• Journal of Multimedia Information System
• /
• 제6권4호
• /
• pp.185-190
• /
• 2019

For future autonomous cars, it is necessary to recognize various surrounding environments such as lanes, traffic lights, and vehicles. This paper presents a method of speed sign recognition from a single image in automatic driving assistance systems. The detection step with the proposed method emphasizes the color attributes in modified YUV color space because speed sign area is affected by color. The proposed method is further improved by extracting the digits from the highlighted circle region. A sequential cascade AdaBoost classifier is then used in the recognition step for real-time processing. Experimental results show the performance of the proposed algorithm is superior to that of conventional algorithms for various speed signs and real-world conditions.

• Journal of Information Processing Systems
• /
• 제13권4호
• /
• pp.818-833
• /
• 2017

This paper introduces a new algorithm that renders motion blur using triangular motion paths. A triangle occupies a set of pixels when moving from a position in the start of a frame to another position in the end of a frame. This is a motion path of a moving triangle. For a given pixel, we use a motion path of each moving triangle to find a range of time that this moving triangle is visible to the camera. Then, we sort visible time ranges in the depth-time dimensions and use bitwise operations to solve the occlusion problem. Thereafter, we compute an average color of each moving triangle based on its visible time range. Finally, we accumulate an average color of each moving triangle in the front-to-back order to produce the final pixel color. Thus, our algorithm performs shading after the visibility test and renders motion blur in real time.

• 한국멀티미디어학회논문지
• /
• 제24권1호
• /
• pp.30-39
• /
• 2021

Research in the field of health lighting has continued to advance to reproduce the color temperature of natural light which periodically changes. However, most of this research could only reproduce a uniform circadian color temperature of natural light, therefore failing to realize the characteristics of the circadian cycle of color temperature difference by latitude and longitude. To reproduce the color temperature of natural light on which the characteristics of a region are reflected, the collection technology of real-time characteristics of natural light is needed. If the color temperatures which are not within a periodical pattern due to climate changes, etc., are measured, it will be difficult to judge the occurrence (presence) of the anomalies and to reproduce the circadian cycle of the color temperature of natural light. Therefore, this study proposes an algorithm for judging the anomalies in real time based on the sliding window to reproduce the color temperature of natural light. First, the natural light characteristics DB collected through the on-site measurement were analyzed, the differential values at a one-minute interval were calculated and examined, and then representative color temperature circadian patterns by solar terms were drawn. The anomalies were then detected by the application of the sliding window that calculated the deviation of the color temperature for the measured color temperature data set, which was collected through RGB sensors, while moving along the time sequence. In addition, the presence of anomalies was verified through the comparison study between the detection results and the representative circadian cycle of the color temperature by solar term. The judgment method for the anomalies from the measured color temperature of natural light was proposed for the first time, confirming that the proposed method was capable of detecting the anomalies with an average accuracy of 94.6%.

• 정보학연구
• /
• 제5권1호
• /
• pp.99-111
• /
• 2002

원 영상에 근접한 색채 재현을 위한 선형 변환을 이용한 영상의 컬러 보정은 컬러 공간의 비 선형성으로 인해 색의 왜곡 현상이라는 문제가 발생하게 된다. 이러한 문제를 극복하기 위해 선형 이론인 임의의 평면상에 주어진 자료점들로 구성되는 베지어 곡선이 사용되어 왔다. 그러나, 이 베지어 곡선은 자료점의 개수에 따라 차수가 증가하게 되므로 수치적 계산상의 많은 제약을 받게 된다. 본 논문에서는 각 구간에서나 전체 구간에서의 차수가 3차이면서 베지어 곡선의 특성을 갖는 "3중첩 구간적 베지어 3차 곡선"(TPBC Curve; Triplicated Piecewise Bezier Cubic Curve)를 이용하였다. 이에 따른, TPBC-곡선과 20차 베지어 곡선을 이용하였을 때와 비교하여 컬러 보정 시 발생하는 왜곡 현상, 그리고 좁은 영역의 컬러 보정으로 인한 작업량의 증가를 감소시킨 결과를 보여주고자 한다. 보여주고자 한다.

• 전자공학회논문지S
• /
• 제34S권6호
• /
• pp.38-45
• /
• 1997

Skin color reappearance problem in color processing system is necessary to transform a specific color sand improve color reappearance quality as a reference color. The skin color has been situated as an important memory color not only in our lives but also in color application systems such as TV. Thus, skin color reappearance problem is more important than other color processing problem. In this paper, we propose a skin color reappearance algorithm for color enhancement in TV which use phase detector to detect the skin colors at real-time from 3.58 MHz color burst signal and color signal, comparators to discriminate the types of skin color, and micom to reprodece standard skin colors for races.

