• Journal of the Korea Society of Computer and Information
• /
• v.14 no.4
• /
• pp.47-57
• /
• 2009

Event detection and recognition is an active and challenging topic recent in Computer Vision. This paper describes a new method for recognizing events caused by human motion from video sequences in an office environment. The proposed approach analyzes human motions using Motion History Image (MHI) sequences, and is invariant to body shapes. types or colors of clothes and positions of target objects. The proposed method has two advantages; one is thant the proposed method is less sensitive to illumination changes comparing with the method using color information of objects of interest, and the other is scale invariance comparing with the method using a prior knowledge like appearances or shapes of objects of interest. Combined with edge detection, geometrical characteristics of the human shape in the MHI sequences are considered as the features. An advantage of the proposed method is that the event detection framework is easy to extend by inserting the descriptions of events. In addition, the proposed method is the core technology for event detection systems based on context-aware computing as well as surveillance systems based on computer vision techniques.

• The Journal of the Korea Contents Association
• /
• v.9 no.4
• /
• pp.45-54
• /
• 2009

The virtual world is simulated in terms of agents and the environment as the real world. Agents are able to perceive and recognize objects as well as components of the environmental elements in the virtual world. As a result, they are able to autonomously act in terms of their decision. They generate diverse situation that make the user to feel familiarity as they would be have like human beings. Such situations are constructed in terms of the concepts of the entities, relations and activities, and agents accordingly recognize the situations in terms of these concepts. In this paper, we propose the method to recognize and represent the shapes which are the most important feature among objects. Various shapes are represented in terms of primitive shapes and their spatial relations in depth. We use distance, direction, and orientation in order to represent basic spatial relation. In order to simplify basic signal processing, objects dynamically send messages of self information to agents, and refer to ontology as the knowledge base of the virtual world. Agents perceive the information from objects by comparing with schematic knowledge and instance knowledge in ontology.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.4
• /
• pp.811-819
• /
• 2017

A behavior pattern analysis algorithm based on descriptors consists of information of a moving object and temporal histogram is proposed. Background learning is performed first for detecting, tracking and analyzing moving objects. Each object is identified using an association of the center of gravity of objects and tracked individually. A temporal histogram represents a motion pattern using positions of the center of gravity and time stamp of objects. The characteristic and behavior of objects are figured out by comparing each coordinates of a position history in the histogram. Behavior information which is comprised with numbers of a start and end frame, and coordinates of positions of objects is stored and managed in the linked list. Descriptors are made with the stored information and the video retrieval algorithm is designed. We confirmed the higher retrieval accuracy compare with conventional methods.

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10b
• /
• pp.70-75
• /
• 1993

We represent a method of 3-D object recognition using multi images in this paper. The recognition process is executed as follows. Object models as prior knowledgement are generated and stored on a computer. To extract features of a recognized object, three CCD cameras are set at vertices of a regular triangle and take images of an object to be recognized. By comparing extracted features with generated models, the object is recognized. In general, it is difficult to recognize 3-D objects because there are the following problems such as how to make the correspondence to both stereo images, generate and store an object model according to a recognition process, and effectively collate information gotten from input images. We resolve these problems using the method that the collation on the basis of features independent on the viewpoint, the generation of object models as enumerating some candidate models in an early recognition level, the execution a tight cooperative process among results gained by analyzing each image. We have made experiments based on real images in which polyhedral objects are used as objects to be recognized. Some of results reveal the usefulness of the proposed method.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.48 no.6
• /
• pp.15-23
• /
• 2011

Stereo vision approach to solve the problem using a single camera three dimension precise distance measurement and object recognition method is proposed. Precise three dimensional information of objects can be obtained using single camera, a laser light and a rotating flat mirror. With a simple thresholding operation on the depth information, the segmentations of objects can be obtained. Comparing the signatures of object boundaries with database, objects can be recognized. Improving the simulation results for the object recognition by precise distance measurement are presented.

