• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.1
• /
• pp.157-165
• /
• 2011

It is challenging to detect foreground objects when background includes an illumination variation, shadow or structural variation due to its motion. Basically pixel-based background models including codebook-based modeling suffer from statistical randomness of each pixel. This paper proposes an algorithm that incorporates Markov random field model into pixel-based background modeling to achieve more accurate foreground detection. Under the assumptions the distance between the pixel on the input imaging and the corresponding background model and the difference between the scene estimates of the spatio-temporally neighboring pixels are exponentially distributed, a recursive approach for estimating the MRF regularizing parameters is proposed. The proposed method alternates between estimating the parameters with the intermediate foreground detection and estimating the foreground detection with the estimated parameters, after computing it with random initial parameters. Extensive experiment is conducted with several videos recorded both indoors and outdoors to compare the proposed method with the standard codebook-based algorithm.

• Korean Journal of Remote Sensing
• /
• v.19 no.6
• /
• pp.411-419
• /
• 2003

An area corresponding to the spatial resolution of optical remote sensor imagery often includes more than one pure surface material. In such case, a pixel value represents a mixture of spectral reflectance of several materials within it. This study attempts to apply the spectral mixture analysis on forest and to evaluate the information content of endmember fractions resulted from the spectral unmixing. Landsat-7 ETM+ image obtained over the study area in the Kwangneung Experimental Forest was initially geo-referenced and radiometrically corrected to reduce the atmospheric and topographic attenuations. Linear mixture model was applied to separate each pixel by the fraction of six endmember: deciduous, coniferous, soil, built-up, shadow, and rice/grass. The fractional values of six endmember could be used to separate forest cover in more detailed spatial scale. In addition, the soil fraction can be further used to extract the information related to the canopy closure. We also found that the shadow effect is more distinctive at coniferous stands.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.6
• /
• pp.239-245
• /
• 2004

A hue-based noise-tolerant corner detector is proposed for the exact detection of the real corners in spite of the shadows and random noise. Based on the fact that the hue gradient at the border of the opaque objects' shadow is smaller than the intensity gradient in HSI (hue-saturation-intensity) color space, the effects of shadow are eliminated by introducing the hue-weighted combination of vector gradient to the proposed corner detector. Furthermore, the proposed corner detector is robust to random noise by offsetting the contribution to the corner candidate when the polarities of the color gradients of the pixel pairs are out of phase each other. Results of the experiment show that the proposed corner detector can effectively detect the real corners.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.4
• /
• pp.49-55
• /
• 2010

Cast shadow caused by an illumination condition can produce troublesome effects for face recognition system using reflectance image. Consequently, we need to separate cast shadow area from feature area for improvement of recognition accuracy. A Bilateral filter smooths image while preserving edges, by means of a nonlinear combination of nearby pixel values. Processing such characteristics, this method is suited to our purpose in illumination estimation process based on Retinex. Therefore, in this paper, we propose a new illumination normalization method based on the Bilateral filter in face images. The proposed method produces a reflectance image that is preserved relatively exact cast shadow area, because coefficient of filter is designed to multiply proximity and discontinuity of pixels in input image. Performance of our method is measured by a recognition accuracy of principle component analysis(PCA) and evaluated to compare with other conventional illumination normalization methods.

• Journal of the Korean Society of Radiology
• /
• v.4 no.1
• /
• pp.25-30
• /
• 2010

The objective of this study was to compare the resolution and density appropriate to diagnosis in chest PA radiography. In comparing the resolution, we radiographed with conventional radiography, computed radiography(CR) and digital radiography(DR) using the linear resolution phantom(Nuclear Associates-Carle Place. N.Y.). 2 radiologists and 3 radiological technologists read the resolution value by the blind test. DR, conventional radiography and CR measured 3.95, 3.58, 3.48 resolution value respectively. In analysing the density, we chose the fifty normal chest CR and DR and conventional film. We estimated the density using by densitometer(X-rite company-Model 301) in seven regions(lung field, lung field margine, mediastinum I, mediastinum II, heart shadow I, heart shadow II, diaphragm) of chest film. We adapted to analysis the Japanese chest X-ray evaluating method and table. It was scored 0(farthest density value) to 2(nearest density value). DR scored 2 at mediastinum I, mediastinum II, heart shadow I, heart shadow II and diaphragm. On the contrary with, CR scored 2 at lung field and lung field margine. Consequently, DR superior than CR and conventional radiography film compairing density and resolution. It was due to small pixel size and post processing algorithm with digital radiography.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.1
• /
• pp.17-21
• /
• 2011

This paper presents a real- time detection of on-road succeeding vehicles based on low level edge features and a boosted cascade of Haar-like features. At first, the candidate vehicle location in an image is found by low level horizontal edge and symmetry characteristic of vehicle. Then a boosted cascade of the Haar-like features is applied to the initial hypothesized vehicle location to extract the refined vehicle location. The initial hypothesis generation using simple edge features speeds up the whole detection process and the application of a trained cascade on the hypothesized location increases the accuracy of the detection process. Experimental results on real world road scenario with processing speed of up to 27 frames per second for $720{\times}480$ pixel images are presented.

