• 제목/요약/키워드: shot domain

검색결과 49건 처리시간 0.031초

인터넷에 기반한 내용기반 검색 시스템 설계 (Content-Based Retrieval System Design over the Internet)

  • 김영호;강대성
    • 제어로봇시스템학회논문지
    • /
    • 제11권5호
    • /
    • pp.471-475
    • /
    • 2005
  • Recently, development of digital technology is occupying a large part of multimedia information like character, voice, image, video, etc. Research about video indexing and retrieval progresses especially in research relative to video. This paper proposes the novel notation in order to retrieve MPEG video in the international standards of moving picture encoding For realizing the retrieval-system, we detect DCT DC coefficient, and then we obtain shot to apply MVC(Mean Value Comparative) notation to image constructed DC coefficient. We choose the key frame for start-frame of a shot, and we have the codebook index generating it using feature of DC image and applying PCA(principal Component Analysis) to the key frame. Also, we realize the retrieval-system through similarity after indexing. We could reduce error detection due to distinguish shot from conventional shot detection algorithm. In the mean time, speed of indexing is faster by PCA due to perform it in the compressed domain, and it has an advantage which is to generate codebook due to use statistical features. Finally, we could realize efficient retrieval-system using MVC and PCA to shot detection and indexing which is important step of retrieval-system, and we using retrieval-system over the internet.

Extrapolation of wind pressure for low-rise buildings at different scales using few-shot learning

  • Yanmo Weng;Stephanie G. Paal
    • Wind and Structures
    • /
    • 제36권6호
    • /
    • pp.367-377
    • /
    • 2023
  • This study proposes a few-shot learning model for extrapolating the wind pressure of scaled experiments to full-scale measurements. The proposed ML model can use scaled experimental data and a few full-scale tests to accurately predict the remaining full-scale data points (for new specimens). This model focuses on extrapolating the prediction to different scales while existing approaches are not capable of accurately extrapolating from scaled data to full-scale data in the wind engineering domain. Also, the scaling issue observed in wind tunnel tests can be partially resolved via the proposed approach. The proposed model obtained a low mean-squared error and a high coefficient of determination for the mean and standard deviation wind pressure coefficients of the full-scale dataset. A parametric study is carried out to investigate the influence of the number of selected shots. This technique is the first of its kind as it is the first time an ML model has been used in the wind engineering field to deal with extrapolation in wind performance prediction. With the advantages of the few-shot learning model, physical wind tunnel experiments can be reduced to a great extent. The few-shot learning model yields a robust, efficient, and accurate alternative to extrapolating the prediction performance of structures from various model scales to full-scale.

퍼지논리에 의한 최적 성형조건 결정 시스템에 관한 연구 (A Study on the Determination System of Process Conditions for Moldability by Using Fuzzy Logic)

  • 강성남;허용정
    • 한국산학기술학회논문지
    • /
    • 제3권1호
    • /
    • pp.1-4
    • /
    • 2002
  • 사출성형에서 제품의 최종 품질에 영향을 미치는 중요한 인자들 중의 하나는 사출압력이다. 전통적으로 현장의 사출전문가는 오래된 현장 경험을 바탕으로 사출압력을 결정한다. 그러나 비전문가에게는 제품의 크기, 형상 그리고 사출공정의 전반적인 과정을 고려한 적절한 사출압을 결정하기가 쉽지 않다. 본 연구에서는 퍼지 논리(fuzzy logic)를 이용하여 제품도면에 나와 있는 제품두께와 유동길이를 알면 쉽게 초기 사출압을 결정할 수 있도록 전문가의 경험을 규칙베이스화 하였다. 규칙베이스를 구성하기 위해서 현장 전문가들을 인터뷰하고 설문조사를 한 후 기술적인 문서를 작성하여야 하지만 본 연구에서는 사출성형 해석 프로그램인 C-Mold를 이용하여 수 차례의 시뮬레이션을 반복 수행하여 규칙베이스를 구성하였다.

