• Journal of Digital Convergence
• /
• v.14 no.2
• /
• pp.183-190
• /
• 2016

This paper proposes algorithm to reduce the computing time in a neural network that reduces transmission of data for tracking mobile objects in surveillance networks in terms of detection and communication load. Object Detection can be defined as follows : Given image sequence, which can forom a digitalized image, the goal of object detection is to determine whether or not there is any object in the image, and if present, returns its location, direction, size, and so on. But object in an given image is considerably difficult because location, size, light conditions, obstacle and so on change the overall appearance of objects, thereby making it difficult to detect them rapidly and exactly. Therefore, this paper proposes fast and exact object detection which overcomes some restrictions by using neural network. Proposed system can be object detection irrelevant to obstacle, background and pose rapidly. And neural network calculation time is decreased by reducing input vector size of neural network. Principle Component Analysis can reduce the dimension of data. In the video input in real time from a CCTV was experimented and in case of color segment, the result shows different success rate depending on camera settings. Experimental results show proposed method attains 30% higher recognition performance than the conventional method.

• Proceedings of the IEEK Conference
• /
• 2000.06d
• /
• pp.206-209
• /
• 2000

Almost vision application systems use 2-D information by taking only one camera. Recently it arises to utilize 3-D information, which is distance from camera to object, because 2-D information is not sufficient. Therefore, we take stereo camera system. In motion detection algorithm using stereo vision, it operates like one camera system, which takes advantage of correlation, edge, and difference algorithm, when it detects any motion. At that time, to detect motion, it compares two images, which is from two cameras, to calculate disparity that contains distance information. By disparity, it can compute real distance and size of object information. We describe a motion detection algorithm which computes 3-D distance and object size in real time.

• Proceedings of the IEEK Conference
• /
• 2000.11d
• /
• pp.101-104
• /
• 2000

An efficient bit rate distribution technique that distributes available bits for multiple objects based on motion vector magnitude, size of object shape, and coding distortion is presented. This coding concept using the three parameters was exploited in MPEG-4 multiple object coding. But the scheme is likely to produce poor results such as allocating more bits to less important objects and degrading picture quality, due to the lack of analysis and research in view of human visual aspect. In this paper importance of each object is represented by the three parameters and visually analyzed. Target bits are distributed according to coding distortion using the pre-assigned shape and motion information.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.4 no.5
• /
• pp.1085-1093
• /
• 2000

An efficient bit rate distribution technique that distributes available bits for multiple objects based on motion vector magnitude, size of object shape, and coding distortion is presented. This coding concept using the three parameters was exploited in MPEG-4 multiple object coding. But the scheme is likely to produce poor results such as allocating more bits to less important objects and degrading picture quality, due to the lack of analysis and research in view of human visual aspect. In this paper importance of each object is represented by the three parameters and visually analyzed. Target bits are distributed according to coding distortion using the pre-assigned shape and motion information.

• The Bulletin of The Korean Astronomical Society
• /
• v.39 no.2
• /
• pp.82-82
• /
• 2014

One of the subjects in clouds' structure and development is small scale structure of interstellar cloud. The possibility of AU scale structure (Marscher et al. 1993; Moore & Marscher 1995; Roy et al. 2012) is discussed, and this small scale structure is considered as the result of hydrogen volume density (Moore & Marscher 1995), or small-scale chemical and other inhomogeneities (Liszt & Lucas 2000). In order to study this subject with emission line, extremely high resolution is mandatory by VLBI system. However, the alternative method could be observing the absorption line of interstellar cloud on the continuum object. In this case, the resolution would be restricted to the size of the continuum object, if the size of the object is smaller than the resolution of a used telescope. We observed the previous researchers' three objects (BLLAC, NRAO150, B0528+138), whose spectrums are changed from 1993 to 1998 (Liszt & Lucas 2000), with KVN. Through KVN observation, we found the changes of optical depth spectrum compared with the previous spectrums. We will discuss the optical depth spectrum variation by time variation and the meaning of it.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2001.04a
• /
• pp.131-136
• /
• 2001

The purpose of this paper is to develop image inspection system endows an automatic operating and measuring that the moment values are invariant with respect to variable object size and rotation. In this paper, using these moment feature vector with Hu s 7 invariant moment is also given. The characteristics of section which is applied in the mechanics used moment descriptor of invariant moment detection algorithm for image inspection system. Corresponding rates between 94% and 96% have been achived for all object tested.

