Minhun Lee

Mr. Minhun Lee

Computer Engineering, Kwangwoon University, Seoul, Republic of Korea
orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 April 2023 in IEIE Transactions on Smart Processing & Computing
Verified
Journal Article
Closed access
MLMinhun Lee
Minhun Lee
HSHyeonJu Song
HyeonJu Song
JPJeeyoon Park
Jeeyoon Park
BJByeungwoo Jeon
Byeungwoo Jeon
JKJungwon Kang
Jungwon Kang
DSDonggyu Sim
Donggyu Sim
Versatile Video Coding (H.266/VVC) is the newest video coding standard jointly developed by the Joint Video Experts Team (JVET), which is organized by the ITU-T Video Coding Experts Group (VCEG) and the ISO/IEC Moving Picture Experts Group (MPEG). H.266/VVC provides about 40% bitrate reduction compared with High Efficiency Video Coding (H.265/HEVC) for the same visual quality. This paper introduces in detail the core structure of H.266/VVC by highlighting its features within block partitioning structure, intra/inter prediction, transform, quantization, and in-loop filtering, compared to its predecessor (H.265/HEVC). H.266/VVC yields significantly improved the coding performance, but it increased the computational complexity, particularly for the encoder side, which remains a problem to be tackled for successful commercialization in the future. This paper examined the statistical performance of H.266/VVC coding tools from the bitstreams encoded by the VVC test model (VTM12.0) encoder through rate-distortion optimization under the JVET common test conditions. In addition, the complexity and performance analyses are conducted on the block partitioning structure and group of picture structure. It is expected that an optimized H.266/VVC encoder can be designed and developed by minimizing the coding loss based on the analysis data.

9 March 2023 in IEEE Access
Verified
Journal Article
Open access
MLMinhun Lee
Minhun Lee
HCHansol Choi
Hansol Choi
JKJihoon Kim
Jihoon Kim
JDJihoon Do
Jihoon Do
HKHyoungjin Kwon
Hyoungjin Kwon
SOSeoung-Jun Oh
Seoung-Jun Oh
This paper presents a method to effectively compress the intermediate layer feature map of a convolutional neural network for the potential structures of Video Coding for Machines, which is an emerging technology for future machine consumption applications. Notably, most extant studies compress a single feature map and hence cannot entirely consider both global and local information within the feature map. This limits performance maintenance during machine consumption tasks that analyze objects with various sizes in images/videos. To address this problem, a multiscale feature map compression method is proposed that consists of two major processes: receptive block based principal component analysis (RPCA) and uniform integer quantization. The RPCA derives the complete basis kernels of a feature map by selecting a set of major basis kernels that can represent a sufficient percentage of global or local information according to the variable-size receptive blocks of each feature map. After transforming each feature map using the set of major basis kernels, a uniform integer quantizer converts the 32-bit floating-point values of the set of major basis kernels, corresponding RPCA coefficients, and a mean vector to five-bit integer representation values. Experiment results reveal that the proposed method reduces the amount of feature maps by 99.30% with a loss of 8.30% in the average precision ( AP ) on the OpenImageV6 dataset and 0.77% in APM and 0.47% in APL on the MS COCO 2017 validation set while outperforming previous PCA-based feature map compression methods even at higher compression rates.

26 September 2023 in Electronics
Verified
Journal Article
Open access
PDF file
MLMinhun Lee
Minhun Lee
SPSeungjin Park
Seungjin Park
SOSeoung-Jun Oh
Seoung-Jun Oh
YKYounhee Kim
Younhee Kim
SJSe Yoon Jeong
Se Yoon Jeong
DSDonggyu Sim
Donggyu Sim
The burgeoning field of machine vision has led to the development by the Moving Picture Experts Group (MPEG) of a new type of compression technology called video coding for machines (VCM), to enhance machine recognition through video information compression. This research proposes a principal component analysis (PCA)-based compression methodology for multi-level feature maps extracted from the feature pyramid network (FPN) structure. Unlike current PCA-based studies that independently carry out PCA for each feature map, our approach employs a generalized basis matrix and mean vector derived from channel correlations by a generalized PCA process to eliminate the need for a PCA process. Further compression is achieved by amalgamating high-dimensional feature maps, capitalizing on the spatial redundancy within these multi-level feature maps. As a result, the proposed VCM encoder forgoes the PCA process, and the generalized data do not incur any compression loss. It only requires compressing the coefficients for each feature map using versatile video coding (VVC). Experimental results demonstrate superior performance by our method over all feature anchors for each machine vision task, as specified by the MPEG-VCM common test conditions, outperforming previous PCA-based feature map compression methods. Notably, it achieved an 89.3% BD-rate reduction for instance segmentation tasks.

26 October 2022
Verified
Conference Paper
Closed access
MLMinhun Lee
Minhun Lee
SOSeoung-Jun Oh
Seoung-Jun Oh
DSDonggyu Sim
Donggyu Sim
The geometric partitioning mode (GPM) which is a part of Versatile Video Coding (VVC) recently standardized by the Joint Video Experts Team (JVET) can improve coding efficiency with enhancing its representation capability to predict the arbitrary boundaries of actual objects. However, the weighted summation process of GPM in the VVC has a limitation, especially for screen content coding (SCC) which contains mainly sharp and strong edges. The proposed method addresses the issue by considering edgeness of the video contents without any syntax changes. The experimental results show that the proposed method can achieve improvement not only objective but also subjective video quality than VTM-12.0. For YUV444 and RGB444 sequences in JVET-SCC common test conditions (CTC), the proposed method can save 1.01% and 0.95% Y_BD-Rate, respectively, without additional computation complexity on random access configuration.

9 October 2023 in Electronics Letters
Verified
Journal Article
Open access
MLMinhun Lee
Minhun Lee
SOSeoung‐Jun Oh
Seoung‐Jun Oh
DSDonggyu Sim
Donggyu Sim
Geometric partitioning mode (GPM) was newly adopted in Versatile Video Coding (VVC) to increase the partitioning precision of the arbitrary boundaries of actual objects. Note that the blending process of the GPM is not suitable for screen content with various sharp and strong edges. To alleviate this drawback, three new GPM matrices are introduced, and an efficient GPM is proposed to utilize four different GPM matrices and implicitly determine one of them depending on the discontinuity and gradients of the two predictors. The proposed method achieves an average BD‐rate reduction of 1.2% and 1.6% without additional computational complexity for random access and low‐delay B configurations, respectively, over the VVC test model (VTM18.0).

31 July 2023 in Journal of Broadcast Engineering
Verified
Journal Article
Closed access
YLYoungbok Lee
Youngbok Lee
ELEunSeong Lee
EunSeong Lee
MLMinhun Lee
Minhun Lee
Joohyung ByeonJoohyung Byeon
Joohyung Byeon
HAHyeonmo Ahn
Hyeonmo Ahn
DSDonggyu Sim
Donggyu Sim