• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2010.07a
• /
• pp.256-259
• /
• 2010

본 논문에서는 적응적 평활화 필터를 이용한 스캔된 하프톤 문서의 하프톤 잡음 제거 방법을 제안한다. 하프톤 잡음은 잡음의 편차가 커서 에지 영역과 유사한 특성을 나타내므로 일반적인 에지 보존 평활화 필터를 적용할 경우에는 잡음 제거 효과가 떨어진다. 또한 인쇄물에 주로 사용되는 집중형 도트 방식의 하프톤은 컬러 영상에서 채널간의 간섭 현상으로 인해 모아레 패턴을 생성한다. 따라서 본 논문에서는 스캔된 하프톤 문서의 하프톤 잡음과 모아레 패턴을 효과적으로 제거하기 위해 하프톤 잡음의 방향성에 기반한 적응적 평활화 필터 방법을 제안한다. 하프톤 잡음의 경우 영상의 에지와 달리 등방성을 가지므로 영상을 블록 단위로 나누어 지배적인 에지의 크기와 방향성을 살핌으로써 적응적 평활화 필터를 구성할 수 있다. 실험 결과, 제안하는 방법은 다양한 인쇄 매체를 통해 생성된 하프톤 문서에 대하여 효과적으로 하프톤 잡음을 제거하면서도 영상의 에지를 보존하는 것을 확인할 수 있었다.

• Journal of Computing Science and Engineering
• /
• v.9 no.1
• /
• pp.29-38
• /
• 2015

Human action recognition has become an important research topic in computer vision area recently due to many applications in the real world, such as video surveillance, video retrieval, video analysis, and human-computer interaction. The goal of this paper is to evaluate descriptors which have recently been used in action recognition, namely Histogram of Oriented Gradient (HOG) and Histogram of Optical Flow (HOF). This paper also proposes new descriptors to represent the change of points within each part of a human body, caused by actions named as Histogram of Changing Points (HCP) and so-called Average Speed (AS) which measures the average speed of actions. The descriptors are combined to build a strong descriptor to represent human actions by modeling the information about appearance, local motion, and changes on each part of the body, as well as motion speed. The effectiveness of these new descriptors is evaluated in the experiments on KTH and Hollywood datasets.

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.6
• /
• pp.562-570
• /
• 2012

This paper proposes a robust object tracking algorithm using object features and on-line learning based particle filter for mobile robots. Mobile robots with a side-view camera have problems as camera jitter, illumination change, object shape variation and occlusion in variety environments. In order to overcome these problems, color histogram and HOG descriptor are fused for efficient representation of an object. Particle filter is used for robust object tracking with on-line learning method IPCA in non-linear environment. The validity of the proposed algorithm is revealed via experiments with DBs acquired in variety environment. The experiments show that the accuracy performance of particle filter using combined color and shape information associated with online learning (92.4 %) is more robust than that of particle filter using only color information (71.1 %) or particle filter using shape and color information without on-line learning (90.3 %).

• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.9
• /
• pp.930-935
• /
• 2014

A Gabor filter is a linear filter used for edge detectionas frequency and orientation representations of Gabor filters are similar to those of the human visual system. In this thesis, we propose a pedestrian detection algorithm using a Gabor filter bank. In order to extract the features of the pedestrian, we use various image processing algorithms and data structure algorithms. First, color image segmentation is performed to consider the information of the RGB color space. Second, histogram equalization is performed to enhance the brightness of the input images. Third, convolution is performed between a Gabor filter bank and the enhanced images. Fourth, statistical values are calculated by using the integral image (summed area table) method. The calculated statistical values are used for the feature matrix of the pedestrian area. To evaluate the proposed algorithm, the INRIA pedestrian database and SVM (Support Vector Machine) are used, and we compare the proposed algorithm and the HOG (Histogram of Oriented Gradient) pedestrian detector, presentlyreferred to as the methodology of pedestrian detection algorithm. The experimental results show that the proposed algorithm is more accurate compared to the HOG pedestrian detector.

• Journal of Broadcast Engineering
• /
• v.18 no.4
• /
• pp.535-542
• /
• 2013

In this paper, we proposed a advanced hardware engine architecture for high speed and high detection rate image recognitions. We adopted the HOG-LBP feature extraction algorithm and more parallelized architecture in order to achieve higher detection rate and high throughput. As a simulation result, the designed engine which can search about 90 frames per second detects 97.7% of pedestrians when false positive per window is $10^{-4}$.

