scispace - formally typeset
Search or ask a question
Author

Jechang Jeong

Other affiliations: Incheon National University, University of Ottawa, Samsung  ...read more
Bio: Jechang Jeong is an academic researcher from Hanyang University. The author has contributed to research in topics: Motion estimation & Interpolation. The author has an hindex of 29, co-authored 408 publications receiving 3287 citations. Previous affiliations of Jechang Jeong include Incheon National University & University of Ottawa.


Papers
More filters
Journal ArticleDOI
TL;DR: A new direction-oriented interpolation method is proposed and then applied to de-interlacing to obtain more accurate direction of the highest spatial correlation and reduces possibility of wrong decision for the highest-correlated spatial direction.
Abstract: A new direction-oriented interpolation method is proposed and then applied to de-interlacing. The proposed method introduces the upper spatial direction vector. (USDV) and the lower spatial direction vector (LSDV) to obtain more accurate direction of the highest spatial correlation. Using the USDV and the LSDV, the proposed method reduces possibility of wrong decision for the highest-correlated spatial direction. Line-based directional interpolation is performed after the direction vector is found. Extensive simulations conducted for images and video sequences show the efficacy of the proposed method over the previous methods based on the ELA and over the line averaging method in terms of the objective and subjective image quality.

145 citations

Proceedings ArticleDOI
16 Jun 2019
TL;DR: A deep iterative down-up convolutional neural network (DIDN) for image denoising, which repeatedly decreases and increases the resolution of the feature maps.
Abstract: Networks using down-scaling and up-scaling of feature maps have been studied extensively in low-level vision research owing to efficient GPU memory usage and their capacity to yield large receptive fields. In this paper, we propose a deep iterative down-up convolutional neural network (DIDN) for image denoising, which repeatedly decreases and increases the resolution of the feature maps. The basic structure of the network is inspired by U-Net which was originally developed for semantic segmentation. We modify the down-scaling and up-scaling layers for image denoising task. Conventional denoising networks are trained to work with a single-level noise, or alternatively use noise information as inputs to address multi-level noise with a single model. Conversely, because the efficient memory usage of our network enables it to handle multiple parameters, it is capable of processing a wide range of noise levels with a single model without requiring noise-information inputs as a work-around. Consequently, our DIDN exhibits state-of-the-art performance using the benchmark dataset and also demonstrates its superiority in the NTIRE 2019 real image denoising challenge.

122 citations

Journal ArticleDOI
TL;DR: This paper presents a novel intra deinterlacing algorithm (NID) based on content adaptive interpolation, which analyzes the local region feature using the gradient detection and classify each missing pixel into four categories.
Abstract: This paper presents a novel intra deinterlacing algorithm (NID) based on content adaptive interpolation. The NID consists of three steps: pre-processing, content classification, and content adaptive interpolation. There are also three main interpolation methods in our proposed NID, i.e. modified edge-based line averaging (M-ELA), gradient directed interpolation (GDI), and window matching method (WMM). Each proposed method shows different performances according to spatial local features. Therefore, we analyze the local region feature using the gradient detection and classify each missing pixel into four categories. And then, based on the classification result, a different de-interlacing algorithm is activated in order to obtain the best performance. Experimental results demonstrate that the NID method performs better than previous techniques.

96 citations

Proceedings ArticleDOI
16 Jun 2019
TL;DR: This study introduces a densely connected hierarchical image denoising network (DHDN), which exceeds the performances of state-of-the-art image Denoising solutions and establishes that the proposed network outperforms conventional methods.
Abstract: Recently, deep convolutional neural networks have been applied in numerous image processing researches and have exhibited drastically improved performances. In this study, we introduce a densely connected hierarchical image denoising network (DHDN), which exceeds the performances of state-of-the-art image denoising solutions. Our proposed network improves the image denoising performance by applying the hierarchical architecture of the modified U-Net; this makes our network to use a larger number of parameters than other methods. In addition, we induce feature reuse and solve the vanishing-gradient problem by applying dense connectivity and residual learning to our convolution blocks and network. Finally, we successfully apply the model ensemble and self-ensemble methods; this enable us to improve the performance of the proposed network. The performance of the proposed network is validated by winning the second place in the NTRIE 2019 real image denoising challenge sRGB track and the third place in the raw-RGB track. Additional experimental results on additive white Gaussian noise removal also establishes that the proposed network outperforms conventional methods; this is notwithstanding the fact that the proposed network handles a wide range of noise levels with a single set of trained parameters.

