• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.410-412
• /
• 2021

This paper proposes an improved pedestrian detection method using object and background histograms. Objects detected through the HOG & SVM algorithm are detected in a square shape. Inside the square area, the background and the object area are mixed. If only the area of the object excluding the background is detected, various object-related information may be easily obtained. The size of the detected rectangle is readjusted using an xy-axis projection algorithm to fit the size of the object. And then, the improved object is detected by dividing the background and the object based on the histogram of the object in the readjusted square. The average values of precision and recall, which are reliability evaluations comparing the detected object with the original object, are 97.9% and 90%, respectively.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.5 no.4
• /
• pp.782-804
• /
• 2011

In video-based recognition systems, stationary cameras are used to monitor an area of interest. These systems focus on a segmentation of the foreground in the video stream and the recognition of the events occurring in that area. The usual approach to discriminating the foreground from the video sequence is background subtraction. This paper presents a novel background subtraction method based on a probabilistic approach. We represent the posterior probability of the foreground based on the current image and all past images and derive an updated method. Furthermore, we present an efficient fusion method for the color and edge information in order to overcome the difficulties of existing background subtraction methods that use only color information. The suggested method is applied to synthetic data and real video streams, and its robust performance is demonstrated through experimentation.

• Journal of Korea Multimedia Society
• /
• v.18 no.2
• /
• pp.138-148
• /
• 2015

Object detection methods based on background learning are widely used in video surveillance. However, when a car runs with headlights on, these methods are likely to detect the car region and the area illuminated by the headlights as one connected change region. This paper describes a method of separating the car region from the area illuminated by the headlights. First, we detect change regions with a background learning method, and extract blobs, connected components in the detected change region. If a blob is larger than the maximum object size, we extract candidate object regions from the blob by clustering the intensity histogram of the frame difference between the mean of background images and an input image. Finally, we compute the similarity between the mean of background images and the input image within each candidate region and select a candidate region with weak similarity as an object region.

• Journal of Korean Society of Rural Planning
• /
• v.22 no.2
• /
• pp.89-98
• /
• 2016

Due to the rapid economic development of Korea, the bridge have been built by government over the several years. Additionally, there are too many mountain and river and the bridge have been built in rural area. But bridge designers weren't considering the bridge landscape. And bridge was a negative factor in regional landscape. Because of this, this study surveyed the landscape preferences of rural bridge landscapes according to different bridge types. The results were summarized as follows: And this research include conducting a study on visual preference according to the bridge's type and background. And, the landscape of arch bridge in the river 1 is landscape of the highest preference. The the landscape of girder bridge in the river 2 is landscape of the lowest preference. In the river 1 and 2 landscape, high preference is observed in the arch bridge and low preference is noted in the girder bridge. In the mountain 1 and 2 landscape, high preference is observed in the cable-stayed bridge and low preference is noted in the girder bridge. In conclusion, the visual preference of bridge landscape depend on the background and bridge shape, the study said. Therefore, when bridge designer design the bridge, designer have to choose proper bridge shape according to the background. This research was conducted only in bridge landscape of rural area but the visual preference of bridge landscape can be changed according to the various background. And further research is needed to analyze visual preference of bridge landscape according to the various background.

• Journal of Fashion Business
• /
• v.13 no.6
• /
• pp.31-44
• /
• 2009

This study aims at clarifying the influence that color, tone, dot size, the combination of area ratios exercise on the harmony in dot necktie, and revealing the harmony differentiation according to the cues of various factors for pattern design. The conclusion is drawn as below, in the result that the cues which can exercise influence on the harmony of dot necktie, was analyzed by 54 stimuli. In the result of analysis of variance in order to clarify the influence which color, tone, dot size, and color area ratio exercise on dot necktie harmony, color and dot size operate appeared to be independent cues which exercise significant influence with main effect. In the result of the harmony difference analysis on color, tone, dot size, and color area ratio combination by multiple comparison, the cyan color in vivid tone was estimated to be most inharmonious in the analysis by color and tone. Viewing the harmony difference according to color and dot size, the dot size of 0.5cm in cyan was perceived to be most harmonious. Viewing the harmony difference according to color and color area ratio combination, both magenta and cyan were estimated to be positive, regardless of area ratio combination, and particularly, the case that the background was in cyan and the dots were in grey was perceived more harmonious compared to the contrary case. Viewing the harmony difference according to tone and dot sizes, the case when the dot sizes were 0.5cm, was perceived to be most positive, regardless of tone. Viewing the harmony difference according to color area ratio combination and tone, the case that the chromatic colors, cyan, magenta, and yellow was used as background, was estimated to be more harmonious, compared to the case that the achromatic color, grey was used as background. Viewing the harmony difference according to dot size and color area ratio combination, in case that the dots were in chromatic color and the background was in grey, the harmony showed difference by dot size, and the case of the dot size of 0.5cm was estimated to be most harmonious.

