• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.1
• /
• pp.364-380
• /
• 2016

The most popular approach in object classification is based on the bag of visual-words model, which has several fundamental problems that restricting the performance of this method, such as low time efficiency, the synonym and polysemy of visual words, and the lack of spatial information between visual words. In view of this, an object classification based on weakly supervised E2LSH and saliency map weighting is proposed. Firstly, E2LSH (Exact Euclidean Locality Sensitive Hashing) is employed to generate a group of weakly randomized visual dictionary by clustering SIFT features of the training dataset, and the selecting process of hash functions is effectively supervised inspired by the random forest ideas to reduce the randomcity of E2LSH. Secondly, graph-based visual saliency (GBVS) algorithm is applied to detect the saliency map of different images and weight the visual words according to the saliency prior. Finally, saliency map weighted visual language model is carried out to accomplish object classification. Experimental results datasets of Pascal 2007 and Caltech-256 indicate that the distinguishability of objects is effectively improved and our method is superior to the state-of-the-art object classification methods.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.14 no.5
• /
• pp.549-560
• /
• 1989

In this paper, the method of determining the initial weighting vlaues fuctioning as a filter under the Directional Constrained Minimization of Power(DCMP) algorithm is presented. By analyzing the sideband beamformer with the Finite Impulse Response (FIR) filter concepts, the constraints of any desired directions are obtained and the initial weighing values with fast adaptation time are formulated from those constraints. By applying this proposed initial weighting values to the DCMP and the spatial averaging processor, the interference of a desired direction and the coherent noises are eliminated at the same time. The improvement of this method compared with the existing algorithm is confirmed by computer simulation.

• Journal of Korean Society of Rural Planning
• /
• v.10 no.4 s.25
• /
• pp.9-18
• /
• 2004

The purpose or this study is to simulate spatially the urban expansion phenomena with a cellular automata (CA) technique using GIS. A study area, Suwon city, was selected for test of model verification and application with the classified land-use maps of three data years: 1986, 1996, and 2000. The urbanized potential maps were generated with seven criteria of one geographic factor (slope of land), and six accessibility factors (time distances from city, national road, Seoul, station, and built-up boundary), considering their weighting values, which were optimized by WSM (weighted scenario method for intensity order) combined a ranking method and a AHP technique. The optimized weighting values at the urban expansion between 1986 and 1996 were applied to verify the CA model for the other expansion between 1996 and 2000. The results of model application showed that urban sprawl phenomena of the urban expansion toward rural area can be simulated spatially and temporally with several boundary conditions considering various scenarios for the criteria and parameters of the model. Ultimately, this study can contribute to reference data for land-use planning of urban fringe areas.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.925-928
• /
• 2015

The application fields of the image processing get gradually diversified as the society develops to the highly leveled digital information era and is highlighted as an important field. Especially, many studies on image restoration, a key technology in the image processing have been carried out. This paper proposed a filter which applies the directivity and spatial weighting based on the degraded pixels in order to restore the image degraded in the high density salt and pepper noise environment. In addition, this paper compared this filter with the current methods for objective judgment using PSNR(peak signal to noise ratio) as a criterion of judgment.

• Nuclear Engineering and Technology
• /
• v.4 no.4
• /
• pp.280-293
• /
• 1972

The differential fast neutron spectra above 0.5 Mev at particular spatial positions in tile reactor(TRIGA MARK-II) core has been determined experimentally using several threshold activation detectors. The series expansion technique utilizing the concept of least squares optimization was used to obtain an approximate solution to the set of integral equations which are defined by the experimentally determined activation data. The influence of use of different weighting functions in the solution was analyzed in each measurement. To carry out the necessary mathematical calculations, a computer code for the UNIVAC 1106 digital computer has been prepared. Good agreement was achieved between the differential fast neutron spectra determined in this work and the computed flux determined independently using space-independent multigroup transport theory.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.17 no.5
• /
• pp.161-172
• /
• 2018

This paper proposed the robot vision control method to track a moving rigid body target using the vision system model that can actively control camera parameters even if the relative position between the camera and the robot and the focal length and posture of the camera change. The proposed robotic vision control scheme uses a batch method that uses all the vision data acquired from each moving point of the robot. To process all acquired data, this robot vision control scheme is divided into two cases. One is to give an equal weight for all acquired data, the other is to give weighting for the recent data acquired near the target. Finally, using the two proposed robot vision control schemes, experiments were performed to estimate the positions of a moving rigid body target whose spatial positions are unknown but only the vision data values are known. The efficiency of each control scheme is evaluated by comparing the accuracy through the experimental results of each control scheme.