  • PDF

Zero-shot voice conversion with HuBERT

  • Hyelee Chung;Hosung Nam
    • 말소리와 음성과학
    • /
    • 제15권3호
    • /
    • pp.69-74
    • /
    • 2023
  • This study introduces an innovative model for zero-shot voice conversion that utilizes the capabilities of HuBERT. Zero-shot voice conversion models can transform the speech of one speaker to mimic that of another, even when the model has not been exposed to the target speaker's voice during the training phase. Comprising five main components (HuBERT, feature encoder, flow, speaker encoder, and vocoder), the model offers remarkable performance across a range of scenarios. Notably, it excels in the challenging unseen-to-unseen voice-conversion tasks. The effectiveness of the model was assessed based on the mean opinion scores and similarity scores, reflecting high voice quality and similarity to the target speakers. This model demonstrates considerable promise for a range of real-world applications demanding high-quality voice conversion. This study sets a precedent in the exploration of HuBERT-based models for voice conversion, and presents new directions for future research in this domain. Despite its complexities, the robust performance of this model underscores the viability of HuBERT in advancing voice conversion technology, making it a significant contributor to the field.

H.264/AVC 압축 영역에서의 동영상 검색 (Video Shot Retrieval in H.264/AVC compression domain)

  • 변주완;김성민;원치선
    • 대한전자공학회논문지SP
    • /
    • 제43권5호
    • /
    • pp.72-78
    • /
    • 2006
  • 본 논문은 H.264/AVC 압축 영역에서의 동영상 검색에 관한 것이다. 기존의 동영상 압축 표준인 MPEG-2 및 4와는 달리 H.264/AVC는 다양한 블록 단위의 움직임 보상으로 인해 기존의 MPEG-2 및 4에서 사용되었던 움직임 벡터를 이용한 방법들을 그대로 적용하기 어렵다. 따라서 본 논문에서는 이러한 문제를 해결하기 위해 H.264/AVC의 다양한 블록 크기의 움직임 벡터를 움직임 보상의 최소 단위인 $4{\times}4$ 블록 단위로 분할하고, 각각의 분할된 블록에 동일한 움직임 벡터를 할당하는 방법을 제안한다. 또한, 유사도 측정을 위해 두 영상으로부터 추출한 특징 간의 상관계수를 이용하였다. 실험은 10558 프레임의 MPEG 표준 동영상과 48161 프레임의 일반 동영상을 대상으로 이루어졌으며, 제안한 방법을 이용한 실험을 통해 0.2 이하의 ANMRR 결과를 나타내었다.

CMP cross-correlation analysis of multi-channel surface-wave data

  • Hayashi Koichi;Suzuki Haruhiko
    • 지구물리와물리탐사
    • /
    • 제7권1호
    • /
    • pp.7-13
    • /
    • 2004
  • In this paper, we demonstrate that Common Mid-Point (CMP) cross-correlation gathers of multi-channel and multi-shot surface waves give accurate phase-velocity curves, and enable us to reconstruct two-dimensional (2D) velocity structures with high resolution. Data acquisition for CMP cross-correlation analysis is similar to acquisition for a 2D seismic reflection survey. Data processing seems similar to Common Depth-Point (CDP) analysis of 2D seismic reflection survey data, but differs in that the cross-correlation of the original waveform is calculated before making CMP gathers. Data processing in CMP cross-correlation analysis consists of the following four steps: First, cross-correlations are calculated for every pair of traces in each shot gather. Second, correlation traces having a common mid-point are gathered, and those traces that have equal spacing are stacked in the time domain. The resultant cross-correlation gathers resemble shot gathers and are referred to as CMP cross-correlation gathers. Third, a multi-channel analysis is applied to the CMP cross-correlation gathers for calculating phase velocities of surface waves. Finally, a 2D S-wave velocity profile is reconstructed through non-linear least squares inversion. Analyses of waveform data from numerical modelling and field observations indicate that the new method could greatly improve the accuracy and resolution of subsurface S-velocity structure, compared with conventional surface-wave methods.

MPEG-2 압축 영상에서의 뉴스 색인을 위한 장면전환 검출 알고리즘 (Scene Change Detection Algorithm for News Indexing in MPEG-2 Compressed-Domain)

  • 박진형;박동권;원치선
    • 한국방송∙미디어공학회:학술대회논문집
    • /
    • 한국방송공학회 1998년도 학술대회
    • /
    • pp.143-146
    • /
    • 1998
  • 본 논문에서는 MPEG-2 압축영상에서 뉴스 색인을 위한 개선된 장면(Shot)전환 알고리즘을 제안한다. 제안된 검출 알고리즘은 압축된 비디오 시퀀스에서 추출한 특징정보인 에지정보와 컬러정보를 함께 사용하여 GOP단위의 빠르고 효율적인 장면전환 검출 결과를 얻을 수 있다. 제안된 알고리즘은 장면전환 검출뿐만 아니라 내용 기반(content - based) 비디오 검색 등에도 효과적으로 이용될 수 있다.

