• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.1
• /
• pp.69-76
• /
• 2010

The segmentation of moving object in video sequence is a core technique of intelligent image processing system such as video surveillance, traffic monitoring and human tracking. A typical method to segment a moving region from the background is the background subtraction. The steps of background subtraction involve calculating a reference image, subtracting new frame from reference image and then thresholding the subtracted result. One of famous background modeling is Gaussian mixture model (GMM). Even though the method is known efficient and exact, GMM suffers from a problem that includes false pixels in ROI (region of interest), specifically shadow pixels. These false pixels cause fail of the post-processing tasks such as tracking and object recognition. This paper presents a method for removing false pixels included in ROT. First, we subdivide a ROI by using shape characteristics of detected objects. Then, a method is proposed to classify pixels from using histogram characteristic and comparing difference of energy that converts the color value of pixel into grayscale value, in order to estimate whether the pixels belong to moving object area or shadow area. The method is applied to real video sequence and the performance is verified.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2005.07a
• /
• pp.639-642
• /
• 2005

A new dual-slope ramp (DSR) reset waveform is proposed to improve the dark room contrast ratio in AC-PDPs. The proposed reset waveform has two different voltage slopes during a ramp-up period. The first voltage slope is lower than the conventional ramp voltage slope, causing a reduction in the background luminance, whereas the second voltage slope is higher than the conventional ramp voltage slope, causing an increase in the background luminance. Thus, a bias voltage is also applied during the second voltage-slope period to adjust the background luminance and address discharge characteristics. As a result, the proposed dual-slope reset waveform can lower the background luminance, thereby improving the high dark room contrast ratio of an AC-PDP without reducing the address voltage margin

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.5
• /
• pp.487-493
• /
• 1999

To predict the background level of harmonics produced by household appliances, information on the site, capacity, and usage pattern of these loads arenecessary. However, as household appliances are distributed widely and various in type, it is difficult to know these kinds of information accurately. This paper presents a method for estimation of background level of harmonics produced by distributed harmonic sources with readily available data. Large industrial customers are excluded from this study. In this paper, customers are grouped into three classes, i.e. residential, commercial, and industrial. Typical customers for each class are assumed and characteristics of their equipments are modeled. As the proposed method does not require harmonic measurement, it can be employed to forecast voltage total harmonic distribution (VTHD) in the future. An illustrative example is described.

• Journal of Korea Multimedia Society
• /
• v.12 no.12
• /
• pp.1745-1754
• /
• 2009

PTZ (Pan-Tilt-Zoom) camera based surveillance systems are enlarging their field of application due to their wide observable area. We aimed to detect both static and moving objects in automated working space by using a PTZ camera. For object detection we used background difference method because of the high quality segmentation. However, the method has a problem called 'hole' that is caused by non-continuous surveillance of the PTZ camera and its own characteristics. Moreover, the occlusion which occurs when the moving object overlaps with the static object should be solved for robust object detection. In this paper, we suggest a region-based technique for updating background images thereby overcoming the hole and occlusion problem. Through experiments with real scenes, it was verified that meaningful static and/or moving objects were detected very well.

• Journal of Information Processing Systems
• /
• v.15 no.5
• /
• pp.1218-1230
• /
• 2019

This study proposes a novel video traffic flow detection method based on machine vision technology. The three-frame difference method, which is one kind of a motion evaluation method, is used to establish initial background image, and then a statistical scoring strategy is chosen to update background image in real time. Finally, the background difference method is used for detecting the moving objects. Meanwhile, a simple but effective shadow elimination method is introduced to improve the accuracy of the detection for moving objects. Furthermore, the study also proposes a vehicle matching and tracking strategy by combining characteristics, such as vehicle's location information, color information and fractal dimension information. Experimental results show that this detection method could quickly and effectively detect various traffic flow parameters, laying a solid foundation for enhancing the degree of automation for traffic management.

• Journal of Korea Multimedia Society
• /
• v.16 no.6
• /
• pp.746-755
• /
• 2013

This paper presents a three dimensional bilateral filter detecting target trajectory, extracting spatial target information using two dimensional bilateral filter and temporal target information using one dimensional bilateral filter. In order to discriminate edge pixel with flat background and target region spatially and temporally, spatial and temporal variance are used for an image and temporal profile. With this procedure, background and background profile are predicted without original target through two dimensional and one dimensional bilateral filter. Finally, using spatially predicted background and temporally predicted background profile, small target can be detected. For comparison of existing target detection methods and the proposed method, the receiver operating characteristics (ROC) is used in experimental results. Experimental results show that the proposed method has superior target detection rate and lower false alarm rate.

