非物质文化遗产视频语义标注方法研究
|
摘要
【目的/意义】针对非物质文化遗产(简称"非遗")视频资源难以入库与管理的难题,提出了一种非遗视频资源的管理和语义组织的语义标注方法。【方法/过程】首先对非遗视频采用基于SURF算法和窗口阈值的镜头分割方法,将非遗视频解构成不同颗粒度的逻辑单元;其次构建了非遗视频语义标注的本体模型;最后通过视频语义标注过程,实现领域知识概念与视频资源间的语义关联,赋予视频单元丰富的语义信息。【结果/结论】非遗视频综合语义标注方法可对非遗视频资源实现有效管理,为用户提供结构化、语义化的视频浏览及知识可视化等知识服务,对非遗数字化保护与传播具有重要的意义和价值。
【Purpose/significance】In this paper, a semantic annotation method for management and semantic organizationis proposed to solve the difficult problems of storage and management of Intangible Cultural Heritage video resources.【Method/process】Firstly, the video is partitioned into a logical unit with different granularity using the SURF algorithmand threshold segmentation method. Secondly, the paper constructed the ontology model of semantic annotation forIntangible Cultural Heritage videos. Finally, the semantic association between the domain knowledge concept and the videoresource is realized through the video semantic annotation process, which gives the video unit abundant related semanticinformation.【Result/conclusion】The comprehensive video semantic annotation method can manage the video resourceseffectively and provide users with knowledge visualization and knowledge services such as structured and semantic videobrowsing. Moreover, it is of great significance and value for digital preservation and dissemination of Intangible CulturalHeritage.
【Purpose/significance】In this paper, a semantic annotation method for management and semantic organizationis proposed to solve the difficult problems of storage and management of Intangible Cultural Heritage video resources.【Method/process】Firstly, the video is partitioned into a logical unit with different granularity using the SURF algorithmand threshold segmentation method. Secondly, the paper constructed the ontology model of semantic annotation forIntangible Cultural Heritage videos. Finally, the semantic association between the domain knowledge concept and the videoresource is realized through the video semantic annotation process, which gives the video unit abundant related semanticinformation.【Result/conclusion】The comprehensive video semantic annotation method can manage the video resourceseffectively and provide users with knowledge visualization and knowledge services such as structured and semantic videobrowsing. Moreover, it is of great significance and value for digital preservation and dissemination of Intangible CulturalHeritage.
引文
1邱均平,牟楠,楼雯,赵蓉英.国内外语义标注研究进展分析[J].情报理论与实践,2014,37(5):12-16
2 Khurana, Khushboo, and M. B. Chandak. Study of various video annotation techniques[J].International Journal of Advanced Research in Computer and Communication Engineering 2.1,2013,(2):909-914.
3 Stegmaier F, Bailer W, Burger T, et al. Unified Access to Media Metadata on the Web[J]. IEEE Multimedia, 2016, 20(2):22-29.
4 Naphade M, Smith J R, Tesic J, et al. Large-scale concept ontology for multimedia[J]. IEEE Multimedia, 2006, 13(3):86-91.
5 Sikos L. VidOnt:the video ontology[J]. International Journal of Computer Science Issues(IJCSI), 2014, 11(4):1.
6 Sjekavica T, Obradovi I, Gledec G. Ontologies for Multimedia Annotation:An overview[C]. 4th European Conference of Computer Science(ECCS'13),2013.
7 Khan M, Khusro S, Ullah I. On Annotation of Video Content for Multimedia Retrieval and Sharing[J]. International Journal of Computer Science and Information Security, 2016, 14(3):198.
8 徐雷,王晓光.叙事型图像语义标注模型研究[J].中国图书馆学报,2017,43(5):70-83.
9 彭太乐.基于镜头及场景上下文的短视频标注方法研究[D].上海:上海大学,2016.
10 Tippaya S, Sitjongsataporn S, Tan T, et al. Multi-modal visual features-based video shot boundary detection[J]. IEEE Access, 2017,(5):12563-12575.
11 Bay H, Ess A, Tuytelaars T, et al. Speeded-Up Robust Features(SURF)[J]. Computer Vision&Image Understanding, 2008, 110(3):346-359.
12 郝会芬.视频镜头分割和关键帧提取关键技术研究[D].武汉:华中师范大学,2015.
13 谈国新,钟正.民族文化资源数字化与产业开发[M].武汉:华中师范大学出版社,2012.
14 周耀林,赵跃,孙晶琼.非物质文化遗产信息资源组织与检索研究路径——基于本体方法的考察与设计[J].情报杂志,2017,36(8):166-174.
