• The Journal of the Acoustical Society of Korea
• /
• v.23 no.3E
• /
• pp.91-97
• /
• 2004

In this paper, we propose a classification system of TV program scenes based on audio information. The system classifies the video scene into six categories of commercials, basketball games, football games, news reports, weather forecasts and music videos. Two type of audio feature set are extracted from each audio frame-timbral features and coefficient domain features which result in 58-dimensional feature vector. In order to reduce the computational complexity of the system, 58-dimensional feature set is further optimized to yield l0-dimensional features through Sequential Forward Selection (SFS) method. This down-sized feature set is finally used to train and classify the given TV program scenes using κ -NN, Gaussian pattern matching algorithm. The classification result of 91.6% reported here shows the promising performance of the video scene classification based on the audio information. Finally, the system stability problem corresponding to different query length is investigated.

• Journal of Digital Contents Society
• /
• v.18 no.8
• /
• pp.1635-1640
• /
• 2017

In this paper, a hierarchical image tree model for weather classification is defined in a single outdoor image, and a weather classification algorithm using image intensity and k-mean segmentation image is proposed. In the first level of the hierarchical image tree model, the indoor and outdoor images are distinguished. Whether the outdoor image is daytime, night, or sunrise/sunset image is judged using the intensity and the k-means segmentation image at the second level. In the last level, if it is classified as daytime image at the second level, it is finally estimated whether it is sunny or foggy image based on edge map and fog rate. Some experiments are conducted so as to verify the weather classification, and as a result, the proposed method shows that weather features are effectively detected in a given image.

• The Journal of Korea Robotics Society
• /
• v.14 no.1
• /
• pp.8-13
• /
• 2019

Visual place recognition is widely researched area in robotics, as it is one of the elemental requirements for autonomous navigation, simultaneous localization and mapping for mobile robots. However, place recognition in changing environment is a challenging problem since a same place look different according to the time, weather, and seasons. This paper presents a feature extraction method using a deep convolutional auto-encoder to recognize places under severe appearance changes. Given database and query image sequences from different environments, the convolutional auto-encoder is trained to predict the images of the desired environment. The training process is performed by minimizing the loss function between the predicted image and the desired image. After finishing the training process, the encoding part of the structure transforms an input image to a low dimensional latent representation, and it can be used as a condition-invariant feature for recognizing places in changing environment. Experiments were conducted to prove the effective of the proposed method, and the results showed that our method outperformed than existing methods.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.43-45
• /
• 2021

The short-term quantitative precipitation prediction (QPF) system is important socially and economically to prevent damage from severe weather. Recently, many studies for short-term QPF model applying the Deep Neural Network (DNN) has been conducted. These studies require the sophisticated pre-processing because the mistreatment of various and vast meteorological data sets leads to lower performance of QPF. Especially, for more accurate prediction of the non-linear trends in precipitation, the dataset needs to be carefully handled based on the physical and dynamical understands the data. Thereby, this paper proposes the following approaches: i) refining and combining major factors (weather radar, terrain, air temperature, and so on) related to precipitation development in order to construct training data for pattern analysis of precipitation; ii) producing predicted precipitation fields based on Convolutional with ConvLSTM. The proposed algorithm was evaluated by rainfall events in 2020. It is outperformed in the magnitude and strength of precipitation, and clearly predicted non-linear pattern of precipitation. The algorithm can be useful as a forecasting tool for preventing severe weather.

• Journal of Korean Society for Atmospheric Environment
• /
• v.30 no.2
• /
• pp.119-127
• /
• 2014

A very high resolution weather analysis system (VHRAS) of 50 m horizontal resolution is established based on LAPS. VHRAS utilizes the 3 hourly forecast data of the Unified Model (UM) of the Korea Meteorological Administration (KMA) with the horizontal resolution of 12 km as initial guess fields. The analysis system ingests the automatic weather station (AWS) data as input observations. The analysis system operates every hour for Seoul, Korea region in real time basis. It takes less than 10 minutes for one analysis cycle. The size of grid of the analysis domain is $800{\times}660$, respectively. The analysis results from December 2010 to February 2011 showed that the mean biases of temperature, maximum and minimum temperature were -0.07, 1.6, $0.2^{\circ}C$, respectively. The temperature in the central part of the city revealed relatively higher value than that of the surrounding mountainous areas, which showed a heat island feature. The heat island appears in zonal direction since the central city region is developed along a large river. Along the heat island, the eastern region was warmer than the western region. The warmer temperature in the western part of the heat island was caused by anthropogenic heat change in conjunction with the change of land use. This system will provide more reliable weather data and information in Seoul.

