BROWSE

Graduate School of Ajou University Department of Artificial Intelligence 3. Theses(Master)

Implementation and Performance Analysis of Mobile Real-Time Frame Interpolation Network Using Deep Learning

DC Field Value Language
dc.contributor.advisor황원준-
dc.contributor.author안현모-
dc.date.accessioned2025-01-25T01:36:01Z-
dc.date.available2025-01-25T01:36:01Z-
dc.date.issued2023-08-
dc.identifier.other32830-
dc.identifier.urihttps://dspace.ajou.ac.kr/handle/2018.oak/24500-
dc.description학위논문(석사)--아주대학교 일반대학원 :인공지능학과,2023. 8-
dc.description.tableofcontentsI. Introduction 1 <br>II. Related Works 4 <br> A. Video Frame Interpolation Techniques 4 <br> B. Model Lightweighting Techniques 5 <br>III. Proposed Method 8 <br> A. Data pipeline 8 <br> B. Convolutional Neural Network for Flow Estimation 10 <br> C. Training 10 <br>Ⅳ. Implementation Details 12 <br>V. Experimental Results 14 <br> A. Results on PC 14 <br> B. Results on mobile 15 <br> C. Network Comparison 15 <br>Ⅵ. Conclusion 17 <br>Ⅶ. Reference 18-
dc.language.isoeng-
dc.publisherThe Graduate School, Ajou University-
dc.rights아주대학교 논문은 저작권에 의해 보호받습니다.-
dc.titleImplementation and Performance Analysis of Mobile Real-Time Frame Interpolation Network Using Deep Learning-
dc.typeThesis-
dc.contributor.affiliation아주대학교 대학원-
dc.contributor.department일반대학원 인공지능학과-
dc.date.awarded2023-08-
dc.description.degreeMaster-
dc.identifier.localIdT000000032830-
dc.identifier.urlhttps://dcoll.ajou.ac.kr/dcollection/common/orgView/000000032830-
dc.subject.keywordDeep learning-
dc.subject.keywordMobile-
dc.subject.keywordOptical flow-
dc.subject.keywordReal time-
dc.subject.keywordVideo frame interpolation-
dc.description.alternativeAbstractThis research emphasizes the importance of constructing an efficient deep learning model that can perform real-time video frame interpolation in resource-constrained mobile environments, amidst the rapid advancements in the field of deep learning technology. <br>The study proposes a lightweight network model and system for real-time video frame interpolation in mobile environments. <br>By integrating intelligent data adjustment, lightweight CNN architecture, and distributed computing techniques, the model is designed to operate efficiently even with limited resources. <br>The proposed lightweight network model contributes to the field of video frame interpolation by providing a lightweight solution tailored to mobile environments. <br>It also opens up possibilities for various industries where efficient storage utilization and high frame rates are crucial. <br>Furthermore, the research provides insights into lightweight techniques and distributed computing strategies that can be applied to other deep learning models in resource-constrained environments.-
Appears in Collections:
Graduate School of Ajou University > Department of Artificial Intelligence > 3. Theses(Master)
Files in This Item:
There are no files associated with this item.
Show simple item record

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

  • License
    sherpa_romeo
    sherpa_juliet
STATISTICS
Total Visit :5,268,837
Total Download :2,137
Today View :5,533

AJOU

AJOU Central Library Repository는 국립중앙도서관 OAK 보급사업으로 구축되었습니다.

Browse

OAK Portal LOGIN