• 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.

• Proceedings of the IEEK Conference
• /
• 1998.06a
• /
• pp.271-274
• /
• 1998

Ultrasonic sensors are becoming indispensable components in every sector of automation equipments due to many advantages. But the main purposes of the noncontact sensing device are rather narrowly confined within object detection and distance measurement. To widen the realm of the applications to object recognition, ultrasonic sensors need to improve the recognition resolution to a certain amount. To resolve the problem of spatial resolution restriction, an increased number of the sensors in the forms of a linear array or 2-dimensional array of the sensor has been used. Also better resolution has been obtained by shifting the array in several steps using mechanical actuators. For an object recognition using ultrasonic sensors, measurements of distance, shift, oblique angle in certain ranges should be obtained. But a little attention has been paid to the measurement of angles. In this paper we propose a practical method for an object angular value detection in addition to distance measurement in ultrasonic sensor array system with little additional hardware burden. Using the established measurement look-up table for the variations of distance, shift, angle and transmitter voltages for each sensor characteristics, a set of different return echo signals for adjacent receivers are processed to provide enhanced angular value reading for an object.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.4 no.3
• /
• pp.27-32
• /
• 2002

This study attempted to make a comparative analysis of dress and architecture to investigate the spatial effect of transparency expressed in fashion. As a result, the following findings were obtained: First, the openness of the space. It means that the human body or the dress inside it can be seen through or the inside space is opened. The volume, form and color of the undergarment seen through this transparent outer garment brings about any change to design. Also, it can be found that the role of the space is further extended as the inside space is seen through outwardly due to the outer garment. Second, interpenetration of the internal and external space. That the human body and the undergarment are seen through due to transparent dress brings about the linkage between spaces and opens the inside outwardly. Third, the briskness of the space. The trait of transparency that exposes the object behind outwardly as it is causes its form and space to be activated and conveys its spatial briskness.

• IE interfaces
• /
• v.18 no.1
• /
• pp.82-87
• /
• 2005

Most of virtual reality systems ask users to control 3D objects or to navigate 3D world using 3D controllers. To maximize the human performance in the control, the design of virtual reality system and its input and output devices should be optimized. In this study, an experiment was designed to investigate the effects of three resolution factors of a virtual reality system on the human performance. Six subjects conducted the experiment for the factors; two frame rates, three spatial resolutions, and three pictorial contents. The result showed that the greater the spatial resolution was, the higher the human performance was. For the temporal resolution, fixed frame rate at 18 Hz was better than the varied maximized frame rate. For the pictorial contents, the virtual space with orientation cues marked the greatest performance than the other two conditions; the virtual space without any orientation cue and the virtual space like real world. These results could be applied for the design of virtual reality systems.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.8
• /
• pp.60-67
• /
• 1996

In this paper, we propose a new temporal interpolation method based on spatial filtering. Compared with the conventional method, the proposed one may use a few adjacent frames and apply temporal lowpass filtering. To develop this method, we follow the basic approach of sampling rate conversion. Additionally, we use some assumption of video sequence : moving object has constant velocity rigid translational motion. From them, spatial filtering for temporal sampling rate conversion is described. This method has a lot of noise immunity on a motion vector and doesn't make a great difference from the original frame. The interpolated frame shows moderate change even there is a great time difference. This method has exactly same description of motion adaptive spatial filter which has an efficient temporal band-limiting characteristics. It imposes the possibility to make video sequence with good pictural quality.

• Journal of The Korean Digital Architecture Interior Association
• /
• v.12 no.2
• /
• pp.61-66
• /
• 2012

In space syntax, the mathmatical process to get a integration could be restrictive in understanding spatial configuration since it is based on only one behavior model. In this study, As another approach to spatial configuration analysis based on behavioral model, there is the simulation tracking analysis model that simulates the movements of human in the space and analyze them. In this study, the relationship between integration and behavioral model will be defined and the similarities and the differences between space syntax and the simulation tracking analysis model will be demonstrated. Furthermore, these two analysis models will be understood as a variety of tools that can analyze an object in multiple viewpoints.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.153-155
• /
• 2003

Laser scanning has become a viable technique for the collection of a large amount of accurate 3D point data densely distributed on the scanned object surface. The inherent 3D nature of the sub-randomly distributed point cloud provides abundant spatial information. To explore valuable spatial information from laser scanned data becomes an active research topic, for instance extracting digital elevation model, building models, and vegetation volumes. The sub-randomly distributed point cloud should be segmented and classified before the extraction of spatial information. This paper investigates some exist segmentation methods, and then proposes an octree-based split-and-merge segmentation method to divide lidar data into clusters belonging to 3D planes. Therefore, the classification of lidar data can be performed based on the derived attributes of extracted 3D planes. The test results of both ground and airborne lidar data show the potential of applying this method to extract spatial features from lidar data.

• Korean Journal of Remote Sensing
• /
• v.26 no.6
• /
• pp.731-740
• /
• 2010

A region merging technique is suggested in this paper for the segmentation of high-spatial resolution imagery. It employs a region growing scheme based on the region adjacency graph (RAG). The proposed algorithm uses directional neighbor-line average feature vectors to improve the quality of segmentation. The feature vector consists of 9 components which includes an observation and 8 directional averages. Each directional average is the average of the pixel values along the neighbor line for a given neighbor line length at each direction. The merging coefficients of the segmentation process use a part of the feature components according to a given merging coefficient order. This study performed the extensive experiments using simulation data and a real high-spatial resolution data of IKONOS. The experimental results show that the new approach proposed in this study is quite effective to provide segments of high quality for the object-based analysis of high-spatial resolution images.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.1 s.39
• /
• pp.27-34
• /
• 2006

Recently, the study about the technology which effectively manage spatial information is actively conducted. For the effective knowledge inquiry, various extended data mining methods are applied in spatial data mining. However, former spatial association rule system appears the problem that does not reflect various non-spatial property along the inquiries because it searches the rule from the calculation among predicates. To resolve the problem, present study suggests the system that extends the inquiries using in spatial database, searches the association rule among non-spatial object property after setting the data based on space information. Especially, the model which is applicable to geographical information system is embodied. Embodied system with this method enables to search more useful spatial association rule in real life since it shows high migration property with extended spatial database and considers spatial property and various non-spatial property.

• The KIPS Transactions:PartD
• /
• v.11D no.7 s.96
• /
• pp.1399-1408
• /
• 2004

Because there are so many spatio-temporal data in Moving Object Databases, a single disk system can not gain the fast response time and tota throughput. So it is needed to take a parallel processing system for the high effectiveness query process. In these existing parallel process-ing system. it does not consider characters of moving object data. Moving object data have to be thought about continuous report to the Moving Object Databases. So it is necessary think about the new Declustering System for the high performance system. In this paper, we propose the new Dechustering Policies of Moving objet data for high effectiveness query processing. At first, consider a spatial part of MBB(Minimum Bounding Box) then take a SD(SemiAllocation Disk) value. Second time, consider a SD value and time value which is node made at together as SDT-Proximity. And for more accuracy Declustering effect, consider a Load Balancing. Evaluation shows performance improvement of aver-age %15\%$ compare with Round-Robin method about $5\%\;and\;10\%$ query area. And performance improvement of average $6\%$ compare with Spatial Proximity method.