• Journal of Animal Environmental Science
• /
• v.4 no.2
• /
• pp.149-160
• /
• 1998

Hog manure slurry amended with sawdust was composted in pilot-scale reactor vessels using continuous aeration nuder different C/N ratios and pH conditions during composting high rate (decomposition) process. For each material two replicated piles were built and monitored over a period of three weeks. The compost piles had an initial volume of 0.18 ㎥. In this study we evaluated the temperature in compost O2 and CO2 evolution, aeration rate, NH3 concentration etc. and investigated the stability of compost during composting high rate process. According to measured results, while the maximum NH3 concentration during composting high rate process. According to measured results, while the maximum NH3 concentration during composting high rate was in the range of 213 to 412 ppm on 5th day which was near the optimum C/N(22∼24) and pH(7.5∼7.9). And then, the NH3 concentration reduced to between 22∼26 ppm by 13th day. The maximum NH3 concentration for the lower C/N(18∼19) and pH value of 6 reached 574∼1,063 ppm by the 16th through 11th days and the NH3 concentration during continuous aerated composting high rate process, it was more important to manage NH3 gas so that compost odor is reduced.

• Journal of the Semiconductor & Display Technology
• /
• v.14 no.2
• /
• pp.29-34
• /
• 2015

Traffic lights are common in cities and are important cues for the path planning of intelligent vehicles. In this paper, we propose a robust and efficient algorithm for recognizing traffic lights from video sequences captured by a low cost off-the-shelf camera. Instead of using color information for recognizing traffic lights, a shape based approach is adopted. In learning and detection phase, Histogram of Oriented Gradients (HOG) feature is used and a cascade classifier based on Adaboost algorithm is adopted as the main classifier for locating traffic lights. To decide the color of the traffic light, a technique based on histogram analysis in HSV color space is utilized. Experimental results on several video sequences from typical urban environment prove the effectiveness of the proposed algorithm.

• Asian-Australasian Journal of Animal Sciences
• /
• v.14 no.9
• /
• pp.1326-1330
• /
• 2001

This study analyzed the lowest production cost and the greatest profit to be obtained from marketing hogs to determine the optimal operation scale for family-owned farrow-to-finish farms. Data were collected from 39 farrow-to-finish farms with 500 to 5,000 inventories for two consecutive years, and treated with GLM and quadratic regression models using the REG procedure. Analysis results indicated that farms capable of marketing 2,933 and 3,286 hogs annually had the lowest production cost and the greatest profit, respectively. Further analysis attributed the lowest production cost or the highest return in farms with an optimal scale of 3,000 to a higher survival rate of the herd, as well as lower expenses in veterinary medicine, labor, utilities and fuel, transportation, and depreciation. A similar feed conversion efficiency was observed for all the farms studied. Obviously, the cost efficiencies were associated with the economy of the operation scale of hog production until it reached 3,000 hogs marketed annually for a family-run unit. Beyond the optimal scale of 3,000 hogs, good stockmanship was more difficult to maintain and the herd management deteriorated as increasing mortality confirms. It is conclude that, unless advanced management is applied, the operation scale should not expand beyond 3,000 hogs.

• Korean Journal of Animal Reproduction
• /
• v.3 no.1
• /
• pp.41-47
• /
• 1979

This experiment was carried out to clarify the methods of the F-body test in human and the B-body test in buil and hog. The effect of pH and albumin concentration on the migration of X- and Y- sperm was also investigated. The results obtained were summarized as follows: 1. In the human semen, the frequency of sperm in which an F-body is visible was different by the fluorochrome. Namely, in case of quinacrine mustard, the F-body frequency was 48.8∼43.4 percent (average 49.6%), and in case of quinacrine dihydrochloride, that was 40.7∼50.8 percent (average 42.0%). 2. The frequency of a, pp.rance of B-body was 43.4${\pm}$1.3 percent in bull semen, and 45.5${\pm}$0.7 percent in hog semen. 3. A, pp.arance of B-body in bovine semen was increased due to duration of time after washing till 12 hours. 4. Separation of X- and Y- spermatozoa using diluents with different hydrogen ion concentration was impossible. 5. A, pp.arance of B-body separated in medium with 6, 10 and 20% ovalbumin was 51.1${\pm}$2.4, 50.6${\pm}$2.5 and 58.2${\pm}$3.0 percent, respectively, and those values were significiantly higher (p<0.01) than corresponding control values.

• Journal of Biomedical Engineering Research
• /
• v.32 no.4
• /
• pp.336-344
• /
• 2011

This article describes a new recognition algorithm using correlation coefficient for intelligent wheelchair to avoid collision for elderly or disabled people. The correlation coefficient can be used to represent the relationship of two different areas. The algorithm has three steps: Firstly, we extract an edge vector using the Histogram of Oriented Gradients(HOG) which includes gradient information and unique magnitude for each cell. From this result, the correlation coefficients are calculated between one cell and others. Secondly, correlation coefficients are used as the weighting factors for normalizing the HOG cell. And finally, these features are used to classify or detect variable and complicated shapes of two wheelers using Adaboost algorithm. In this paper, we propose a new feature vectors which is calculated by weighted cell unit to classify with multiple view-based shapes: frontal, rear and side views($60^{\circ}$, $90^{\circ}$ and mixed angle). Our experimental results show that two wheeler detection system based on a proposed approach leads to a higher detection accuracy than the method using traditional features in a similar detection time.