• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 추계종합학술대회 논문집(4)
• /
• pp.9-12
• /
• 2000

This paper proposes an improved image illumination estimation method based on the conventional color constancy algorithm. The most important process of color constancy algorithm is the estimation of the spectral distributions of illuminant of an input image. To estimate of the spectral distributions of illuminant of an input image, we use the brightest pixel values and the values of surface reflectance of an input image using a principal component analysis of the given munsell chips. We estimate a CIE tristimulus values of an input image using the estimated .spectral distribution of illuminant and recover an image by scaling it regularity. From the experimental results, the proposed method was effective in estimating the image illumination

• 전자공학회논문지S
• /
• 제36S권12호
• /
• pp.76-84
• /
• 1999

본 논문에서는 항공 영상을 이용한 통합된 비행체의 위치 추정기법을 제안하였다. 제안한 항법 변수 추정 시스템은 상대위치 추정과 절대위치 추정 두 부분으로 구성되어 있다. 상대위치 추정 기법은 연속된 두 영상의 상대적 움직임을 추정하고 이것을 누적함으로써 현재의 위치를 추정한다. 이러한 단순한 누적 방법으로 비행이 진행됨에 따라 오차가 점차 증가하게 된다. 그러므로 상대위치 추정 부분에서 발생하는 오차를 줄일 수 있는 절대위치 추정기법이 필요하다. 본 논문의 절대위치 추정기법은 영상정합과 DEM (Digital Elevation Model) 정보를 이용하는 방법으로 구성되어 있다. 영상정합을 위하여 robust oriented Hausdorff measure (ROHM)을 사용하였으며 DEM 정합을 위하여 여러 장의 영상 쌍을 사용하는 알고리듬을 이용하였다. 네 개의 항공영상을 이용한 컴퓨터 시뮬레이션을 통해 제안한 방법의 효율성을 보였다.

• 융합신호처리학회논문지
• /
• 제24권1호
• /
• pp.69-75
• /
• 2023

최근 동물 행동 분석 및 건강관리 분야를 중심으로 딥러닝 기반 동물 자세 추정 기법에 대한 관심이 높아지고 있다. 그러나 기존 동물 자세 추정 기법은 영상에서 신체 부위가 가려지거나 존재하지 않을 경우 좋은 성능을 보이지 않는다. 특히 꼬리나 귀가 가려진 경우, 반려견의 행동 및 감정 분석의 성능에도 심각한 영향을 미친다. 본 논문에서는 이러한 다루기 힘든 문제를 해결하기 위해, 이미지 아웃페인팅 네트워크를 자세 추정 네트워크에 연결하여 이미지 외부에 존재하는 반려견의 신체를 복원한 확장된 이미지를 생성하여 반려견의 자세를 추정하는 단순하면서도 새로운 접근방법을 제안하였고, 제안된 방법의 실현가능성을 검토하는 예비 연구를 수행하였다. 이미지 아웃페인팅 모델로는 CE-GAN과 트랜스포머 기반의 BAT-Fill을 사용하였고, 자세 추정 모델로는 SimpleBaseline을 사용하였다. 실험 결과, 크롭된 입력 이미지에서 반려견의 자세를 추정하였을 때보다, BAT-Fill을 사용하여 아웃페인팅된 확장 이미지에서 반려견의 자세를 추정하였을 때 자세 추정의 성능이 향상되었다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1998년도 추계종합학술대회 논문집
• /
• pp.143-146
• /
• 1998

A new stereoscopic codec. structure using MPEG-2 multiview profile is presented in this paper. In the suggested codec., the left image is coded with motion estimation in the base layerand the right image is coded with disparity estimation in the enhancement layer. Since it is possible to calculate rough motion of the right image sequence with disparity and motion of the left image sequence, motion compensation of the enhancement layer is performed without motion estimation. Since the proposed codec. does not perform motion estimation in the enhancement layer encoding, it is simple and reduces the encoding time. We compared the PSNR of encoded image with three different structured codec., and the experimental results show that suggested codec. has comparable with other codecs.

