請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/78042
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 簡韶逸 | |
dc.contributor.author | Meng-Ting Zhong | en |
dc.contributor.author | 鍾孟庭 | zh_TW |
dc.date.accessioned | 2021-07-11T14:40:29Z | - |
dc.date.available | 2022-02-21 | |
dc.date.copyright | 2017-02-21 | |
dc.date.issued | 2016 | |
dc.date.submitted | 2016-11-14 | |
dc.identifier.citation | [1] Zhao, Rui, Wanli Ouyang, and Xiaogang Wang. 'Unsupervised salience learning for person re-identification.' Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2013.
[2] Das, Abir, Anirban Chakraborty, and Amit K. Roy-Chowdhury. 'Consistent re-identification in a camera network.' European Conference on Computer Vision. Springer International Publishing, 2014. [3] Li, Wei, et al. 'Deepreid: Deep filter pairing neural network for person re-identification.' Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2014. [4] McLaughlin, N., J. Martinez del Rincon, and P. Miller. 'Recurrent Convolutional Network for Video-based Person Re-Identification.' Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016. [5] Xiao, Tong, et al. 'Learning deep feature representations with domain guided dropout for person re-identification.' Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016. [6] Fleuret, Francois, et al. 'Multicamera people tracking with a probabilistic occupancy map.' IEEE Transactions on Pattern Analysis and Machine Intelligence 30.2 (2008): 267-282. [7] Berclaz, Jerome, et al. 'Multiple object tracking using k-shortest paths optimization.' IEEE transactions on pattern analysis and machine intelligence 33.9 (2011): 1806-1819. [8] D'Orazio, Tiziana, et al. 'A semi-automatic system for ground truth generation of soccer video sequences.' Advanced Video and Signal Based Surveillance, 2009. AVSS'09. Sixth IEEE International Conference on. IEEE, 2009. [9] De Vleeschouwer, Christophe, et al. 'Distributed video acquisition and annotation for sport-event summarization.' NEM summit 2008:: Towards Future Media Internet. 2008. [10] Ferryman, J., and A. Shahrokni. 'An overview of the pets 2009 challenge.' (2009). [11] Cao, Lijun, et al. 'An equalised global graphical model-based approach for multi-camera object tracking.' arXiv preprint arXiv:1502.03532 (2015). [12] Kuo, Cheng-Hao, Chang Huang, and Ram Nevatia. 'Inter-camera association of multi-target tracks by on-line learned appearance affinity models.' European Conference on Computer Vision. Springer Berlin Heidelberg, 2010. [13] Zhang, Shu, et al. 'A camera network tracking (CamNeT) dataset and performance baseline.' 2015 IEEE Winter Conference on Applications of Computer Vision. IEEE, 2015. [14] Milan, Anton, Konrad Schindler, and Stefan Roth. 'Challenges of ground truth evaluation of multi-target tracking.' Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 2013. [15] Felzenszwalb, Pedro F., et al. 'Object detection with discriminatively trained part-based models.' IEEE transactions on pattern analysis and machine intelligence 32.9 (2010): 1627-1645. [16] Cai, Yinghao, and Gerard Medioni. 'Exploring context information for inter-camera multiple target tracking.' IEEE Winter Conference on Applications of Computer Vision. IEEE, 2014. [17] Liao, Shengcai, et al. 'Person re-identification by local maximal occurrence representation and metric learning.' Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015. [18] Wang, Xiaogang. 'Intelligent multi-camera video surveillance: A review.' Pattern recognition letters 34.1 (2013): 3-19. [19] Ristani, Ergys, et al. 'Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking.' European Conference on Computer Vision. Springer International Publishing, 2016. [20] Huang, Wenxin, et al. 'Camera Network Based Person Re-identification by Leveraging Spatial-Temporal Constraint and Multiple Cameras Relations.' International Conference on Multimedia Modeling. Springer International Publishing, 2016. [21] Dollár, Piotr, et al. 'Fast feature pyramids for object detection.' IEEE Transactions on Pattern Analysis and Machine Intelligence 36.8 (2014): 1532-1545. [22] Tian, Y., Luo, P., Wang, X., Tang, X.: Deep learning strong parts for pedestrian detection. In: Proceedings of the IEEE International Conference on Computer Vision. (2015) 1904-1912. [23] Cai, Z., Saberian, M., Vasconcelos, N.: Learning complexity-aware cascades for deep pedestrian detection. In: Proceedings of the IEEE International Conference on Computer Vision. (2015) 3361-3369. [24] Zheng, Liang, et al. 'Person Re-identification in the Wild.' arXiv preprint arXiv:1604.02531 (2016). [25] Li, Zhen, et al. 'Learning locally-adaptive decision functions for person verification.' Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2013. [26] Köstinger, Martin, et al. 'Large scale metric learning from equivalence constraints.' Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on. IEEE, 2012. [27] D. Yi, Z. Lei, S. Liao, and S. Z. Li. Deep metric learning for person re-identification. In ICPR, pages 34–39, 2014. [28] Cheng, De, et al. 'Person re-identification by multi-channel parts-based CNN with improved triplet loss function.' Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016. [29] Per, Janez, et al. 'Dana36: A multi-camera image dataset for object identification in surveillance scenarios.' Advanced Video and Signal-Based Surveillance (AVSS), 2012 IEEE Ninth International Conference on. IEEE, 2012. [30] Baltieri, Davide, Roberto Vezzani, and Rita Cucchiara. '3dpes: 3d people dataset for surveillance and forensics.' Proceedings of the 2011 joint ACM workshop on Human gesture and behavior understanding. ACM, 2011. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/78042 | - |
dc.description.abstract | 在傳統的視訊感測器網路裡面,每台攝影機把各自的畫面傳回到伺服器上才進行分析,不過隨著環境中的攝影機數量越來越多,頻寬越來越不能負荷的這樣的傳輸量,攝影機所消耗的功率也越來越可觀,如果能採用分散式計算,再將重要的結果傳回伺服器,將會是一大突破。除了分散式外,我們也希望這樣的系統能夠及時得到結果,而且可攜性高,在一個新環境架設完成之後,能夠在不需要人為標記的前提下馬上運作。
另一方面,在不同的攝影機下辨認是不是同一個人仍然是一個困難的問題,因為同一個人在不同的攝影機下被照到的角度不一樣,有時候會被其他人擋住,有時候移動到畫面的遠處,看起來很小很模糊,這些情況都大大的影響了判斷的準確度,也顯示人為定義特徵的不足,很希望能利用卷積神經網路讓系統自己學習應該用哪些特徵來得到比較理想的結果。 這篇碩士論文提出了一個可以及時得到結果、基於卷積神經網路的系統,並利用視訊感測器網路的時間和空間線索調整配對結果,最後改善視訊特徵抽取方式,讓系統的精確度可以達到百分之八十以上,同時再現性達到百分之九十以上。與此同時,目前可取得的視訊測試資料各有不大適合應用在視訊感測器網路的地方,於是本篇論文也提供了新的視訊測試資料和一套改良的評量方式,用以評估基於此應用而開發的系統。 在論文的最後,系統得到的配對結果進一步用兩種方法視覺化,一種是哈利波特裡面的劫盜地圖,另一種則是個人化影片,希望藉由開發這樣的系統,讓視訊感測器網路的相關研究更貼近現實世界的應用。 | zh_TW |
dc.description.abstract | In traditional video sensor network, analysis starts after the collection of videos from each video sensor. However, with the number of video sensors growing in the environment, the limited bandwidth can hardly handle this kind of transmission, and power consumption becomes considerable. Consequently, distributed computation, on-line algorithm, and portable system that does not require manually labeling is needed.
On the other hand, human tracking in a video sensor network has been a challenging problem owing to pose variation, low resolution, and occlusion. At this moment, neural network based systems are expected to solve the problem by their great learning power. In this thesis, a convolutional neural network based video sensor network tracking system is proposed and improved. Furthermore, a newly collected dataset as well as a novel benchmark is provided for evaluation of video sensor network tracking systems. The proposed system reaches a promising result and further visualizes it, showing the possibility to realize the system in the real world. | en |
dc.description.provenance | Made available in DSpace on 2021-07-11T14:40:29Z (GMT). No. of bitstreams: 1 ntu-105-R03943021-1.pdf: 1831770 bytes, checksum: bcf9a3e1076dc0297b50f9f7636d5a97 (MD5) Previous issue date: 2016 | en |
dc.description.tableofcontents | ABSTRACT v
LIST OF FIGURES viii LIST OF TABLES ix Chapter 1 Introduction 1 1.1 Video Sensor Network 1 1.2 Challenges 2 1.2.1 Distributed 2 1.2.2 On-line 2 1.2.3 Portable 3 1.3 Video Sensor Network Tracking 3 1.4 Thesis Organization 4 Chapter 2 Related Work 5 2.1 Video Sensor Network Tracking 5 2.2 Detection 6 2.3 Re-Identification 6 2.4 Available Datasets 6 Chapter 3 Proposed System 8 3.1 System Overview 8 3.2 Pedestrian Detection 8 3.3 Tracking Stage I 9 3.4 Tracking Stage II 10 3.5 Re-Identification 11 3.5.1 Re-Identification between Video Sensors 11 3.5.2 Traveling Time Model 12 Chapter 4 Experiments 13 4.1 Dataset 13 4.2 Benchmark 14 4.2.1 Traditional Evaluation Approach 14 4.2.2 Recent Evaluation Approach 15 4.2.3 Proposed Benchmark 15 4.3 Experimental Results 15 4.3.1 Proposed System 16 4.3.2 Without Traveling Time Model 17 4.3.3 Without Connection Temporal Constraint 17 4.3.4 With Fewer Sample Points 17 4.3.5 Without Endpoints Avoidance 18 4.3.6 Without Resolution Selection 18 4.3.7 Without Connection Spatial Constraint 19 4.3.8 Without HSV Histogram 19 4.4 Applications 19 4.4.1 Marauder’s Map 20 4.4.2 Personal Video 20 Chapter 5 Conclusion 22 REFERENCE 23 | |
dc.language.iso | en | |
dc.title | 應用於視訊感測器網路之分散式線上目標追蹤技術 | zh_TW |
dc.title | Distributed On-line Object Tracking in a Video Sensor Network | en |
dc.type | Thesis | |
dc.date.schoolyear | 105-1 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 盧奕璋,黃朝宗,曹昱 | |
dc.subject.keyword | 偵測,追蹤,感測器網路,卷積神經網路,線上,分散式, | zh_TW |
dc.subject.keyword | detection,tracking,re-identification,video sensor network,convolutional neural network,on-line,distributed, | en |
dc.relation.page | 26 | |
dc.identifier.doi | 10.6342/NTU201603737 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2016-11-15 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 電子工程學研究所 | zh_TW |
顯示於系所單位: | 電子工程學研究所 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-105-R03943021-1.pdf 目前未授權公開取用 | 1.79 MB | Adobe PDF |
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。