• Journal of the Korean Society for Precision Engineering
• /
• v.11 no.2
• /
• pp.149-163
• /
• 1994

A novel method of dimensional measurement using machine vision, which is called Landmark Tracking System, has been developed. Its advantages come form tracking only the bright, standard shaped "landmarks" which are made from retroreflective sheets. In the design of the LTS, it is essential to know the relationship between optical parameters and their influence on system performance. Such optical parameters include the brightness of landmark image, the illumination system design, and the choice of imaging optics. And the performance of retroreflective material also plays important role in the LTS performances. Influences of such optical parameters on LTS's dimensional measurement characteristics are investigated, with respect to the retroreflective material, the imaging optics, and the illumination system. Measuremtn errors due to parameter variations are also analyzed. Experiments are performed with a LTS prototype. Retroreflective characteristics are verified, and the LTS's measurement performances are measured in the form of repeatability and accuracy. Experimental results shgow that the LTS has repeatability better than 1/30,000 of a field of view(30 degrees), and accuracy better tha 1/3,000 of a field fo view.d fo view.

• Journal of Korea Multimedia Society
• /
• v.21 no.11
• /
• pp.1244-1253
• /
• 2018

The color of traffic light is sensitive to various illumination conditions. Especially it loses the hue information when oversaturation happens on the lighting area. This paper proposes a traffic light recognition method robust to these illumination variations. The method consists of two steps of traffic light detection and recognition. It just uses the intensity and saturation in the first step of traffic light detection. It delays the use of hue information until it reaches to the second step of recognizing the signal of traffic light. We utilized a deep learning technique in the second step. We designed a deep convolutional neural network(DCNN) which is composed of three convolutional networks and two fully connected networks. 12 video clips were used to evaluate the performance of the proposed method. Experimental results show the performance of traffic light detection reporting the precision of 93.9%, the recall of 91.6%, and the recognition accuracy of 89.4%. Considering that the maximum distance between the camera and traffic lights is 70m, the results shows that the proposed method is effective.

• The KIPS Transactions:PartB
• /
• v.16B no.5
• /
• pp.385-394
• /
• 2009

Face tracking and recognition are difficult problems because the face is a non-rigid object. The main reasons for the failure to track and recognize the faces are the changes of a face pose and environmental illumination. To solve these problems, we propose a nonlinear manifold framework for the face pose and the face illumination normalization processing. Specifically, to track and recognize a face on the video that has various pose variations, we approximate a face pose density to single Gaussian density by PCA(Principle Component Analysis) using images sampled from training video sequences and then construct the GMM(Gaussian Mixture Model) for each person. To solve the illumination problem for the face tracking and recognition, we decompose the face images into the reflectance and the illuminance using the SSR(Single Scale Retinex) model. To obtain the normalized reflectance, the reflectance is rescaled by histogram equalization on the defined range. We newly approximate the illuminance by the trained manifold since the illuminance has almost variations by illumination. By combining these two features into our manifold framework, we derived the efficient face tracking and recognition results on indoor and outdoor video. To improve the video based tracking results, we update the weights of each face pose density at each frame by the tracking result at the previous frame using EM algorithm. Our experimental results show that our method is more efficient than other methods.

• Proceedings of the KIEE Conference
• /
• 2005.05a
• /
• pp.63-65
• /
• 2005

In this study, the automatic face tracking algorithm is proposed by using the color and edge information of a color image. To reduce the effects of variations in the illumination conditions, an acquired CCD color image is first transformed into YCbCr color coordinates, and subsequently the morphological image processing operations, and the elliptical geometric measures are applied to extract the refined facial area.

• Proceedings of the KSR Conference
• /
• 2004.06a
• /
• pp.1410-1412
• /
• 2004

Light flickering is caused by the degradation of power quality in electric train and can be measured by electronic illuminometer. This paper has shown the relations between voltage variations and illumination of lamps which has two kinds of incandescent lamp and 3-wavelength fluorescent lamp.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.11
• /
• pp.974-978
• /
• 2013

AVI (Automatic Vision Inspection) systems automatically detect defect features and measure their sizes via camera vision. AVI systems usually report different measurements on the same defect with some variations on position or rotation mainly because different images are provided. This is caused by possible variations from the image acquisition process including optical factors, nonuniform illumination, random noises, and so on. For this reason, conventional area based defect measuring methods have problems of robustness and consistency. In this paper, we propose a new defect size measuring method to overcome this problem, utilizing volume information that is completely ignored in the area based defect measuring method. The results show that our proposed method dramatically improves the robustness and consistency of defect size measurement.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.1194-1196
• /
• 2003