• Proceedings of the Optical Society of Korea Conference
• /
• 2009.10a
• /
• pp.331-332
• /
• 2009

We present an analysis on the quality factors of the Fourier hologram generated from multiple orthographic view images of three-dimensional object. In the analysis, we analyze both the maximum size of the reconstructed object and its spatial resolution. For the maximum size of the reconstruction, we found that the main factor is the orthographic projection angle interval. Too large projection angle interval causes overlapping in the reconstruction space domain. For the spatial resolution, there are three factors, i.e. the capturing lens array pitch which determines the spatial sampling rate of the original three-dimensional objects, the maximum orthographic projection angle, and the spatial frequency bandwidth of the object. The dominant factor is determined by the relationship between those three factors.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.10d
• /
• pp.608-612
• /
• 2007

FOTA는 무선기능이 장착된 Mobile Device에 새로운 Software에 대한 알림기능이 도착하면, Software가 탐재된 서버에 접속하여 Software를 Download 받고, 그 Download한 Software를 Upgrade 하는 기능을 말한다. FOTA 기능을 장착하기 위해서 Mobile Device는 Delta Package의 사이즈를 최소화하기 위한 특별한 Binary 구조를 가지는데 두 Binary의 차이를 압축한 것을 Delta Package라고 부르며, Binary 사이에 Upgrade를 위한 여분의 Gap을 두어, 향후 수정된 내용이 있을 때, 수정사항을 공간 내에 포함할 수 있도록 한다. 바이너리를 구성하는 Object들이 Image내에 어떤 위치에 포함될 것인지를 결정하는 Scatter Loader에 따라, Binary의 구조 및 확장성, Delta의 크기를 결정하게 되는데, 이것은 Object의 Type이나 Scatter Loading File내에서 명시한 순서와는 관계가 없고, Execution Region의 분할 개수를 늘릴수록, 각 Object의 Dependency 별로 묶을수록 Delta Size가 작아지는 것을 알게 되었다. 이 논문에서는 위에서 제시한 조건이 Delta Size에 미치는 원인에 대해 분석하고, Scatter Loading File을 최적화시킬 수 있는 방안에 대해서 연구한다.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.8
• /
• pp.30-41
• /
• 1996

This paper presents a comparative study of four pattern recognition algorithms which are invariant to translations, rotations, and scale changes of the input object; namely, object shape features (OSF), geometrica fourier mellin transform (GFMT), moment invariants (MI), and centered polar exponential transform (CPET). Pattern description is obviously one of the most important aspects of pattern recognition, which is useful to describe the object shape independently of translation, rotation, or size. We first discuss problems that arise in the conventional invariant pattern recognition algorithms, or size. We first discuss problems that arise in the coventional invariant pattern recognition algorithms, then we analyze their performance using the same criterion. Computer simulations with several distorted images show that the CPET algorithm yields better performance than the other ones.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 1999.11a
• /
• pp.53-58
• /
• 1999

Recently, the size and complexity of the system we have to develop and to deal with are expanding quickly. Because of the great size of causally related network in itself, such a system will be very difficult to deal with based on the typical reduction model. One of alternatives for this is to adopt emergence-based paradigm instead of reduction-based paradigm. The first is based on the low level causality and the latter on the high level emergence. In this paper we proposed an emergence-based object model realizable in terms of engineering. It is the abstracted one from original object model using of such concepts as performance function, interest function and emotional layer. The suggested model allows us to emerge some important concepts which might be useful for implementing the complex system which can hardly be available by reduction paradigm.