• Korean Journal of Remote Sensing
• /
• v.26 no.6
• /
• pp.721-730
• /
• 2010

In satellite remote sensing, irregular temporal sampling is a common feature of geophysical and biological process on the earth's surface. Lee (2008) proposed a feed-back system using a harmonic model of single period to adaptively reconstruct observation image series contaminated by noises resulted from mechanical problems or environmental conditions. However, the simple sinusoidal model of single period may not be appropriate for temporal physical processes of land surface. A complex model of multiple periods would be more proper to represent inter-annual and inner-annual variations of surface parameters. This study extended to use a multi-periodic harmonic model, which is expressed as the sum of a series of sine waves, for the adaptive system. For the system assessment, simulation data were generated from a model of negative errors, based on the fact that the observation is mainly suppressed by bad weather. The experimental results of this simulation study show the potentiality of the proposed system for real-time monitoring on the image series observed by imperfect sensing technology from the environment which are frequently influenced by bad weather.

• Journal of The Korean Astronomical Society
• /
• v.54 no.5
• /
• pp.139-155
• /
• 2021

We present an updated version of the multilayer spectral inversion (MLSI) recently proposed as a technique to infer the physical parameters of plasmas in the solar chromosphere from a strong absorption line. In the original MLSI, the absorption profile was constant over each layer of the chromosphere, whereas the source function was allowed to vary with optical depth. In our updated MLSI, the absorption profile is allowed to vary with optical depth in each layer and kept continuous at the interface of two adjacent layers. We also propose a new set of physical requirements for the parameters useful in the constrained model fitting. We apply this updated MLSI to two sets of Hα and Ca II line spectral data taken by the Fast Imaging Solar Spectrograph (FISS) from a quiet region and an active region, respectively. We find that the new version of the MLSI satisfactorily fits most of the observed line profiles of various features, including a network feature, an internetwork feature, a mottle feature in a quiet region, and a plage feature, a superpenumbral fibril, an umbral feature, and a fast downflow feature in an active region. The MLSI can also yield physically reasonable estimates of hydrogen temperature and nonthermal speed as well as Doppler velocities at different atmospheric levels. We conclude that the MLSI is a very useful tool to analyze the Hα line and the Ca II 8542 line spectral daya, and will promote the investigation of physical processes occurring in the solar photosphere and chromosphere.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2005.05b
• /
• pp.1209-1213
• /
• 2005

It reflects well feature of slope that is characteristic of city river basin of Pusan local. Process various hydrological datas and basin details datas which is collected through basin basis data. weather satellite equipment(EMS-DEU) and automatic water level equipment(AWS-DEU) and use as basin input data of ILLUDAS model, SWMM model and HEC-HMS model In order to examine outflow feature of experiment basin and then use in reservoir design of experiment basin through calibration and verification about HEC-HMS model. Inserted design rainfall for 30 years that is design criteria of creek into HEC-HMS model and then calculated design floods according to change aspect of the impermeable rate. Capacity of reservoir was determined on the outflow mass curve. Designed imagination reservoir(volume $54,000m^3$) at last outlet upper stream of experiment basin, after designing reservoir. It could be confirmed that the peak flow was reduced resulting from examining outflow aspect. Designing reservoir must decrease outflow of urban areas.

• Journal of the Korean Society of Earth Science Education
• /
• v.17 no.2
• /
• pp.153-167
• /
• 2024

This study explored the errors and context occurred during high school students' data analysis processes. For the study, 222 data inquiry reports produced by 74 students from 'A' High School were collected and explored the detailed error types in the data analysis processes such as data collection and preprocessing, data representation, and data interpretation. The results of study found that in the data interpretation process, students had a somewhat insufficient understanding of seasonal variations and periodic patterns about weather elements. And, various types of errors were identified in the data representation process, such as basic unit in graphs, legend settings, trend lines. The causes of these errors are the feature of authoring tools, misconceptions related to weather elements, and cognitive biases, etc. Based on the study's results, educational implications for big data education, a significant topic in future science education, were derived. And related follow-up studies were suggested.

• Journal of KIISE:Software and Applications
• /
• v.31 no.11
• /
• pp.1534-1542
• /
• 2004

A novel vision-based scheme of extracting real-time traffic information parameters is presented. The method is based on a region classification followed by a spatio-temporal image analysis. The detection region images for each traffic lane are classified into one of the three categories: the road, the vehicle, and the shadow, using statistical and structural features. Misclassification in a frame is corrected by using temporally correlated features of vehicles in the spatio-temporal image. Since only local images of detection regions are processed, the real-time operation of more than 30 frames per second is realized without using dedicated parallel processors, while ensuring detection performance robust to the variation of weather conditions, shadows, and traffic load.