http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Mahalanobis Distance Cross-Correlation for Illumination-Invariant Stereo Matching
Seungryong Kim,Bumsub Ham,Bongjoe Kim,Kwanghoon Sohn Institute of Electrical and Electronics Engineers 2014 IEEE Transactions on Circuits and Systems for Vide Vol. No.
<P>A robust similarity measure called the Mahalanobis distance cross-correlation (MDCC) is proposed for illumination-invariant stereo matching, which uses a local color distribution within support windows. It is shown that the Mahalanobis distance between the color itself and the average color is preserved under affine transformation. The MDCC converts pixels within each support window into the Mahalanobis distance transform (MDT) space. The similarity between MDT pairs is then computed using the cross-correlation with an asymmetric weight function based on the Mahalanobis distance. The MDCC considers correlation on cross-color channels, thus providing robustness to affine illumination variation. Experimental results show that the MDCC outperforms state-of-the-art similarity measures in terms of stereo matching for image pairs taken under different illumination conditions.</P>
( Seungryong Yu ) 홍익대학교 법학연구소 2021 동북아법 Vol.13 No.-
COVID-19 spread over the world in 2020. This is an unprecedented global pandemic. In order to provide their students with the educational service, the universities made a progressive decision: transmission to online class. The students objected this change. They argued that the online class is a breach of contract and it is inferior to the in-person class. This paper is study for the dispute between university and the students. Therefore, the purpose of this study is examine both parties’ argument within the purview of contract theory. This theory introduced the ground for the students’ motion and universities’ defense. Even though the lawsuit is going on, this study would be helpful to expect the court’s decision. Moreover, the students and universities will get aid to prevail on their lawsuit if both parties have a plan to bring their actions.
FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence
Kim, Seungryong,Min, Dongbo,Ham, Bumsub,Lin, Stephen,Sohn, Kwanghoon IEEE 2019 IEEE transactions on pattern analysis and machine Vol.41 No.3
<P>We present a descriptor, called fully convolutional self-similarity (FCSS), for dense semantic correspondence. Unlike traditional dense correspondence approaches for estimating depth or optical flow, semantic correspondence estimation poses additional challenges due to intra-class appearance and shape variations among different instances within the same object or scene category. To robustly match points across semantically similar images, we formulate FCSS using local self-similarity (LSS), which is inherently insensitive to intra-class appearance variations. LSS is incorporated through a proposed convolutional self-similarity (CSS) layer, where the sampling patterns and the self-similarity measure are jointly learned in an end-to-end and multi-scale manner. Furthermore, to address shape variations among different object instances, we propose a convolutional affine transformer (CAT) layer that estimates explicit affine transformation fields at each pixel to transform the sampling patterns and corresponding receptive fields. As training data for semantic correspondence is rather limited, we propose to leverage object candidate priors provided in most existing datasets and also correspondence consistency between object pairs to enable weakly-supervised learning. Experiments demonstrate that FCSS significantly outperforms conventional handcrafted descriptors and CNN-based descriptors on various benchmarks.</P>
DASC: Robust Dense Descriptor for Multi-Modal and Multi-Spectral Correspondence Estimation
Kim, Seungryong,Min, Dongbo,Ham, Bumsub,Do, Minh N.,Sohn, Kwanghoon IEEE 2017 IEEE transactions on pattern analysis and machine Vol.39 No.9
