• Journal of Intelligence and Information Systems
• /
• v.16 no.2
• /
• pp.95-108
• /
• 2010

In this paper, we present a hybrid neural network model for dynamic hand gesture recognition. The model consists of two modules, feature extraction module and pattern classification module. We first propose a modified CNN(convolutional Neural Network) a pattern recognition model for the feature extraction module. Then we introduce a weighted fuzzy min-max(WFMM) neural network for the pattern classification module. The data representation proposed in this research is a spatiotemporal template which is based on the motion information of the target object. To minimize the influence caused by the spatial and temporal variation of the feature points, we extend the receptive field of the CNN model to a three-dimensional structure. We discuss the learning capability of the WFMM neural networks in which the weight concept is added to represent the frequency factor in training pattern set. The model can overcome the performance degradation which may be caused by the hyperbox contraction process of conventional FMM neural networks. From the experimental results of human action recognition and dynamic hand gesture recognition for remote-control electric home appliances, the validity of the proposed models is discussed.

• Journal of Broadcast Engineering
• /
• v.9 no.4 s.25
• /
• pp.434-445
• /
• 2004

Motion Estimation is an essential module in video encoders based on international standards such as H.263 and MPEG. Many fast motion estimation algorithms have been proposed in order to reduce the computational complexity of a well-known full search algorithms(FS). However, these fast algorithms can not work efficiently in DSP processors recently developed for video processing. To solve for this. we propose an efficient motion estimation scheme optimized in the DSP processor like Philips TM1300. A motion vector predictor is pre-estimated and a small search range is chosen in the proposed scheme using strong motion vector correlation between a current macro block (MB) and its neighboring MB's to reduce computation time. An MPEG-4 SP@L3(Simple Profile at Level 3) encoding system is implemented in Philips TM1300 to verify the effectiveness of the proposed method. In that processor, we can achieve better performance using our method than other conventional ones while keeping visual quality as good as that of the FS.

• The KIPS Transactions:PartA
• /
• v.14A no.3 s.107
• /
• pp.133-140
• /
• 2007

The SWBF(shrink-wrapped boundary face) algorithm is a recent mesh reconstruction method for constructing a surface model from a set of unorganized 3D points. In this paper, we point out the surface duplication problem of SWBF and propose an improved mesh reconstruction scheme. Our method tries to classify the non-boundary cells as the inner cell or the outer cell, and makes an initial mesh without surface duplication by adopting the improved boundary face definition. To handle the directional unbalance of surface sampling density arise in typical 3D scanners, two dimensional connectivity in the cell image is introduced and utilized. According to experiments, our method is proved to be very useful to overcome the surface duplication problem of the SWBF algorithm.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.8
• /
• pp.311-318
• /
• 2021

Research has been ongoing to detect ships from offshore photographs for a variety of reasons, including maritime security, identifying international trends, and social scientific research. Due to the development of artificial intelligence, R-CNN models for object detection in photographs and images have emerged, and the performance of object detection has risen dramatically. Ship detection in offshore photographs using the R-CNN model has also begun to apply to satellite photography. However, satellite images project large areas, so various objects such as vehicles, landforms, and buildings are sometimes recognized as ships. In this paper, we propose a novel methodology to improve the performance of ship detection in satellite photographs using R-CNN series models. We separate land and sea via marker-based watershed algorithm and perform morphology operations to specify RoI one more time, then detect vessels using R-CNN family models on specific RoI to reduce typology. Using this method, we could reduce the misdetection rate by 80% compared to using only the Fast R-CNN.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.3
• /
• pp.173-182
• /
• 2009

In this paper, we studied about the extraction of the parameter and implementation of speechreading system to recognize the Korean 8 vowel. Face features are detected by amplifying, reducing the image value and making a comparison between the image value which is represented for various value in various color space. The eyes position, the nose position, the inner boundary of lip, the outer boundary of upper lip and the outer line of the tooth is found to the feature and using the analysis the area of inner lip, the hight and width of inner lip, the outer line length of the tooth rate about a inner mouth area and the distance between the nose and outer boundary of upper lip are used for the parameter. 2400 data are gathered and analyzed. Based on this analysis, the neural net is constructed and the recognition experiments are performed. In the experiment, 5 normal persons were sampled. The observational error between samples was corrected using normalization method. The experiment show very encouraging result about the usefulness of the parameter.

