requirements are summarized as follows: We expect to be a cornerstone for system development.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.14 no.4
• /
• pp.332-339
• /
• 2014

Face classification has wide applications in security and surveillance. However, this technique presents various challenges caused by pose, illumination, and expression changes. Face recognition with long-distance images involves additional challenges, owing to focusing problems and motion blurring. Multiple frames under varying spatial or temporal settings can acquire additional information, which can be used to achieve improved classification performance. This study investigates the effectiveness of multi-frame decision-level fusion with photon-counting linear discriminant analysis. Multiple frames generate multiple scores for each class. The fusion process comprises three stages: score normalization, score validation, and score combination. Candidate scores are selected during the score validation process, after the scores are normalized. The score validation process removes bad scores that can degrade the final output. The selected candidate scores are combined using one of the following fusion rules: maximum, averaging, and majority voting. Degraded facial images are employed to demonstrate the robustness of multi-frame decision-level fusion in harsh environments. Out-of-focus and motion blurring point-spread functions are applied to the test images, to simulate long-distance acquisition. Experimental results with three facial data sets indicate the efficiency of the proposed decision-level fusion scheme.

• Korean Journal of Remote Sensing
• /
• v.35 no.5_1
• /
• pp.681-692
• /
• 2019

In this paper, a hybrid deep learning model, called 2D convolution with bidirectional long short-term memory (2DCBLSTM), is presented that can effectively combine both spatial and temporal features for crop classification. In the proposed model, 2D convolution operators are first applied to extract spatial features of crops and the extracted spatial features are then used as inputs for a bidirectional LSTM model that can effectively process temporal features. To evaluate the classification performance of the proposed model, a case study of crop classification was carried out using multi-temporal unmanned aerial vehicle images acquired in Anbandegi, Korea. For comparison purposes, we applied conventional deep learning models including two-dimensional convolutional neural network (CNN) using spatial features, LSTM using temporal features, and three-dimensional CNN using spatio-temporal features. Through the impact analysis of hyper-parameters on the classification performance, the use of both spatial and temporal features greatly reduced misclassification patterns of crops and the proposed hybrid model showed the best classification accuracy, compared to the conventional deep learning models that considered either spatial features or temporal features. Therefore, it is expected that the proposed model can be effectively applied to crop classification owing to its ability to consider spatio-temporal features of crops.

• Journal of The Korean Astronomical Society
• /
• v.29 no.spc1
• /
• pp.331-332
• /
• 1996

We present 3 rare subtypes of the FFSs observed with high temporal resolution at 4-frequency (1.42, 2.13, 2.84 and 4.2G GHz). The various FFSs occurred during the main and post-flare phase can demonstrate that coronal nonthermal electron acceleration/injection may go through the whole development process of flares, and deduce that there may exist the re-forming of loop-like structures in the post-flare phase, and the complex multi-type magnetic structures in corona.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.690-690
• /
• 2003

The purpose of this study is to analyze the geological environment changes of tidal flat in the Hampyeong Bay. Especially, it centers on the changes in the sedimentary environment using remote sensing data. Multi-temporal Landsat data were used in this study. Remote sensing methods can be effectively applied for quantitative analysis of geological environment changes in tidal flat.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.15 no.3
• /
• pp.66-80
• /
• 2012

It is necessary to normalize spectral image values derived from multi-temporal satellite data to a common scale in order to apply remote sensing methods for change detection, disaster mapping, crop monitoring and etc. There are two main approaches: absolute radiometric normalization and relative radiometric normalization. This study focuses on the multi-temporal satellite image processing by the use of relative radiometric normalization. Three scenes of KOMPSAT-2 imagery were processed using the Multivariate Alteration Detection(MAD) method, which has a particular advantage of selecting PIFs(Pseudo Invariant Features) automatically by canonical correlation analysis. The scenes were then applied to detect disaster areas over Sendai, Japan, which was hit by a tsunami on 11 March 2011. The case study showed that the automatic extraction of changed areas after the tsunami using relatively normalized satellite data via the MAD method was done within a high accuracy level. In addition, the relative normalization of multi-temporal satellite imagery produced better results to rapidly map disaster-affected areas with an increased confidence level.