• Journal of Information Processing Systems
• /
• v.18 no.4
• /
• pp.587-598
• /
• 2022

To increase building change recognition accuracy, we present a deep learning-based building change detection using remote sensing images. In the proposed approach, by merging pixel-level and object-level information of multitemporal remote sensing images, we create the difference image (DI), and the frequency-domain significance technique is used to generate the DI saliency map. The fuzzy C-means clustering technique pre-classifies the coarse change detection map by defining the DI saliency map threshold. We then extract the neighborhood features of the unchanged pixels and the changed (buildings) from pixel-level and object-level feature images, which are then used as valid deep neural network (DNN) training samples. The trained DNNs are then utilized to identify changes in DI. The suggested strategy was evaluated and compared to current detection methods using two datasets. The results suggest that our proposed technique can detect more building change information and improve change detection accuracy.

• Proceedings of the IEEK Conference
• /
• 2007.07a
• /
• pp.209-210
• /
• 2007

Obtained disparity map from the stereo camera by using the several stereo matching algorithms carries lots of noise because of various causes. In our approach, mode filtering and noise elimination technique using the histogram and projection-based region merging methods are adopted for improving the quality of disparity map and image segmentation. The proposed algorithms are implemented in VHDL and the real-time experimentation shows the accurately divided objects.

• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10a
• /
• pp.15-17
• /
• 1999

본 논문은 다수의 사용자에 대한 실시간 멀티미디어 서비스에서 문제가 되는 초기 지연시간을 최소화하는 새로운 동적 스트림 합병 기법을 제안한다. 제안된 기법은 멀티미디어 서비스, 특히 비디오 서비스의 경우 약간의 QoS 변화가 서비스의 질에 큰 영향을 미치는 않는 점을 이용하여, 시간적으로 서로 인접한 여러 개의 스트림을 점차적으로 합병하여 서비스함으로써 짧은 초기 지연시간 유지를 위한 버퍼의 양을 최소화 할 수 있다. 성능분석 결과에서 제안된 기법은 기존의 방법들에 비하여 버퍼 활용면에서 우수한 성능을 나타냄을 보인다.

• Journal of Korea Water Resources Association
• /
• v.50 no.12
• /
• pp.849-862
• /
• 2017

The increased frequency of meteorological disasters has been observed due to increased extreme events such as heavy rainfalls and flash floods. Numerous studies using high-resolution weather radar rainfall data have been carried out on the hydrological effects. In this study, a conditional merging technique is employed, which makes use of geostatistical methods to extract the optimal information from the observed data. In this context, three different techniques such as kriging, inverse distance weighting and spline interpolation methods are applied to conditionally merge radar and ground rainfall data. The results show that the estimated rainfall not only reproduce the spatial pattern of sub-hourly rainfall with a relatively small error, but also provide reliable temporal estimates of radar rainfall. The proposed modeling framework provides feasibility of using conditionally merged rainfall estimation at high spatio-temporal resolution in ungauged areas.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.17 no.3
• /
• pp.197-202
• /
• 2011

This study introduces a technique to merge three different sea surface temperature(SST) data obtained from multi-satellite sensors. NGSST algorithm, the most popular method of related society, estimates a center pixel of target SST using temporal and spatial correlations, excluding SST accuracies according to sensing methods or properties of satellites. We suggest a merging method of SST to consider the accuracy by satellite or sensor with a comparison with NGSST method. The data used for a merged daily SST with spatial resolution of 5 km was applied from three different satellite sensors such as MODIS, AVHRR and AMSR-E from April 2 to 4, 2011 around the southern coast of Korea. Results of the comparisons showed that the new method is higher than the NGSST method and its STDEV represents a comparatively low value. In future we are planning to compare and analyze the datasets during the daytime as well as nighttime over total cycle of the day.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.28 no.4
• /
• pp.421-430
• /
• 2010

