• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.100.3-100
• /
• 2002

This paper presents the method for detection and tracking of multiple humans robustly in mobile platform. The perception of human is performed in real time through the processing of images acquired from a moving stereo vision system. We performed multi-cue integration such as human shape, skin color and depth information to detect and track each human in moving background scene. Human shape is measured by edge-based template matching on distance transformed image. Improving robustness for human detection, we apply the human face skin color in HSV color space. And we could increase the accuracy and the robustness in both detection and tracking by applying random sampling stochastic estimati...

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2005년도 춘계종합학술대회
• /
• pp.828-831
• /
• 2005

본 논문에서는 얼굴을 검출하기 위해서 컬러영상에서 눈동자 템플릿을 사용한 얼굴을 검출하는 방법에 관해 제안하였다. 전체 시스템의 구성은 크게 피부색 모델에 의한 피부 영역을 검출하고 검출된 피부 영역에 타원을 적용하여 얼굴영역을 찾은 뒤 템플릿을 사용하여 눈동자를 추출하여 정규화 된 얼굴을 검출하는 단계로 이루어 졌다. 특히 타원을 적용할 때와 눈동자 템플릿을 적용할 때는 모멘트를 사용하였으며, 눈동자를 추출할 때 벡터를 기반으로 하기 때문에 사이즈에 제한 없이 자유로운 변형이 가능할 뿐만 아니라 눈동자 템플릿을 사용하면 눈동자의 위치와 크기를 동시에 얻어 낼 수 있었다. 마지막으로 이렇게 검출된 얼굴을 기울어진 각도만큼 회전시켜 정규화 된 얼굴을 검출 할 수 있었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권8호
• /
• pp.3806-3825
• /
• 2016

This paper brings out a neoteric frame of reference for visual semantic based 3d video search and retrieval applications. Newfangled 3D retrieval application spotlight on shape analysis like object matching, classification and retrieval not only sticking up entirely with video retrieval. In this ambit, we delve into 3D-CBVR (Content Based Video Retrieval) concept for the first time. For this purpose we intent to hitch on BOVW and Mapreduce in 3D framework. Here, we tried to coalesce shape, color and texture for feature extraction. For this purpose, we have used combination of geometric & topological features for shape and 3D co-occurrence matrix for color and texture. After thriving extraction of local descriptors, TB-PCT (Threshold Based- Predictive Clustering Tree) algorithm is used to generate visual codebook. Further, matching is performed using soft weighting scheme with L₂ distance function. As a final step, retrieved results are ranked according to the Index value and produce results .In order to handle prodigious amount of data and Efficacious retrieval, we have incorporated HDFS in our Intellection. Using 3D video dataset, we fiture the performance of our proposed system which can pan out that the proposed work gives meticulous result and also reduce the time intricacy.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2003년도 학술회의 논문집 정보 및 제어부문 B
• /
• pp.528-531
• /
• 2003

Recognition of licence plate becomes a key issue to many traffic related application such as road traffic monitoring or parking lots access control. In this paper, the brightness, YIQ and HSI methods were used to locate a license. After the characters in license plate were extracted, template matching method was applied for character recognitions. To test the performance of the proposed algorithm, images of seventy vehicle were tested. The success rates for license plate and character recognition were approximately 99%, and 96%, respectively

• 정보처리학회논문지B
• /
• 제17B권3호
• /
• pp.207-214
• /
• 2010

본 논문에서는 실제 도로환경의 신호등 및 속도표지판 영역 검출 및 인식 방법을 제안하였다. 밝기정보 및 HIS 컬러모델에기반한 색상정보를 이용하여 신호등을 인식하였다. 또한 HSI 컬러정보로부터 적색강도를 추정함으로써 속도 표지판을 검출하였다. 표지판의 경사여부를 판단하여 시계방향, 반시계방향으로 각각 표지판을 회전시켜 기울기를 보정한 후 인식을 행함으로써 인식률을 제고하였다. 도로환경의 동영상을 대상으로 인식을 행한 결과 신호등과 속도표지판이 혼합된 영상에서도 매우 강건한 인식 결과를 보인다.

• Smart Structures and Systems
• /
• 제17권6호
• /
• pp.935-956
• /
• 2016

With the help of advanced image acquisition and processing technology, the vision-based measurement methods have been broadly applied to implement the structural monitoring and condition identification of civil engineering structures. Many noncontact approaches enabled by different digital image processing algorithms are developed to overcome the problems in conventional structural dynamic displacement measurement. This paper presents three kinds of image processing algorithms for structural dynamic displacement measurement, i.e., the grayscale pattern matching (GPM) algorithm, the color pattern matching (CPM) algorithm, and the mean shift tracking (MST) algorithm. A vision-based system programmed with the three image processing algorithms is developed for multi-point structural dynamic displacement measurement. The dynamic displacement time histories of multiple vision points are simultaneously measured by the vision-based system and the magnetostrictive displacement sensor (MDS) during the laboratory shaking table tests of a three-story steel frame model. The comparative analysis results indicate that the developed vision-based system exhibits excellent performance in structural dynamic displacement measurement by use of the three different image processing algorithms. The field application experiments are also carried out on an arch bridge for the measurement of displacement influence lines during the loading tests to validate the effectiveness of the vision-based system.