  • PDF

Crank Angle Analysis

  • Gade, Svend;Hald, Jorgen
    • 한국소음진동공학회:학술대회논문집
    • /
    • 한국소음진동공학회 2001년도 추계학술대회논문집 II
    • /
    • pp.1040-1043
    • /
    • 2001
  • This paper describes the principle behind Crank Angle Analysis, as implemented by Bruel & Kjaer in the Non-Stationary Spatial Transformation of Sound Fields (NS-STSF) system. The NS-STSF system combines a Time Domain Holography measurement on for example an engine with two simultaneously recorded Tacho signals. The Tacho signals provide the crankshaft angle and the RPM at the instant of each instantaneous output (snap-shot) from Time Domain Holography. As a result, the system allows precise analysis of the temporal and spatial relation between the acoustical emission (or the vibration pattern) and the mechanical events during an engine cycle. Some results from a measurement on a DaimlerChrysler engine are presented.

  • PDF

Task-Ambient 공조시스템의 난방시 열환경 특성에 관한 실험적 연구 (The Thermal Environmental Characteristics for Task-Ambient Air-Conditioning System in Heating Condition)

  • 이정재;윤창오;정광섭;한화택;박영철
    • 설비공학논문집
    • /
    • 제13권2호
    • /
    • pp.115-121
    • /
    • 2001
  • Recently, the requirement of healthier and more comfortable environment makes the zoning domain more details. However, it has limitation to satisfy the thermal comfort of an individual because of the effect of the heat generation from the OA machine and partitions in indoor room. In this paper, we certify the validity of task-ambient air-conditioning system that has been developed as a new concept of personal air-conditioning system, and specify design strategies for more efficient task-ambient air-conditioning system with a specification guided by indoor environmental characteristics analyzed through experiment data. In this experiment, we changed the temperature and the quantity of air-flow in task domain to understand characteristic behavior of the thermal environment and investigate the possibility of energy saving. The experiment result is that the environment of the task area depends on the condition of supply air, and though the airflow of the low temperature is supplied with the ambient area, the personal environment and the efficiency of energy saving are improved by controlling the temperature and the quantity of the air shot around the task domain.

  • PDF

Metagenome Analysis of Protein Domain Collocation within Cellulase Genes of Goat Rumen Microbes

  • Lim, SooYeon;Seo, Jaehyun;Choi, Hyunbong;Yoon, Duhak;Nam, Jungrye;Kim, Heebal;Cho, Seoae;Chang, Jongsoo
    • Asian-Australasian Journal of Animal Sciences
    • /
    • 제26권8호
    • /
    • pp.1144-1151
    • /
    • 2013
  • In this study, protein domains with cellulase activity in goat rumen microbes were investigated using metagenomic and bioinformatic analyses. After the complete genome of goat rumen microbes was obtained using a shotgun sequencing method, 217,892,109 pair reads were filtered, including only those with 70% identity, 100-bp matches, and thresholds below $E^{-10}$ using METAIDBA. These filtered contigs were assembled and annotated using blastN against the NCBI nucleotide database. As a result, a microbial community structure with 1431 species was analyzed, among which Prevotella ruminicola 23 bacteria and Butyrivibrio proteoclasticus B316 were the dominant groups. In parallel, 201 sequences related with cellulase activities (EC.3.2.1.4) were obtained through blast searches using the enzyme.dat file provided by the NCBI database. After translating the nucleotide sequence into a protein sequence using Interproscan, 28 protein domains with cellulase activity were identified using the HMMER package with threshold E values below $10^{-5}$. Cellulase activity protein domain profiling showed that the major protein domains such as lipase GDSL, cellulase, and Glyco hydro 10 were present in bacterial species with strong cellulase activities. Furthermore, correlation plots clearly displayed the strong positive correlation between some protein domain groups, which was indicative of microbial adaption in the goat rumen based on feeding habits. This is the first metagenomic analysis of cellulase activity protein domains using bioinformatics from the goat rumen.