• Journal of Advanced Navigation Technology
• /
• v.15 no.6
• /
• pp.1132-1137
• /
• 2011

In this paper, we propose Modified Multi CAMShift Algorithm(Modified Multi Continuously Adaptive Mean Shift Algorithm) that extracts skin color area and tracks several human body parts for real-time human tracking system. Skin color area is extracted by filtering input image in predefined RGB value range. These areas are initial search windows of hands and face for tracking. Gaussian background model prevents search window expending because it restricts skin color area. Also when occluding between these areas, we give more weights in occlusion area and move mass center of target area in color probability distribution image. As result, the proposed algorithm performs better than the original CAMShift approach in multiple object tracking and even when occluding of objects with similar colors.

• Journal of Fisheries and Marine Sciences Education
• /
• v.28 no.3
• /
• pp.841-847
• /
• 2016

To study the influence of background color and substratum on hypermelanosis of starry flounder, we compared the daily food intake (DFI), the feed efficiency (FE), the survival, the growth, the ratio of pigmented area on the blind side and the ratio of hypermelanic fish duplicately reared for 180 days in dark-green FRP aquarium (control), white FRP aquarium together with dark-green substratum. The ratio of pigmented area on the blind side was significantly higher at the dark-green group than at the white group. DFI, FE and growth were higher in the dark-green substratum. Pigmented area rate and ratio of hypermelanic fish were significantly higher at the dark green group than at the high dark-green substratum. The results suggest that bright tank color and substratum bottom could inhibit the hypermelanosis.

• Journal of Environmental Impact Assessment
• /
• v.18 no.6
• /
• pp.393-399
• /
• 2009

The water of rivers and lakes are affecting by point and nonpoint source pollutions. The point source pollution can be controlled by establishing the treatment plants. However, nonpoint source pollution by various human activities is not easy to be controlled because it is difficult to determine the exits of the water flow and have many exit points. Due to contribution of nonpoint source pollution, the achievement ratio of water quality in rivers and lakes is not high. TMDL is the outstanding water quality control policy because all of the pollutant loadings from the watershed area are counting on the input loads. Our aqua-ecosystem has self-purification process by biological, physical and ecological processes. The self-purification process can remove the pollutant load from background concentrations. Usually forest area is main source of background concentrations. In Korea, about 70% of the national boundary area consists of mountains. This study is conducting as part of long-term monitoring to determine the Event Mean Concentration during a storm. The monitoring was performed on a broad-leaved tree area.

• Journal of Environmental Science International
• /
• v.8 no.3
• /
• pp.281-286
• /
• 1999

This study was conduced to examine the monthly and seasonal variation of $SO_2$, TSP, $O_3$ concentration in Dongsamdong, Pusan coastal area. And the characteristics of air pollution of this area was compared to Kwangbokdong in Pusan and Taehadong in Ullungdo. Monthly mean concentration of $SO_2$ and TSP showed lower than Kwangbokdong, $O_3$ was higher than Kwangbokdong. In case of $SO_2$, seasonal variation of Dongsamdong was remarkabler thn Kwangbokdong and the concentration difference of early morning and daytime was higher than Kwangbokdong. Taehadong showed very lower concentration as background area. In case of TSP, Dongsamdong was lower concentration and smaller diurnal change than Kwangbokdong, Taehadong showed very lower concentration as backgound area. In case of $O_3$, Dongsamdong was 10ppb higher than Kwangbokdong at daytime maximum concentration, diurnal change of concentration was higher, too. In case of frequency distribution of concentration, $SO_2$, and TSP at Dongsamdong showed higher frequency in low concentration class and $O_3$ showed in high concentration class as compared with Kwangbokdong.

• Journal of the Korean association of regional geographers
• /
• v.20 no.1
• /
• pp.92-100
• /
• 2014

This paper aimed to estimate Heonhwa-ga(獻花歌) background place, Hae-ga(海歌) background place based on the Heonhwa-ga background narrative, The main results are as follows. 1) Heonhwa-ga background place is judged as the area of the rock cliff and its suburbs in Golgok-po(Jigyeong-cheon Bugyeong-ri Namjeong-myeon, Yeongdeog county). 2) Hae-ga background place is judged as the area of the Weolsong-jeong in Uljin county, which is located in two day's distance(about 60km) from Heonhwa-ga background place. 3) Some local governments tend to estimate Heonhwa-ga background place, Hae-ga background place from the viewpoint of place marketing. So such judgement of those local governments is not persuasive.