請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/6164完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 歐陽明(Ming Ouhyoung) | |
| dc.contributor.author | Hsuan-Ming Liu | en |
| dc.contributor.author | 劉軒銘 | zh_TW |
| dc.date.accessioned | 2021-05-16T16:22:14Z | - |
| dc.date.available | 2013-07-31 | |
| dc.date.available | 2021-05-16T16:22:14Z | - |
| dc.date.copyright | 2013-07-31 | |
| dc.date.issued | 2013 | |
| dc.date.submitted | 2013-07-23 | |
| dc.identifier.citation | [1] Hamed Pirsiavash and Deva Ramanan. Detecting activities of daily living in firstperson
camera views. In CVPR, 2012. [2] Steve Hodges, Lyndsay Williams, Emma Berry, Shahram Izadi, James Srinivasan, Alex Butler, Gavin Smyth, Narinder Kapur, and Ken Wood. Sensecam: A retrospective memory aid. In International Conference on Ubicomp, 2006. [3] B. Kopp, A. Kunkel, H. Flor, T. Platz, U. Rose, K.H. Mauritz, K. Gresser, K.L. Mc- Culloch, and E. Taub. The arm motor ability test: reliability, validity, and sensitivity to change of an instrument for assessing disabilities in activities of daily living. Arch Phys Med Rehabil, 78(6):615--20, 1997. [4] J. K. Aggarwal, Michael S. Ryoo, and Kris M. Kitani. Frontiers of human activity analysis, 2011, Apr. [Online; CVPR2011 tutorial. [5] Douglas L. Vail, Manuela M. Veloso, and John D. Lafferty. Conditional random fields for activity recognition. Proceedings of the 6th international joint conference on Autonomous agents and multiagent systems. [6] Young-Seol Lee and Sung-Bae Cho. Activity recognition using hierarchical hidden markov models on a smartphone with 3d accelerometer. In HAIS, 2011. [7] Tao Gu, Zhanqing Wu, Xianping Tao, Hung Keng Pung, and Jian Lu. epsicar: An emerging patterns based approach to sequential, interleaved and concurrent activity recognition. In PERCOM, 2009. 28 [8] Wen-Huang Cheng, Yung-Yu Chuang, Bing-Yu Chen, Ja-Ling Wu, Shao-Yen Fang, Yin-Tzu Lin, Chi-Chang Hsieh, Chen-Ming Pan, Wei-Ta Chu, and Min-Chun Tien. Semantic-event based analysis and segmentation of wedding ceremony videos. Proceedings of the international workshop on Workshop on multimedia information retrieval, pp. 95-104, 2007. [9] Thi V. Duong, Hung H. Bui, Dinh Q. Phung, and Svetha Venkatesh. Activity recognition and abnormality detection with the switching hidden semi-markov model. In CVPR, 2005. [10] John D. Lafferty, Andrew McCallum, and Fernando C. N. Pereira. Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In ICML, 2001, pp. 282-289, 2001. [11] Derek Hao Hu and Qiang Yang. Cigar: concurrent and interleaving goal and activity recognition. In AAAI, 2008. [12] Ivan Laptev, Marcin Marszalek, Cordelia Schmid, and Benjamin Rozenfeld. Learning realistic human actions from movies. In CVPR 2008. [13] Mohammad Amin Sadeghi and Ali Farhadi. Recognition using visual phrases. In CVPR, 2011. [14] Emmanuel Munguia Tapia, Stephen S. Intille, and Kent Larson. Activity recognition in the home using simple and ubiquitous sensors. In In Pervasive, pages 158--175, 2004. [15] T. Kudo. Crf++: Yet another crf toolkit, 2007, Aug. [16] Heng Wang, Muhammad Muneeb Ullah, Alexander Klaser, Ivan Laptev, and Cordelia Schmid. Evaluation of local spatio-temporal features for action recognition. British Machine Vision Conference, 2009. [17] Pedro F Felzenszwalb, Ross B Girshick, David McAllester, and Deva Ramanan. Object detection with discriminatively trained part-based models. In PAMI, 2010. 29 [18] Shengcai Liao, Xiangxin Zhu, Zhen Lei, Lun Zhang, and Stan Z. Li. Learning multiscale block local binary patterns for face recognition. In ICB 2007. [19] Alireza Fathi, Xiaofeng Ren, and James M. Rehg. Learning to recognize objects in egocentric activities. In CVPR, 2011. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/6164 | - |
| dc.description.abstract | 在本篇論文中, 我們提出了針對於拍攝自第一人稱攝影機的影片, 進