• Korean Journal of Optics and Photonics
• /
• v.9 no.3
• /
• pp.205-211
• /
• 1998

The MTF(modulation transfer function) measuring system with a linear CCD(charge coupled-device) was constructed to cvaluate a color CRT(catode ray tube). The measured MTF values were corrected by considering the spectral response and the pixel sizes of CCD. The effects of a spot size, video bandwidth, pitch of shadow mask holes, display luminance, and ambient illumination on image quality were studied. The uniformity of resolution and the contrast Ioss by ambient light of the color CRT monitor were measured, and the results were analyzed by MTFA(modulation threshold area).

• Spatial Information Research
• /
• v.7 no.1
• /
• pp.89-101
• /
• 1999

This paper represents methods to calculate heights of buildings by estimating their shadow lengths in a single and panchromatic image of the KVR-1000 camera system Shadows are identified Com brightness intensity of each pixel, and their lengths are measured. Two methods are implemented to estimate heights from shadows. One method is to use a ratio of shadow s lengths with respect to heights of reference buildings measured on site. The other method uses sun elevation angles calculated from various camera s parameters at the exposure time. The estimated heights of 20 buildings are compared with heights measured on site, and the RMS errors for each method are 1.70m and 1.75m, respectively. When a resampling method to enhance identification of shadows is used and their lengths are accordingly re-calculated, the estimated errors for each method are significantly reduced to 1.17m and 1.16m, respectively. Meanwhile, effects of land slope on shadows can be hardly obtained unless detailed DTM(digital terrain model) are available, and they introduce additional errors up to 25m.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_1
• /
• pp.989-998
• /
• 2021

In the utilization of optical satellite imagery, which is greatly affected by clouds, periodic composite technique is a useful method to minimize the influence of clouds. Recently, a technique for selecting the optimal pixel that is least affected by the cloud and shadow during a certain period by directly inputting cloud and cloud shadow information during period compositing has been proposed. Accurate extraction of clouds and cloud shadowsis essential in order to derive optimal composite results. Also, in the case of an surface targets where spectral information is important, such as crops, the loss of spectral information should be minimized during cloud-free compositing. In thisstudy, clouds using two spectral indicators (Haze Optimized Tranformation and MeanVis) were used to derive a detection technique with low loss ofspectral information while maintaining high detection accuracy of clouds and cloud shadowsfor cabbage fieldsin the highlands of Gangwon-do. These detection results were compared and analyzed with cloud and cloud shadow information provided by Sentinel-2A/B. As a result of analyzing data from 2019 to 2021, cloud information from Sentinel-2A/B satellites showed detection accuracy with an F1 value of 0.91, but bright artifacts were falsely detected as clouds. On the other hand, the cloud detection result obtained by applying the threshold (=0.05) to the HOT showed relatively low detection accuracy (F1=0.72), but the loss ofspectral information was minimized due to the small number of false positives. In the case of cloud shadows, only minimal shadows were detected in the Sentinel-2A/B additional layer, but when a threshold (= 0.015) was applied to MeanVis, cloud shadowsthat could be distinguished from the topographically generated shadows could be detected. By inputting spectral indicators-based cloud and shadow information,stable monthly cloud-free composited vegetation index results were obtained, and in the future, high-accuracy cloud information of Sentinel-2A/B will be input to periodic cloud-free composite for comparison.

• Current Optics and Photonics
• /
• v.2 no.6
• /
• pp.554-562
• /
• 2018

This study presents a color 3D scanner based on the laser structured-light imaging method that can simultaneously acquire 3D shape data and color of a target object using a single camera. The 3D data acquisition of the scanner is based on the structured-light imaging method, and the color data is obtained from a natural color image. Because both the laser image and the color image are acquired by the same camera, it is efficient to obtain the 3D data and the color data of a pixel by avoiding the complicated correspondence algorithm. In addition to the 3D data, the color data is helpful for enhancing the realism of an object model. The proposed scanner consists of two line lasers, a color camera, and a rotation table. The line lasers are deployed at either side of the camera to eliminate shadow areas of a target object. This study addresses the calibration methods for the parameters of the camera, the plane equations covered by the line lasers, and the center of the rotation table. Experimental results demonstrate the performance in terms of accurate color and 3D data acquisition in this study.