15 郝挺雷.传统节日知识本体的构建及表示方法研究[D].武汉:华中师范大学,2011.
16 蔡璐,熊拥军,刘灿姣.基于本体和元数据的非遗资源知识组织体系构建[J].图书馆理论与实践,2016,(3):39-43.
17 董坤.基于关联数据的高校知识资源语义化组织研究[J].情报理论与实践,2016,(3):91-95.
18 Aguilar J, Jerez M, Rodríguez T. CAMeOnto:Context awareness meta ontology modeling[J]. Applied computing and informatics, 2018, 14(2):202-213.
19 Stegmaier F, Bailer W, Burger T, et al. Unified Access to Media Metadata on the Web[J]. IEEE Multimedia, 2016, 20(2):22-29.
20 任飞亮,沈继坤,孙宾宾,朱靖波.从文本中构建领域本体技术综述[J].计算机学报,2017,(56):1-26
21 陈烨,赵一鸣,姜又琦.基于关联数据的知识组织研究述评[J].情报理论与实践,2016,39(2):139-144.
22 仝召娟,许鑫,钱佳轶.基于关联数据的非遗数字资源聚合研究[J].图书情报工作,2014,(21):21-26.
2 Khurana, Khushboo, and M. B. Chandak. Study of various video annotation techniques[J].International Journal of Advanced Research in Computer and Communication Engineering 2.1,2013,(2):909-914.
3 Stegmaier F, Bailer W, Burger T, et al. Unified Access to Media Metadata on the Web[J]. IEEE Multimedia, 2016, 20(2):22-29.
4 Naphade M, Smith J R, Tesic J, et al. Large-scale concept ontology for multimedia[J]. IEEE Multimedia, 2006, 13(3):86-91.
5 Sikos L. VidOnt:the video ontology[J]. International Journal of Computer Science Issues(IJCSI), 2014, 11(4):1.
6 Sjekavica T, Obradovi I, Gledec G. Ontologies for Multimedia Annotation:An overview[C]. 4th European Conference of Computer Science(ECCS'13),2013.
7 Khan M, Khusro S, Ullah I. On Annotation of Video Content for Multimedia Retrieval and Sharing[J]. International Journal of Computer Science and Information Security, 2016, 14(3):198.
8 徐雷,王晓光.叙事型图像语义标注模型研究[J].中国图书馆学报,2017,43(5):70-83.
9 彭太乐.基于镜头及场景上下文的短视频标注方法研究[D].上海:上海大学,2016.
10 Tippaya S, Sitjongsataporn S, Tan T, et al. Multi-modal visual features-based video shot boundary detection[J]. IEEE Access, 2017,(5):12563-12575.
11 Bay H, Ess A, Tuytelaars T, et al. Speeded-Up Robust Features(SURF)[J]. Computer Vision&Image Understanding, 2008, 110(3):346-359.
12 郝会芬.视频镜头分割和关键帧提取关键技术研究[D].武汉:华中师范大学,2015.
13 谈国新,钟正.民族文化资源数字化与产业开发[M].武汉:华中师范大学出版社,2012.
14 周耀林,赵跃,孙晶琼.非物质文化遗产信息资源组织与检索研究路径——基于本体方法的考察与设计[J].情报杂志,2017,36(8):166-174.
15 郝挺雷.传统节日知识本体的构建及表示方法研究[D].武汉:华中师范大学,2011.
16 蔡璐,熊拥军,刘灿姣.基于本体和元数据的非遗资源知识组织体系构建[J].图书馆理论与实践,2016,(3):39-43.
17 董坤.基于关联数据的高校知识资源语义化组织研究[J].情报理论与实践,2016,(3):91-95.
18 Aguilar J, Jerez M, Rodríguez T. CAMeOnto:Context awareness meta ontology modeling[J]. Applied computing and informatics, 2018, 14(2):202-213.
19 Stegmaier F, Bailer W, Burger T, et al. Unified Access to Media Metadata on the Web[J]. IEEE Multimedia, 2016, 20(2):22-29.
20 任飞亮,沈继坤,孙宾宾,朱靖波.从文本中构建领域本体技术综述[J].计算机学报,2017,(56):1-26
21 陈烨,赵一鸣,姜又琦.基于关联数据的知识组织研究述评[J].情报理论与实践,2016,39(2):139-144.
22 仝召娟,许鑫,钱佳轶.基于关联数据的非遗数字资源聚合研究[J].图书情报工作,2014,(21):21-26.