• Journal of IKEEE
• /
• v.22 no.2
• /
• pp.350-355
• /
• 2018

In this paper, a system that can classify the objects in the image according to their sizes using the reference points is proposed. The object is studied with samples. The proposed system recognizes and classifies objects by the size in images acquired using a mobile phone camera. Conventional object recognition systems classify objects using only object size. As the size of the object varies depending on the distance, such systems have the disadvantage that an error may occurs if the image is not acquired with a certain distance. In order to overcome the limitation of the conventional object recognition system, the object recognition system proposed in this paper can classify the object regardless of the distance with comparing the size of the reference point by placing it at the upper left corner of the image.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.10
• /
• pp.43-53
• /
• 2012

In the this paper, a gesture-based user interface based on object detection using predefined gesture and the tracking of the detected object is proposed. For object detection, moving objects in a frame are computed by comparing multiple previous frames and predefined gesture is used to detect the target object among those moving objects. Any object with the predefined gesture can be used to control. We also propose an object tracking algorithm, namely density based meanshift algorithm, that uses color distribution of the target objects. The proposed object tracking algorithm tracks a target object crossing the background with a similar color more accurately than existing techniques. Experimental results show that the proposed object detection and tracking algorithms achieve higher detection capability with less computational complexity.

• Korean Journal of Human Ecology
• /
• v.20 no.2
• /
• pp.377-389
• /
• 2011

The object of this study was to analyze the meaning of luxurious consumption, the subjects and the objects of luxurious consumption, the desires that propel luxurious consumption, and the luxurious consumption patterns of the past and the present. The materials and information used for this research were acquired by reviewing literatures from a library. The time frame used to separate the past and the present was the Second World War. The analyzed materials and contents for the research were the subjects and the objects of luxurious consumption, the desires that propel luxurious consumption, and the patterns of luxurious consumption. Comparing the trends of luxurious consumption of the past and present historically, the biggest differentiation between the past and present was the spread of subjects and objects of luxurious consumption. In the past, luxury consumption belonged to the wealthy only, but the accessibility of luxury consumption has increased to the point where anybody can buy what they want at will. Another difference was found in the desires that prompt luxury consumption and the consumption patterns of the past and present. Based on these results, several suggestions about luxury consumption were presented in this paper.

• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.12
• /
• pp.1053-1060
• /
• 2016

As location recognition for autonomous vehicles develops, the need for a precise map for autonomous driving has increased. A precise map must be built based upon accurate position. Recent studies have accelerated research in this area by using various sensors that calculate the accurate position by comparing and recognizing objects around the roads. However, application of such methods is limited because these studies only take objects with significant verticality into consideration. Thus, new research is needed to overcome the limitations: a method that is not constrained by the existence of certain types of surrounding objects shall be proposed. Most roads contain road marking information, such as lanes, direction signs, and pedestrian crossings. Such information on the road surface is a valuable resource for building a precise map. This paper proposes a method of building a precise map by using road marking information.

• The Bulletin of The Korean Astronomical Society
• /
• v.37 no.2
• /
• pp.75.1-75.1
• /
• 2012

Narrow-Line Seyfert 1 galaxies are arguably the most important AGN subclass in investigating the origin of the black hole mass-galaxy stellar velocity dispersion (MBH-${\sigma}$) relation because of their high accretion rates close to the Eddington limit. Currently, it is still under discussion whether NLS1s are off from the local MBH-${\sigma}$ relation. We select a sample of 325 NLS1 at relatively low redshift (z<0.1) from the SDSS DR7 by constraining FWHM of $H{\beta}$ in the range of 800-2,200 km/s. Among them, we measured stellar velocity dispersion of 40 objects which show strong stellar absorption lines, e.g. Mg b triplet(${\sim}5175{\AA}$), Fe($5270{\AA}$). In contrast, the other 285 objects show too weak stellar absorption lines to measure velocity dispersion. Using the sample of 40 objects with stellar velocity dispersion measurements, we investigate whether NLS1s follow the same MBH-${\sigma}$ relation as normal galaxies and broad line AGNs. We also test the reliability of the width of narrow lines as a surrogate of stellar velocity dispersion by comparing directly measured stellar velocity dispersion with ${\sigma}$ inferred from [O III], [N II], [S II] line widths, respectively. We will discuss the connection between AGN activity in NLS1s and galaxy evolution based on these results.