行主角執行中的行為的辨識方法. 我們將此問題轉換為鏈狀條件隨機場 (Linear-chain Conditional Random Fields) 的序列標註問題. 在本方法中 使用高階視覺線索, 也就是畫面中物件偵測的結果, 來當做辨識特徵. 另 外也使用了時序金字塔(Temporal Pyramid) 來實現在時間軸上的多重解 析度, 並證明其可以改善現行的物件偵測結果. 另外也針對在日常生活 中常會發生的事件交錯情況, 提出在時序金字塔中找尋可能解的辦法. 最後我們利用目前最新研究提供的資料[1] 進行實驗, 得出可匹敵的結 果. 再利用自行拍攝的影片資料, 比較有無進行交錯事件搜尋的差別. | zh_TW |
| dc.description.abstract | We present a simple but effective online recognition system for detecting
interleaved activities of daily life (ADLs) in first-person-view videos. The two major difficulties in detecting ADLs are interleaving and variability in duration. We use temporal pyramid in our system to attack these difficulties, and this means we can use relatively simple models instead of time dependent probability ones such as Hidden semi-Markov model or nested models. The proposed solution includes the combination of conditional random fields (CRF) and an online inference algorithm, which explicitly considers multiple interleaved sequences by inferencing multi-stage activities on temporal pyramid. Although our system only uses linear chain-structured CRF model, which can be easily learned without a large amount of training data, it still recognizes complicated activity sequences. The system is evaluated on a data set provided by the work from state-of-the-art, and the result is comparable to their method. We also provide some experiment result using a customized dataset. | en |
| dc.description.provenance | Made available in DSpace on 2021-05-16T16:22:14Z (GMT). No. of bitstreams: 1 ntu-102-R00944041-1.pdf: 4317470 bytes, checksum: 64d22ed19662a75929ec65f46b9b7192 (MD5) Previous issue date: 2013 | en |
| dc.description.tableofcontents | 致謝 i
中文摘要 ii Abstract iii Contents iv List of Figures vi List of Tables viii 1 Introduction 1 1.1 Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 2 Related Work 4 3 Method 6 3.1 Visual Phrase Object Feature . . . . . . . . . . . . . . . . . . . . . . . . 6 3.2 Activity Model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 3.3 Temporal Pyramid Feature Aggregation . . . . . . . . . . . . . . . . . . 8 3.4 Online Inference Algorithm . . . . . . . . . . . . . . . . . . . . . . . . . 10 3.5 Algorithm . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15 4 Experiments and Results 17 4.1 Experiment 1 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17 iv 4.1.1 Dataset . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17 4.1.2 Evaluation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19 4.2 Experaiment 2 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22 4.2.1 Dataset . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22 4.2.2 Evaluation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24 5 Conclusion 27 Bibliography 28 | |
| dc.language.iso | en | |
| dc.subject | 日常生活行為辨識 | zh_TW |
| dc.subject | 條件隨機場 | zh_TW |
| dc.subject | 時序金字塔 | zh_TW |
| dc.subject | temporal pyramid | en |
| dc.subject | activity of daily livings | en |
| dc.subject | conditional random fileds | en |
| dc.title | 基於時序金字塔之第一人稱影像行為辨識 | zh_TW |
| dc.title | Activity Recognition in First-Person Camera View Based on
Temporal Pyramid | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 101-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 楊傳凱(Chuan-Kai Yang),徐宏民(Winston Hsu) | |
| dc.subject.keyword | 日常生活行為辨識,時序金字塔,條件隨機場, | zh_TW |
| dc.subject.keyword | activity of daily livings,temporal pyramid,conditional random fileds, | en |
| dc.relation.page | 30 | |
| dc.rights.note | 同意授權(全球公開) | |
| dc.date.accepted | 2013-07-23 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 資訊網路與多媒體研究所 | zh_TW |
| 顯示於系所單位： | 資訊網路與多媒體研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-102-1.pdf | 4.22 MB | Adobe PDF | 檢視/開啟 |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。