• 전기전자학회논문지
• /
• 제21권1호
• /
• pp.46-65
• /
• 2017

This paper proposes a fast patch-based de-blurring algorithm including kernel estimation based on the angle between the edge and the blur direction. For de-blurring, image patches from the most informative edges in the blurry image are used to estimate a kernel with low computational cost. Moreover, the kernels of each patch are estimated based on the correlation between the edge direction and the blur direction. This makes the final kernel more reliable and creates an accurate latent image from the blurry image. The combination of directionally oriented kernel estimation and patch-based de-blurring is faster and more accurate than existing state-of-the art methods. Experimental results using various test images show that the proposed method achieves its objectives: speed and accuracy.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1997년도 한국자동제어학술회의논문집; 한국전력공사 서울연수원; 17-18 Oct. 1997
• /
• pp.1722-1725
• /
• 1997

This paper presents image analysis method using a Markov random field(MRF) model. Particulary, image esgmentation is to partition the given image into regions. This scheme is first segmented into regions, and the obtained domain knowledge is used to obtain the improved segmented image by a Markov random field model. The method is a maximum a posteriori(MAP) estimation with the MRF model and its associated Gibbs distribution. MAP estimation method is applied to capture the natural image by TMS320C80(MVP) and to realize the segmented image by a MRF model.

• 한국멀티미디어학회논문지
• /
• 제17권11호
• /
• pp.1270-1278
• /
• 2014

The modern infrared (IR) imaging systems use mainly one or more wavelength bands among short wavelength IR (SWIR), middle wavelength IR (MWIR), and long wavelength IR (LWIR) bands. In the process of IR image synthesis and modeling, IR image wavelength-band conversion which transforms arbitrary band image to other band one is required. The wavelength-band conversion procedure includes a temperature estimation process of an object surface. However, in this procedure, an approximated Planck's radiation equation causes errors in estimated temperature. In this paper, we propose an estimation temperature error attenuation method in IR image band conversion procedure. The estimated temperature is corrected with a slope information of radiance according to it. The corrected temperature is used for generation of the other band IR image. The verification of proposed method is demonstrated through the simulation.

• 조명전기설비학회논문지
• /
• 제22권7호
• /
• pp.37-42
• /
• 2008

In this paper, a real-time multiview video coding system using fast disparity estimation is proposed. In the multiview encoder, adaptive disparity-motion estimation (DME) for an effective 3-dimensional (3D) processing are proposed. That is, by adaptively predicting the mutual correlation between stereo images in the key-frame using the proposed algorithm, the bandwidth of stereo input images can be compressed to the level of a conventional 2D image and a predicted image also can be effectively reconstructed using a reference image and adaptive disparity vectors. Also, in multiview decoder, intermediate view reconstruction (IVR) using adaptive disparity search algorithm (DSA) for real-time multiview video processing is proposed. The proposed IVR can reduce a processing time of disparity estimation by selecting adaptively disparity search range. Accordingly, the proposed multiview video coding system is able to increase the efficiency of the coding rate and improve the resolution.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1452-1457
• /
• 2004

In this paper, a method of measuring the length of defects on the wall and restructuring the defect image is proposed based on the estimation algorithm of a camera orientation which uses the declination angle of a laser slit beam. The estimation algorithm of the horizontally inclined angle of CCD camera adopts a 3-dimensional coordinate transformation of the image plane where both the laser beam and the original image of the defects exist. The estimation equation is obtained by using the information of the beam projected on the wall and the parameters of this equation are experimentally obtained. With this algorithm, the original image of the defect can be reconstructed to an image normal to the wall. From the result of a series of experiments, the measuring accuracy of the defect is measured within 0.5% error bound of real defect size under 30 degree of the horizontally inclined angle. The proposed algorithm provides the method of reconstructing the image taken at any arbitrary horizontally inclined angle to the image normal to the wall and thus, it enables the accurate measurement of the defect lengths only by using a single camera and a laser slit beam.

• 제어로봇시스템학회논문지
• /
• 제8권1호
• /
• pp.37-45
• /
• 2002

A method of measuring the length of defects on the wall and restructuring the defect image is proposed based on the estimation algorithm of a camera orientation, which uses the declination angle of a laser slit beam. The estimation algorithm of the horizontally inclined angle of CCD camera adopts a 3-dimensional coordinate transformation of the image plane where both the laser beam and the original image of the defects exist. The estimation equation is obtained by using the information of the beam projected on the wall and the parameters of this equation are experimentally obtained. With this algorithm, the original image of the defect can be reconstructed as an image normal to the wall. From the result of a series of experiments, the measuring accuracy of the defect is measured within 0.5% error bound of real defect size under 30 degree of the horizontally inclined angle. The proposed algorithm provides the method of reconstructing the image taken at any arbitrary horizontally inclined angle as the image normal as the wall and thus, it enables the accurate measurement of the defect lengths by using a single camera and a laser slit beam.