• The Research Journal of the Costume Culture
• /
• v.23 no.5
• /
• pp.793-806
• /
• 2015

This study is to explore the effect of music characteristics (i.e., likeliness and familiarity of music) on the relationship between mood and attitude toward the product in the online shopping mall selling hand-made shoes. A total of 319 consumers participated in experiments with online shopping mall stimuli with a variety of background music. In results, consumer mood positively affected attitude toward the hand-made shoe products in the online shopping mall under background music. A moderating effect of music likeliness was found in the relationship between mood and product attitude, indicating that mood more strongly affected product attitude under more liked music than under less liked music. When consumers are listening to more liked music and are in good mood, they may build their attitudes toward products independently from their mood, whereas they may build positive attitude under good mood versus negative attitudes under bad mood if they are listening to less liked music. A moderating effect of music familiarity was not found in the relationship between mood and product attitude. Based on results, it was confirmed that the S-O-R model could be applied to explain the effect of background music on consumer responses in online shopping malls. Marketers may be able to select and adjust the likeliness and familiarity of background music to better serve consumers in diverse shopping conditions, referring to the study findings.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.34 no.1 s.114
• /
• pp.69-80
• /
• 2006

The purposes of this study are to analyze the meanings of urban spaces which are the background of the Korean films, and to capture the interactions of ordinary culture and urban spaces. By reading urban spaces through films, it is possible to understand the variety of experiences that are hardly captured with direct eyes, specific and vivid urban images, and various events formed by the interactions of spaces and people. The scope of the study is the urban spaces revealed in Korean films portraying cities after the 1960's as their settings, and the total of 18 films was selected with every $4{\sim}5$ films for each time stage. With the selected films, analytical meanings were developed with considering three aspects; 1) phylogenetic meaning that simply reflects social-cultural and historical background, 2) the outer strum meaning that concerns the situation of special background and film scene, and 3) metaphorical and metanymic meaning on films. According to the appearance frequency, spatial backgrounds of film scenes are mainly alleys, main streets, railroad, loft, and riverside. And then the connection between spaces and meaning clusters was grasped, and reflected meanings were derived for every spaces. And the meaning of urban space in films was analyzed based on the meaning of developments and outer stratum. The fundamental characteristics and feelings of people in media such as films are more emphasized than in real world. Urban space is not considered as a simple visible shell, but is recognized as 'a real situation' created by people. The intension of this study was to open the possibility of the various views of urban spaces. The construction of the urban space should be approached from a perspective of creating new places at where the space and human beings interact with considerations of stories of various human lives. I hope new vistas can be opened up for the research subjects and methodologies about the hereafter study of urban spaces through the mutual communications with various adjacent regions including films.

• Restorative Dentistry and Endodontics
• /
• v.25 no.1
• /
• pp.71-77
• /
• 2000

The color of an esthetic restorative material is controlled primarily by thickness of the material and background color. Although the effects of the two factors on the color coordinates of esthetic dental materials have been reported, the mechanism has not been clarified well enough to explain the effects quantitatively. The purpose of this study was to evaluate the effect of thickness and background color on the color of tooth colored restorative materials quantitatively. One hundred sixty samples were fabricated from two commercial light-cured composite resins and two commercial compomers. The color characteristics and changes in the color coordinates were measured by a tristimulus colorimeter (Model TC-6FX, Tokyo Denshoku Co. Japan) using the CIELAB system. The results were as follows: 1. As thickness increased from 1.0 to 4.0mm, values of $L^*$ $a^*$ $b^*$ changed irregulary for white and dentin color background, but showed no obvious difference in color for black background. 2. The colors of composite resins and compomers were significantly influenced by background color. 3. The color difference was recognized even the same shade name in four representative kinds of composite resins and compomers. 4. As thickness changed, values of color difference for same products and same background color showed constancy, but showed difference for different background color.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.12
• /
• pp.1122-1129
• /
• 2015

This paper suggests a method of detecting traffic lights for vehicles by combining the HSV(hue saturation value) color model, morphometric characteristics, and location information appearing on consecutive images in daytime. In order to detect the traffic light, the color corresponding to the signal lights should be explored. It is difficult to detect traffic lights among colors of lights from buildings, taillight of cars, leaves, placards, etc. The proposed algorithm searches for the traffic lights from many candidates using morphometric characteristics and location information in consecutive images. The recognition process is divided into three steps. The first step is to detect candidates after converting RGB channel into HSV color model. The second step is to extract the boundaries between the housing of traffic lights and background by exploiting the assumption that the housing has lower brightness than the surrounding background. The last step is to recognize the signal light after eliminating the false candidates using morphometric characteristics and location information appearing on consecutive images. This paper demonstrates successful detection results of traffic lights from various images captured on the city roads.