• 한국콘텐츠학회논문지
• /
• 제16권8호
• /
• pp.427-434
• /
• 2016

본 논문은 인간이 인지할 수 있는 감각들 중 인체의 회전, 방향 변화 및 움직임의 정도를 알 수 있는 근감각에서 시각 및 청각 요소로의 변환 알고리즘을 이용하여 ARM Cortex-M4에 기반한 실시간 임베디드시스템으로 구현한 방법에 초점을 맞추었다. 근감각의 입력 방식으로는 자세측정장치(AHRS : Attitude Heading Reference System)를 이용해 롤(Roll), 피치(Pitch) 및 요(Yaw) 값을 실시간 획득하고, 이들 각각의 색을 표현하는 HSI 컬러 모델의 명도(Intensity), 색상(Hue) 및 채도(Saturation)에 대응하여 변환하였다. 최종 컬러신호는 HSI 에서 RGB 컬러모델로 변환하여 획득하였다. 또한, 근감각의 세 가지 입력 값들을 음을 표현하는 요소인 옥타브(Octave), 음계(Scale) 및 음의 세기(Velocity)에 대응하여 변환한 값을 MIDI(Musical Instrument Digital Interface)를 이용해 사운드를 합성하여 출력하였다. 출력 컬러신호 및 사운드를 분석한 결과, 근감각 입력 신호가 제안한 변환 방식에 따라 실시간으로 정확하게 색과 음으로 변환, 출력됨을 확인하였다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 신호처리소사이어티 추계학술대회 논문집
• /
• pp.317-320
• /
• 2003

In this paper, we present real-time, accurate face region detection and tracking technique for an intelligent surveillance system. It is very important to obtain the high-resolution images, which enables accurate identification of an object-of-interest. Conventional surveillance or security systems, however, usually provide poor image quality because they use one or more fixed cameras and keep recording scenes without any clue. We implemented a real-time surveillance system that tracks a moving person using pan-tilt-zoom (PTZ) cameras. While tracking, the region-of-interest (ROI) can be obtained by using a low-pass filter and background subtraction. Color information in the ROI is updated to extract features for optimal tracking and zooming. The experiment with real human faces showed highly acceptable results in the sense of both accuracy and computational efficiency.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 추계종합학술대회 논문집
• /
• pp.224-227
• /
• 1999

This paper presents a design of the real-time preprocessor for CMOS image sensor suitable to the digital camera applications. CMOS image sensor offers some advantages in on-chip integration, system power reduction, and low cost. However, it has a lower-quality image than CCDs. We describe an image enhancement algorithm, which includes color interpolation, color correction, gamma correction, sharpening, and automatic exposure control, to compensate for this disadvantage, and present its efficient hardware architecture to implement on the real-time processor. The presented real-time preprocessor was designed using VHDL, and it contains about 19.2K logic gates. We also implement our system on FPGA chips in order to provide the real-time adjustment and it was successfully tested.

• 한국컴퓨터정보학회논문지
• /
• 제10권4호
• /
• pp.113-121
• /
• 2005

실시간 영상에서 사람의 얼굴을 검출하는 것은 얼굴 인식 분야에 있어서 주요한 관심 분야 중의 하나이다. 본 본문에서는 실시간 입력되는 영상에서 피부색과 Haar-like feature를 이용한 얼굴 검출 알고리즘을 제안하였다. 제안된 알고리즘은 YCbCr 색 공간에서의 차 연산 기법을 이용하여 이동 물체의 움직임 영역을 ROI(region of interest)로 선정하고 Haar-like feature를 이용하여 얼굴 후보영역을 선정한 다음 피부색 정보를 이용하여 얼굴을 검출하였다. 특히, 가변적으로 선정되는 ROI 영역에 대하여 피부색 정보와 특징 정보를 이용함으로서 실시간 영상에 대하여 처리 속도의 향상과 비슷한 특징 또는 색상을 가진 영상이 얼굴로 검출되는 오류를 방지하였다. 실험 결과는 기존의 연구에 비해 30%의 처리 속도 향상과 96.8%의 검출 성공률을 보였다.

• 한국멀티미디어학회논문지
• /
• 제19권2호
• /
• pp.180-188
• /
• 2016

In this paper, we propose a fire detection algorithm based on motion information and color information analysis. Conventional fire detection algorithms have as main problem the difficulty to detect fire due to external light, intensity, background image complexity, and little fire diffusion. So we propose a fire detection algorithm that accurate and fast. First, it analyzes the motion information in video data and then set the first candidate. Second, it determines this domain after analyzing the color and the domain. This algorithm assures a fast fire detection and a high accuracy compared with conventional fire detection algorithms. Our algorithm will be useful to real-time fire detection in real world.