• Journal of IKEEE
• /
• v.28 no.1
• /
• pp.65-71
• /
• 2024

This paper proposes a neural network that can reduce the number of parameters while reducing matching errors in occluded regions to increase the accuracy of depth maps in stereo matching. Stereo matching-based object recognition is utilized in many fields to more accurately recognize situations using images. When there are many objects in a complex image, an occluded area is generated due to overlap between objects and occlusion by background, thereby lowering the accuracy of the depth map. To solve this problem, existing research methods that create context information and combine it with the cost volume or RoIselect in the occluded area increase the complexity of neural networks, making it difficult to learn and expensive to implement. In this paper, we create a depthwise seperable neural network that enhances regional feature extraction before cost volume generation, reducing the number of parameters and proposing a neural network that is robust to occlusion errors. Compared to PSMNet, the proposed neural network reduced the number of parameters by 30%, improving 5.3% in color error and 3.6% in test loss.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_3
• /
• pp.1475-1490
• /
• 2021

Detecting oil spill area using statistical characteristics of SAR images has limitations in that classification algorithm is complicated and is greatly affected by outliers. To overcome these limitations, studies using neural networks to classify oil spills are recently investigated. However, the studies to evaluate whether the performance of model shows a consistent detection performance for various oil spill cases were insufficient. Therefore, in this study, two CNNs (Convolutional Neural Networks) with basic structures(Simple CNN and U-net) were used to discover whether there is a difference in detection performance according to the structure of CNN and distribution characteristics of oil spill. As a result, through the method proposed in this study, the Simple CNN with contracting path only detected oil spill with an F1 score of 86.24% and U-net, which has both contracting and expansive path showed an F1 score of 91.44%. Both models successfully detected oil spills, but detection performance of the U-net was higher than Simple CNN. Additionally, in order to compare the accuracy of models according to various oil spill cases, the cases were classified into four different categories according to the spatial distribution characteristics of the oil spill (presence of land near the oil spill area) and the clarity of border between oil and seawater. The Simple CNN had F1 score values of 85.71%, 87.43%, 86.50%, and 85.86% for each category, showing the maximum difference of 1.71%. In the case of U-net, the values for each category were 89.77%, 92.27%, 92.59%, and 92.66%, with the maximum difference of 2.90%. Such results indicate that neither model showed significant differences in detection performance by the characteristics of oil spill distribution. However, the difference in detection tendency was caused by the difference in the model structure and the oil spill distribution characteristics. In all four oil spill categories, the Simple CNN showed a tendency to overestimate the oil spill area and the U-net showed a tendency to underestimate it. These tendencies were emphasized when the border between oil and seawater was unclear.

• Cartoon and Animation Studies
• /
• s.33
• /
• pp.449-467
• /
• 2013

Contemporary 21st century, the rapid development of technology has achieved due to the emergence of various digital devices, a variety of media to the diversification of the limits of visual representation is reduced. Therefore, the combination of technology and art, visual arts, giving limits of getting it free to the public will feel fresh new visual impact. Such a new approach to light of a combination of technology and art, a variety of fine art and motion picture of the visual arts, such as has been recognized as a new genre. Of the resolution of the projector by utilizing the current reality and unreality beyond the boundaries of the building or structure in the city, as a schematic design of the screen projected structure and mapping of the art technology in an attempt to integrate recent has been studied in various ways. The projected structure design and the mapping of the art technology in an attempt to incorporate recent research has been diverse. In this study, as a new technology of a projection mapping to study the technique of looking for the definition of mapping practices to maximize the effectiveness of Visual Perception 3D animation was applied to a case study. A combination of 3D animation and project mapping in the future the fusion of art and technology to meet the zeitgeist with new possibilities of visual art to create synergies that is expected.

• Journal of the Korean association of regional geographers
• /
• v.13 no.5
• /
• pp.563-575
• /
• 2007

This study aims to investigate a possibility of using topographic information by web mapping in open environments. Web mapping intends to focus on a map analysis and application of the function and geo-visualization. Functions of Web topographic info-map include a spatial analysis, enlargement and minimization, movement, landuse information, user-controling 3 dimension map, landform cross-section analysis, shortest path analysis. The web system adopts SVG(scalable vector graphics), MYSQL, PHP, XML for mapping. SVG has open source policy, so everyone can use it, as well, it is effective on flexible database linkage, cartographic representation. 3D map is intended to represent 3D map by user-controlled sunshine putting pixel opacity by elevation values after making DEM. Landform is designed to show a cross-section analysis and statistics by retrieving height information from database engine with clicking two points on the map. Shortest path analysis within regions uses Dijkstra's algorithm. Near future, resultantly, the area of WebGIS will have to meet more social demands for use-created geo-information and application, so more researches are needed to be web mapping more applicable for users.

• Journal of the Korean association of regional geographers
• /
• v.1 no.1
• /
• pp.93-101
• /
• 1995

Nam Khane watershed, in the Northern Laos, consists of limestone plateau surrounded with steep slope(above 1000m), wide piedmont hill land(300-700m) and narrow alluvial plain. Opium on the plateau and up-land rice on the hill-side are cultivated for each, but its shifting agricultural activity, which degrades the forest and soil, has caused the serious environmental problems. MOS-1 satellite image and 40 points of soil samples are analyzed to identify the distribution of the shifting cultivation and to evaluate the environmental problems for Nam Khane watershed. The land use classification map is presented on the photo 2, and the value of each land use area by elevation level and soil property are showed on the table 2 and 3, respectively. Excessive agricultural activity of shifting cultivation in the Nam Khane watershed not only decreased the forest area, but also changed the primary forest of tree into secondary woodland of shrub. On the phase of soil property, it accelerated the soil and gully erosion, and acidification. To solve these environmental problems, the most important step is to settle the agriculture from shifting cultivation to permanent cropping.