<P>Establishing dense correspondences between multiple images is a fundamental task in many applications. However, finding a reliable correspondence between multi-modal or multi-spectral images still remains unsolved due to their challenging photometric and geometric variations. In this paper, we propose a novel dense descriptor, called dense adaptive self-correlation (DASC), to estimate dense multi-modal and multi-spectral correspondences. Based on an observation that self-similarity existing within images is robust to imaging modality variations, we define the descriptor with a series of an adaptive self-correlation similarity measure between patches sampled by a randomized receptive field pooling, in which a sampling pattern is obtained using a discriminative learning. The computational redundancy of dense descriptors is dramatically reduced by applying fast edge-aware filtering. Furthermore, in order to address geometric variations including scale and rotation, we propose a geometry-invariant DASC (GI-DASC) descriptor that effectively leverages the DASC through a superpixel-based representation. For a quantitative evaluation of the GI-DASC, we build a novel multi-modal benchmark as varying photometric and geometric conditions. Experimental results demonstrate the outstanding performance of the DASC and GI-DASC in many cases of dense multi-modal and multi-spectral correspondences.</P>
파장 가변형 레이저 흡수 분광법을 이용한 광학적 포화 상태의 CO 농도 측정에 관한 연구
이승룡(Seungryong Lee),정낙원(Nakwon Jeong),황정호(Jungho Hwang),유미연(Miyeon Yoo),박대근(DaeGeun Park),김대해(Daehae Kim) 한국에너지기후변화학회 2021 한국에너지기후변화학회 학술대회 Vol.2021 No.11
다양한 연소 시스템에서 발생하는 대기 오염 물질 저감과 연소 효율 증가를 위해 일산화탄소(carbon monoxide, CO)를 정밀하게 측정하는 기술에 대한 연구가 지속적으로 이루어지고 있다. 불완전 연소에 의해 발생되는 일산화탄소를 측정하는 기술로 파장 가변형 레이저 흡수 분광법(tunable diode laser absorption spectroscopy, TDLAS)을 사용하여 연소 환경에서 실시간으로 측정 하는 연구가 진행되었다. TDLAS 기법은 비접촉식 방식으로 빠른 응답성과 높은 신뢰성을 가지며 열악한 연소 환경 내 측정에 적합한 기술이다. 하지만 연소 환경 내 높은 일산화탄소 농도 조건이나 광학적 측정 구간의 증가로 발생되는 광학적 포화 상태(optically thick condition)에서의 측정은 어려움을 가지고 있다. 포화상태의 측정신호를 재구성하는 기술은 TDLAS의 가스 측정 범위를 효과적으로 확장 시켜줄 수 있다. 본 연구는 CO 농도 측정을 위해 직접흡수분광법(Direct absroption spectroscopy)을 사용하여 실험을 진행하였다. 측정된 광학적 포화 상태의 데이터는 HITRAN database를 이용하여 voigt 함수 기반 시뮬레이션을 통해 얻어진 재구성 데이터와 비교하여 분석하였다.
( Yu Seungryong ) 홍익대학교 법학연구소 2022 동북아법 Vol.14 No.-
Foreign Corrupt Practices Act is one of the most important law in international business. Business entities have high risk to violate the FCPA because it remains the definition of its terms less clear. Additionally, Department of Justice (DOJ) and Securities and Exchange Commission (SEC) enforce the law more harshly than prior era. Amid the harshness of the enforcement, the major corporation embarks to recognize comply to the law. However, because of the uncertainty of the law and harshness, business entity does their job more restrictive. Therefore, if the government suggests some standard and dissolve the uncertainty through the regulation or recommendations, the corporations can do business more readily in the country. This Article overview the FCPA and how DOJ and SEC open the investigation. With comparing FCPA and Korean laws to deal with corrupt, this article provides some resolution and supplement to the law. Those solutions would lower the risk of doing business in Korea.
Modality-Invariant Image Classification Based on Modality Uniqueness and Dictionary Learning
Kim, Seungryong,Cai, Rui,Park, Kihong,Kim, Sunok,Sohn, Kwanghoon IEEE 2017 IEEE TRANSACTIONS ON IMAGE PROCESSING - Vol.26 No.2
<P>We present a unified framework for the image classification of image sets taken under varying modality conditions. Our method is motivated by a key observation that the image feature distribution is simultaneously influenced by the semantic-class and the modality category label, which limits the performance of conventional methods for that task. With this insight, we introduce modality uniqueness as a discriminative weight that divides each modality cluster from all other clusters. By leveraging the modality uniqueness, our framework is formulated as unsupervised modality clustering and classifier learning based on modality-invariant similarity kernel. Specifically, in the assignment step, each training image is first assigned to the most similar cluster according to its modality. In the update step, based on the current cluster hypothesis, the modality uniqueness and the sparse dictionary are updated. These two steps are formulated in an iterative manner. Based on the final clusters, a modality-invariant marginalized kernel is then computed, where the similarities between the reconstructed features of each modality are aggregated across all clusters. Our framework enables the reliable inference of semantic-class category for an image, even across large photometric variations. Experimental results show that our method outperforms conventional methods on various benchmarks, such as landmark identification under severely varying weather conditions, domain-adapting image classification, and RGB and near-infrared image classification.</P>