• Journal of Climate Change Research
• /
• v.4 no.4
• /
• pp.331-348
• /
• 2013

The frequency and intensity of abnormal climate caused by climate change is increasing in Korea. Also, the amount of damage from disaster is increasing rapidly. The research on vulnerability assessment analyzes environmentally, socially and economically vulnerable indicators and is ongoing to reduce the intensity of damage and establish adaptation policies for climate change. Therefore, in this study, we assessed vulnerability using weighting value derived by the regression equation. There are 3 evaluation items : vulnerability assessment for farmland erosion to flood, vulnerability assessment for health to heat wave, vulnerability assessment for forest fire to drought. For this study, indicators for each sectors were selected and spatial data for each sectors were established using GIS program. Results showed that vulnerability to heat wave was more affected by climate factors. On the other hand, vulnerability to flood and drought was more affected by social-economic factors. Then, to analysis efficiency of the regression analysis, vulnerability result was compared between the existing vulnerability research with no weighting applied and the vulnerability research with the influence of weighting value derived by the regression. This study showed that the regression analysis is efficient to provide practical and feasible alternatives in terms of planning climate change adaptation policies and it is expected to be utilized for vulnerability assessment in the future.

• Journal of the Korean Geotechnical Society
• /
• v.26 no.1
• /
• pp.5-19
• /
• 2010

Geo-layer information is important to determine pile length and estimate residual settlement in the construction site. An overall spatial distribution of geo-layers in the entire construction site can be predicted using drill-log information. In this study, the geo-layer distribution at Song-do area was estimated by kriging and inverse distance weighting methods, and a cross validation was adopted to verify the reliability of estimation results. The analysis results indicate that the best fitted theoretical variogram model to the experimental variogram does not always provide the most reliable estimation in the kriging method. The proper $\alpha$ value of inverse distance weighting method must be determined by types of geo-layer, because the $\alpha$ value is affected by types of geo-layer. Results of the kriging method show more reliable results than those of inverse distance weighting method, and the structure of geo-layer distribution could be evaluated by variogram in the kriging method.

• KIEAE Journal
• /
• v.16 no.3
• /
• pp.47-55
• /
• 2016

Purpose: This study was aimed at providing the basic checklist as a means to assess the crime risk in physical environment of the pedestrian passage at residential area. Method: For this purpose, the preliminary checklists were selected according to the review of the precedent studies of checklists in exterior pedestrian passage. The usefulness and the importance of the preliminary checklists were analyzed through the seven expert group meetings, the 87 questionnaires survey of the crime experts & the architectural/urban experts, preliminary assessment and field survey. Results: The assessment categories of checklists were sorted into six types, i.e. spatial structure & function, lighting, landscaping, security facilities, other facilities and cleaning & maintenance. The 49 checklists were proposed according to the assessment categories. The final checklists were divided key checklists and general checklists based on the results of experts' weighting of each list item. There were significant differences between crime experts' weighting and architectural/urban experts' weighting in several checklists, i.e. dividing between pavements and streets, the brightness of light, white light.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.5
• /
• pp.822-832
• /
• 1994

DSC-HDTV image compression algorithm removes spatial, temporal, and amplitude redundancies of an image by using transform coding, motion-compensated predictive coding, and adaptive quantization, respectively. In this paper, leak processing method which is used to recover image quality quickly from scene change and transmission error and adaptive quantization using perceptual weighting factor obtained by HVS are proposed. Perceptual weighting factor is calculated by contrast sensitivity, spatio-temporal masking and frequency sensitivity. Adaptive quantization uses the perceptual weighting factor and global distortion level from buffer history state. Redundant bits according to adaptation of HVS are used for the next image coding. In the case of scene change, DFD using motion compensated predictive coding has high value, large bit rate and unstabilized buffer states since reconstructed image has large quantization noise. Thus, leak factor is set to 0 for scene change frame and leak factor to 15/16 for next frame, and global distortion level is calculated by using standard deviation. Experimental results show that image quality of the proposed method is recovered after several frames and then buffer status is stabilized.