Variations in soil physical and chemical properties can affect agricultural productivity and the environmental implications of crop production. These variations are present and may be important at regional, field, and sub-field (precision agriculture) scales. Because traditional measurements are time-consuming and expensive, reflectance-based estimates of soil properties such as texture, organic matter content, water content, and nutrient status are attractive. Soil properties have been related to reflectance measured with laboratory, in-field, airborne, and satellite sensors. Both multispectral and hyperspectral instruments have been used, with both natural and artificial illumination. Varying levels of accuracy have been obtained, with the best results (r > 0.95) using hyperspectral reflectance data to estimate soil organic matter and water content.

• Journal of KIISE:Software and Applications
• /
• v.30 no.3_4
• /
• pp.372-378
• /
• 2003

Limitations on the linear discriminant analysis (LDA) for face rerognition, such as the loss of generalization and the computational infeasibility, are addressed and illustrated for a small number of samples. The principal component analysis (PCA) followed by the LDA mapping may be an alternative that ran overcome these limitations. We also show that any schemes based on either mappings or template matching are vulnerable to image variations due to rotation, translation, facial expressions, or local illumination conditions. This entails the importance of a proper preprocessing that can compensate for such variations. A simple template matching, when combined with the geometrically correlated feature-based detection as a preprocessing, is shown to outperform mapping techniques in terms of both the accuracy and the robustness to image variations.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.11
• /
• pp.5474-5490
• /
• 2017

Although two-dimensional principal component analysis (2DPCA) has been shown to be successful in face recognition system, it is still very sensitive to illumination variations. To reduce the effect of these variations, texture-based techniques are used due to their robustness to these variations. In this paper, we explore several texture-based techniques and determine the most appropriate one to be used with 2DPCA-based techniques for face recognition. We also propose a new distance metric computation in 2DPCA called Row Assembled Matrix Distance (RowAMD). Experiments on Yale Face Database, Extended Yale Face Database B, AR Database and LFW Database reveal that the proposed RowAMD distance computation method outperforms other conventional distance metrics when Local Line Binary Pattern (LLBP) and Multi-scale Block Local Binary Pattern (MB-LBP) are used for face authentication and face identification, respectively. In addition to this, the results also demonstrate the robustness of the proposed RowAMD with several texture-based techniques.

• The Bulletin of The Korean Astronomical Society
• /
• v.40 no.1
• /
• pp.53.2-53.2
• /
• 2015

Fiber Bragg gratings (FBGs) are the most compact and reliable method of suppressing atmospheric emission lines in the infrared for ground-based telescopes. It has been proved that real FBGs based filters were able to eliminate 63 bright sky lines with minimal interline losses in 2011 (GNOSIS). Inscribing FBGs on multi-core fibers offers advantages. Compared to arrays of individual SMFs, the multi-core fiber Bragg grating (MCFBG) is greatly reduced in size, resistant to damage, simple to fabricate, and easy to taper into a photonics lantern (PRAXIS). Multi-mode fibers should be used and the number of modes has to be large enough to capture a sufficient amount of light from the telescope. However, the fiber Bragg gratings can only be inscribed in the single-mode fiber. A photonic lantern bi-directionally converts multi-mode to single-mode. The number of cores in MCFBGs corresponds to the mode. For a writing system consisting of a single ultra-violet (UV) laser and phase mask, the standard writing method is insufficient to produce uniform MCFBGs due to the spatial variations of the field at each core within the fiber. Most significant technical challenges are consequences of the side-on illumination of the fiber. Firstly, the fiber cladding acts as a cylindrical lens, narrowing the incident beam as it passes through the air-cladding interface. Consequently, cores receive reduced or zero illumination, while the focusing induces variations in the power at those that are exposed. The second effect is the shadowing of the furthest cores by the cores nearest to the light source. Due to a higher refractive index of cores than the cladding, diffraction occurs at each core-cladding interface as well as cores absorb the light. As a result, any core that is located directly behind another in the beam path is underexposed or exposed to a distorted interference pattern from what phase mask originally generates. Technologies are discussed to overcome the problems and recent experimental results are presented as well as simulation results.