• 한국염색가공학회지
• /
• 제25권2호
• /
• pp.102-109
• /
• 2013

A new series of anthraquinoid magenta dyes having alkylphenyl substituents was synthesized and applied toward pure polypropylene fibers. The affinity of the dyes toward polypropylene fibers was increased gradually with the increase of the length of alkyl substituents. The optimum length of alkyl group was determined as heptyl substituents from the practical point of view. The color values of the dyes on polypropylene fabrics displayed slight bluish red, namely magenta which is more practical than primary red in color matching. The good fastness ratings to washing, rubbing and light were obtained for the dyes having longer alkyl groups than hexyl substituents. Expecially they exhibited ratings 4 of light fastness, which is higher than primary red dyes previously reported.

• Tribology and Lubricants
• /
• 제32권5호
• /
• pp.141-146
• /
• 2016

The diketopyrrolopyrrole (DPP) pigment is a bicyclic 8-π-electron system containing two lactam units. Typical DPP derivative pigments have melting points of over 350°C and very low solubility in most solvents, and show absorption in the visible region with a molar extinction coefficient of 33,000 dm²mol⁻¹ and strong photoluminescence with maxima in the range 500–600 nm. X-ray structure analyses of DPP show that the whole molecule is almost in one plane. The phenyl rings are twisted out of the heterocyclic plane and the intermolecular hydrogen bonding between neighboring lactam NH and carbonyl units influences the structure of the DPP pigment in the solid state. In this study, mono-N-alkylation and mono-N-arylation were undertaken for Pigment Red 264 or Pigment Orange 73 with alkyl halide and aryl halide, respectively, in the presence of sodium tert-butoxide as a base catalyst to improve the solubility of DPP pigments and their application as CO₂ indicators. The synthetic yield was in the range 11–88%. The indicator dyes are highly soluble in organic solvents and shows pH-dependent absorption (λ_max 501 and 572 nm for the protonated and deprotonated forms, respectively) and emission (λ_max 524 and 605 nm for the protonated and deprotonated forms, respectively) spectra. The mono-N-alkylated and mono-N-arylated DPP pigment was identified by ¹H-NMR (¹H-Nuclear Magnetic Resonance Spectrometer), FT-IR (Fourier Transform Infrared Spectroscopy), and MS (Mass Spectrometry). According to the results of color and hue properties obtained by a color matching analyzer, the synthesized DPP pigment material can be used as a CO₂ indicator.

• IEIE Transactions on Smart Processing and Computing
• /
• 제4권4호
• /
• pp.237-250
• /
• 2015

This paper describes a hardware-oriented algorithm and its conceptual implementation in a real-time speed limit traffic sign detection system on an automotive-oriented field-programmable gate array (FPGA). It solves the training and color dependence problems found in other research, which saw reduced recognition accuracy under unlearned conditions when color has changed. The algorithm is applicable to various platforms, such as color or grayscale cameras, high-resolution (4K) or low-resolution (VGA) cameras, and high-end or low-end FPGAs. It is also robust under various conditions, such as daytime, night time, and on rainy nights, and is adaptable to various countries' speed limit traffic sign systems. The speed limit traffic sign candidates on each grayscale video frame are detected through two simple computational stages using global luminosity and local pixel direction. Pipeline implementation using results-sharing on overlap, application of a RAM-based shift register, and optimization of scan window sizes results in a small but high-performance implementation. The proposed system matches the processing speed requirement for a 60 fps system. The speed limit traffic sign recognition system achieves better than 98% accuracy in detection and recognition, even under difficult conditions such as rainy nights, and is implementable on the low-end, low-cost Xilinx Zynq automotive Z7020 FPGA.

• 한국염색가공학회지
• /
• 제25권1호
• /
• pp.65-69
• /
• 2013

PET fabrics of various luster, fiber thickness(denier), and weaving structure were dyed at the same conditions and determined their grey scale by using naked eyes, computer color matching (CCM) system, and real industry color (RIC) device to evaluate the effectiveness of RIC device developed in this study. As for the luster of fabrics, bright PET showed more differences when compared with semi-dull and full-dull. PET in both naked eyes and RIC device since the RIC device provide the real image of fabrics to observers. As for the fiber thickness, the results of naked eyes and RIC device were very similar while the result of CCM showed lower color grade. Finally, as for the weaving structures of PET fabrics, all the test results by naked eyes, CCM, and RIC device showed almost same grey scales. In these regards, the RIC device developed in this study was comparable to naked eyes by providing the real image of fabrics, however it was difficult to compare the very bright colors such as yellow and fiber thickness(denier) and weaving structure of fabrics.