91 citations

Proceedings ArticleDOI
24 Nov 2003
TL;DR: This paper proposes the motion field adaptive search using the hierarchical block structure based on the diamond search applicable to variable motion block sizes of H.264.
Abstract: The adaptive and powerful coding schemes in H.264 provide significant coding efficiency and some additional merits like error resilience and network friendliness. In spite of these outstanding features, it is not easy to implement H.264 codec as a real-time system due to its high requirement of memory bandwidth and intensive computation. Although the variable block size motion compensation using multiple reference frames is one of the key coding tools to bring about its main performance gain, it demands substantial computational complexity due to exhaustive search among all possible combinations of coding modes. Many existent fast motion estimation algorithms are not suitable for H.264 having variable motion block sizes. In this paper, we propose the motion field adaptive search using the hierarchical block structure based on the diamond search applicable to variable motion block sizes.

80 citations


Cited by
More filters
Journal ArticleDOI
TL;DR: This paper is aimed to demonstrate a close-up view about Big Data, including Big Data applications, Big Data opportunities and challenges, as well as the state-of-the-art techniques and technologies currently adopt to deal with the Big Data problems.

2,516 citations

Journal ArticleDOI
TL;DR: It is shown that some of the properties of Pawlak's rough set theory are special instances of those of MGRS, and several important measures are presented, which are re-interpreted in terms of a classic measure based on sets, the Marczewski-Steinhaus metric and the inclusion degree measure.

604 citations

01 Dec 1996

452 citations

Journal ArticleDOI
TL;DR: A meta-analysis investigation of recent peer-reviewed GEE articles focusing on several features, including data, sensor type, study area, spatial resolution, application, strategy, and analytical methods confirmed that GEE has and continues to make substantive progress on global challenges involving process of geo-big data.
Abstract: Google Earth Engine (GEE) is a cloud-based geospatial processing platform for large-scale environmental monitoring and analysis. The free-to-use GEE platform provides access to (1) petabytes of publicly available remote sensing imagery and other ready-to-use products with an explorer web app; (2) high-speed parallel processing and machine learning algorithms using Google’s computational infrastructure; and (3) a library of Application Programming Interfaces (APIs) with development environments that support popular coding languages, such as JavaScript and Python. Together these core features enable users to discover, analyze and visualize geospatial big data in powerful ways without needing access to supercomputers or specialized coding expertise. The development of GEE has created much enthusiasm and engagement in the remote sensing and geospatial data science fields. Yet after a decade since GEE was launched, its impact on remote sensing and geospatial science has not been carefully explored. Thus, a systematic review of GEE that can provide readers with the “big picture” of the current status and general trends in GEE is needed. To this end, the decision was taken to perform a meta-analysis investigation of recent peer-reviewed GEE articles focusing on several features, including data, sensor type, study area, spatial resolution, application, strategy, and analytical methods. A total of 349 peer-reviewed articles published in 146 different journals between 2010 and October 2019 were reviewed. Publications and geographical distribution trends showed a broad spectrum of applications in environmental analyses at both regional and global scales. Remote sensing datasets were used in 90% of studies while 10% of the articles utilized ready-to-use products for analyses. Optical satellite imagery with medium spatial resolution, particularly Landsat data with an archive exceeding 40 years, has been used extensively. Linear regression and random forest were the most frequently used algorithms for satellite imagery processing. Among ready-to-use products, the normalized difference vegetation index (NDVI) was used in 27% of studies for vegetation, crop, land cover mapping and drought monitoring. The results of this study confirm that GEE has and continues to make substantive progress on global challenges involving process of geo-big data.

438 citations