Image segmentation technique is becoming increasingly important in the field of remote sensing image analysis in areas such as object oriented image classification to extract object regions of interest within images. This paper presents a new method for image segmentation in High Resolution Remote Sensing Image based on Improved Seeded Region Growing (ISRG) and Region merging. Firstly, multi-spectral edge detection was done using an entropy operator in pan-sharpened QuickBird imagery. Then, the initial seeds were automatically selected from the obtained multi-spectral edge map. After automatic selection of significant seeds, an initial segmentation was achieved by applying ISRG to consider spectral and edge information. Finally the region merging process, integrating region texture and spectral information, was carried out to get the final segmentation result. The accuracy assesment was done using the unsupervised objective evaluation method for evaluating the effectiveness of the proposed method. Experimental results demonstrated that the proposed method has good potential for application in the segmentation of high resolution satellite images.

• Journal of the Society of Naval Architects of Korea
• /
• v.31 no.4
• /
• pp.23-31
• /
• 1994

The compartmentation model is represented by the characteristics and geometric information of the spaces defined by the structural members which are used for the boundary planes of the compartment. For the efficient compartment modeling a program performing the compartmentation design by the chopping and merging method was presented by authors. In this research, the development of an interactive ship compartmentation modeller is introduced. It is natural that the value of the program lessens if the input process is complicated and uneasy, even though the internal techniques for the compartmentation modeling are superior. In this paper, a method for the convenient input is proposed and implemented with the help of a graphical user interface technique. The modeling method introduced in this paper performs an efficient compartmentation modeling fast and conveniently by the solid modeling concept and the graphical user interface.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.21 no.4
• /
• pp.114-130
• /
• 2022

The purpose of this study was to investigate the possibility of increasing the efficiency of disaster relief rescue operations through collaboration among multiple aerial and ground robots. The robots create 2.5D maps, which are merged into a 2.5D map. The 2.5D map can be handled by a low-specification controller of an aerial robot and is suitable for ground robot navigation. For localization of the aerial robot, a six-degree-of-freedom pose recognition method using VIO was applied. To build a 2.5D map, an image conversion technique was employed. In addition, to merge 2.5D maps, an image similarity calculation technique based on the features on a wall was used. Localization and navigation were performed using a ground robot to evaluate the reliability of the 2.5D map. As a result, it was possible to estimate the location with an average and standard error of less than 0.3 m for the place where the 2.5D map was normally built, and there were only four collisions for the obstacle with the smallest volume. Based on the 2.5D map building and map merging system for the aerial robot used in this study, it is expected that disaster response work efficiency can be improved by combining the advantages of heterogeneous robots.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.428-431
• /
• 2004

A multi-stage hierarchical clustering technique, which is an unsupervised technique, has been proposed in this paper for classifying the hyperspectral data .. The multistage algorithm consists of two stages. The 'local' segmentor of the first stage performs region-growing segmentation by employing the hierarchical clustering procedure with the restriction that pixels in a cluster must be spatially contiguous. The 'global' segmentor of the second stage, which has not spatial constraints for merging, clusters the segments resulting from the previous stage, using a context-free similarity measure. This study applied the multistage hierarchical clustering method to the data generated by band reduction, band selection and data compression. The classification results were compared with them using full bands.

• Proceedings of the KSRS Conference
• /
• v.1
• /
• pp.188-190
• /
• 2006

A multistage hierarchical clustering technique, which is an unsupervised technique, was suggested in this paper for classifying large remotely-sensed imagery. The multistage algorithm consists of two stages. The local segmentor of the first stage performs regiongrowing segmentation by employing the hierarchical clustering procedure of CN-chain with the restriction that pixels in a cluster must be spatially contiguous. This stage uses a sliding window strategy with boundary blocking to alleviate a computational problem in computer memory for an enormous data. The global segmentor of the second stage has not spatial constraints for merging to classify the segments resulting from the previous stage. The experimental results show that the new approach proposed in this study efficiently performs the segmentation for the images of very large size and an extensive number of bands