http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
히스토그램 손실함수와 순차적 작업을 이용한 CCTV 영상 화질 향상
정민교(Minkyo Jeong),최종인(Jongin Choi),정제창(Jechang Jeong) 한국방송·미디어공학회 2022 한국방송공학회 학술발표대회 논문집 Vol.2022 No.6
본 논문에서는 CCTV 영상 화질을 향상하고 해상도를 높이기 위해 딥 러닝(Deep Learning)을 이용하여 잡음 제거(Denoising) 와 초해상도(Super-resolution) 작업을 수행한다. 데이터 증강(Data Augmentation)을 통한 초해상도 성능 향상을 위해서 잡음 제거 네트워크의 출력 영상을 초해상도 네트워크의 입력으로 사용하는 순차적 작업을 사용한다. 또한 딥 러닝을 이용한 영상처리에서 발생하는 평균 밝기 오차 문제를 해결하기 위한 손실함수(Loss Function)와 두 가지 이상의 순차적인 딥 러닝 작업에서 발생하는 문제점을 극복하기 위한 손실함수를 제안한다. 제안하는 손실함수는 네트워크의 출력 영상과 타겟 영상의 밝기 오차를 줄이는 것이 가능하고, 순차적 작업에서 보다 정확한 모델 성능 판단이 가능하다.
Adaptive Search Range Selection Algorithm Based on Block Complexity in Frame Rate Up-Conversion
Kangjun Lee,Jechang Jeong 한국산학기술학회 2015 SmartCR Vol.5 No.3
A frame rate up-conversion algorithm based on block texture complexity is proposed. The motion estimation process for frame interpolation uses an adaptive search range selection algorithm that considers the block texture complexity. Since the information of texture complexity is extracted from the motion estimation prediction size of the original frame, additional computational complexity is not required. In the experimental results, the objective and subjective image quality of the interpolated frames is found to be improved, and the computational complexity is reduced, when compared to bilateral motion estimation with a full search.
Experiment of HDR10 Down/Up-sampling through MATLAB Implementation
Daejun Park,Jechang Jeong 대한전자공학회 2017 대한전자공학회 학술대회 Vol.2017 No.1
As the video industry supports UHD resolution, the discussion of the HDR/WCG technology for realvideo are underway. Many techniques for light intensity and color gamut discussed by experts offer viewers an experience of realness. To encode HDR sequences, HEVC Main10 profile is used after HDR-to- SDR format conversion (i.e. HDR10 process). Through HDR10 process, the conversion from a half float 4:4:4 RGB linear-light format with high bit to 4:2:0 10bits Y’CbCr is obtained. HDR output sequence can be obtained by performing a reverse process, HEVC decoding and SDR-to-HDR format conversion. The loss of image information occurs in the above procedure, especially in Y’CbCr down/up-sampling procedure. In this work, we experimented with different filters to optimize HDR10 down/up-sampling process. We implemented the core techniques of HDR10 in Matlab programming in order to utilize the existing filters. In this paper, the necessity of the filter selection algorithm in down-conversion process is proposed. By presenting the difference between the CIE1931 x’y’ gamut of several filters, we show a variety of problems that can occur in the HDR video compression.
Bilateral frame rate upconversion algorithm based on image texture complexity compensation
Kangjun Lee,Jechang Jeong IET 2015 Electronics letters Vol.51 No.16
<P>A new bilateral frame rate upconversion algorithm using the image texture complexity characteristic is proposed. In the proposed algorithm, as the cost function is adjusted according to the image texture complexity, the accuracy of motion estimation (ME) is improved. In the experimental results, the proposed algorithm outperforms the conventional bilateral ME process by 0.32 dB.</P>
Blocking Artifacts Reduction in Image Compression with Block Boundary Discontinuity Criterion
Jeon,Byeungwoo,Jeong,Jechang 성균관대학교 1998 학술회의지원논문목록집 Vol.1998 No.-
This paper proposes a novel blocking artifacts reduction method based on the notion that the blocking artifacts are caused by heavy accuracy loss of transform coefficients in the quantization process. We define the block boundary discontinuity measure as the sum of the squared differences of pixel values along the block boundary. The proposed method compensates for selected transform coefficients so that the resultant image has a minimum block boundary discontinuity. The proposed method does not require a particular transform domain where the compensation should take place; therefore, an appropriate transform, domain can be selected at the user's discretion. In the experiments, the scheme is applied to DCT-based compressed images to show its performance.
Error Concealment Using Intra-Mode Information Included in H.264/AVC-Coded Bitstream
김동형,Seyoon Jeong,Jin Soo Choi,전광길,김승종,Jechang Jeong 한국전자통신연구원 2008 ETRI Journal Vol.30 No.4
The H.264/AVC standard has adopted new coding tools such as intra-prediction, variable block size, motion estimation with quarter-pixel-accuracy, loop filter, and so on. The adoption of these tools enables an H.264/AVC-coded bitstream to have more information than was possible with previous standards. In this paper, we propose an effective spatial error concealment method with low complexity in H.264/AVC intra-frame. From information included in an H.264/AVC-coded bitstream, we use prediction modes of intra-blocks to recover a damaged block. This is because the prediction direction in each prediction mode is highly correlated to the edge direction. We first estimate the edge direction of a damaged block using the prediction modes of the intra-blocks adjacent to a damaged block and classify the area inside the damaged block into edge and flat areas. Our method then recovers pixel values in the edge area using edge-directed interpolation, and recovers pixel values in the flat area using weighted interpolation. Simulation results show that the proposed method yields better video quality than conventional approaches.