臺灣博碩士論文加值系統

物聯網概念的興起，低複雜度的感測節點成為開發的趨勢。本論文為將完整的物件偵測和追蹤實作於低成本嵌入式DSP平台，並進行效能上的驗證，目的是開發出一個低複雜度、低硬體資源需求，且無作業系統的智慧型嵌入式攝影機系統。在移動物偵測方面，我們採用近似中值濾波法實作背景建模，由於其複雜度低，不需太多的記憶體資源，因此作為物件偵測的主要方法。接著我們應用PSO演算法，偵對移動物建立移動物樣板，並利用粒子群全域最佳化進行非線性的移動物追蹤。此系統在記憶體資源有限及開發成本有限的情況下，能達到即時運算的需求，且系統以C語言作為開發工具，可移植性高，未來可作為物聯網中智慧監控攝影機的應用。

In rising of IoT, low-complexity sensor node is the trend of development. This paper implements complete object detection and tracking on a low-cost DSP platform, and verify the system performance on efficacy. Our goal is to achieve an intelligent embedded camera of low-complexity, hardware-constrained, and without operating system. For detection, because of the low-complexity, the paper utilize Approximated Median Filter (AMF) to achieve background modeling for the main method of object detection. Then particle swarm optimization (PSO) is main method which is used as tracking strategy: First, build the target model for moving object. Through PSO algorithm, the system can track moving objects in the nonlinear system. Limited on the memory and development costs, the experiments and analysis still show the efficiency. Due to using C language as development tools, the system is high portability. The proposed system can be the IoT application system case in the future.

摘要 i
Abstract ii
誌謝 iii
目錄 iv
圖目錄 vii
表目錄 ix
第一章、緒論 1
1.1研究背景 1
1.2研究目的 2
1.3論文架構 2
第二章、文獻回顧 3
2.1背景移除法(Background Subtraction) 3
2.1.1影像差異法(Frame Difference) 4
2.1.2近似中值濾波法(Approximated Median Filtering) 4
2.1.3單高斯背景模型(Single Gaussian Background Model) 5
2.1.4混和高斯背景模型(Gaussian Mixture Model, GMM) 6
2.1.5碼本背景模型(Codebook Background Model,CB) 8
2.2物件追蹤 8
2.2.1連通區塊追蹤(Blob Tracking) 9
2.2.2輪廓追蹤(Contour Tracking) 9
2.2.3特徵追蹤(Visual Feature Matching) 9
2.2.4多特徵聯合稀疏表示(Multi-Feature Joint Sparse Representation) 10
2.2.5粒子濾波器追蹤(Particle Filter Tracking) 10
2.2.6粒子群體最佳化(Particl Swarm Optimization Tracking, PSO) 10
2.3嵌入式視覺(Embedded Vision) 12
第三章、嵌入式物件偵測與追蹤系統設計 14
3.1 MIAT系統設計方法論 14
3.1.2 GRAFCET離散事件建模 17
3.2系統架構設計 18
3.3離散事件建模 20
3.3.1物件偵測模組 21
3.3.2特徵擷取 24
3.3.3物件追蹤模組 25
3.4軟體合成 27
第四章、DSP系統實作與整合驗證 31
4.1實驗平台 31
4.2 DSP嵌入式視覺系統開發流程 35
4.3嵌入式軟體實作 37
4.4系統整合驗證與實驗 41
4.4.1系統整合驗證 41
4.4.2效能分析 43
第五章、結論與未來研究方向 45
5.1結論 45
5.2未來研究方向 46
參考文獻 47

[1] 常賽, "基於專用物聯網的遠端更新技術研究與應用," 蘇州: 蘇州大學, 2011.
[2] ReportLinker. Intelligent Video Surveillance, VCA & Video Analytics: Technologies & Global Market – 2013-2020. Available: http://www.reportlinker.com/p01154046-summary/Intelligent-Video-Surveillance-VCA-Video-Analytics-Technologies-Global-Market-.html
[3] 盧美榮, "移動物件偵測的背景移除方法之比較研究," 資訊工程學系, 國立中央大學, 2016.
[4] N. J. McFarlane and C. P. Schofield, "Segmentation and tracking of piglets in images," Machine vision and applications, vol. 8, pp. 187-193, 1995.
[5] C.-H. Chen, C.-C. Wang, and M.-C. Yan, "Robust tracking of multiple persons in real-time video," Multimedia Tools and Applications, pp. 1-15, 2016.
[6] C. Stauffer and W. E. L. Grimson, "Adaptive background mixture models for real-time tracking," in Computer Vision and Pattern Recognition, 1999. IEEE Computer Society Conference on., 1999.
[7] K. Kim, T. H. Chalidabhongse, D. Harwood, and L. Davis, "Real-time foreground–background segmentation using codebook model," Real-time imaging, vol. 11, pp. 172-185, 2005.
[8] G. Deng and K. Guo, "Self-adaptive background modeling research based on change detection and area training," in Electronics, Computer and Applications, 2014 IEEE Workshop on, 2014, pp. 59-62.
[9] C. R. Wren, A. Azarbayejani, T. Darrell, and A. P. Pentland, "Pfinder: Real-time tracking of the human body," IEEE Transactions on pattern analysis and machine intelligence, vol. 19, pp. 780-785, 1997.
[10] A. Elgammal, D. Harwood, and L. Davis, "Non-parametric model for background subtraction," in European conference on computer vision, 2000, pp. 751-767.
[11] R. T. Collins, "Mean-shift blob tracking through scale space," in Computer Vision and Pattern Recognition, 2003. Proceedings. 2003 IEEE Computer Society Conference on, 2003, pp. II-234-40 vol. 2.
[12] Z. Li, Q. Tang, and N. Sang, "Improved mean shift algorithm for occlusion pedestrian tracking," Electronics Letters, vol. 44, pp. 622-623, 2008.
[13] D. Koller, K. Daniilidis, and H.-H. Nagel, "Model-based object tracking in monocular image sequences of road traffic scenes," International Journal of Computer 11263on, vol. 10, pp. 257-281, 1993.
[14] Q. Delamarre and O. Faugeras, "3D articulated models and multi-view tracking with silhouettes," in Computer Vision, 1999. The Proceedings of the Seventh IEEE International Conference on, 1999, pp. 716-721.
[15] P. KaewTrakulPong and R. Bowden, "Adaptive Visual System for Tracking Low Resolution Colour Targets," in BMVC, 2001, pp. 243-52.
[16] J. Sturges and T. Whitfield, "Locating basic colours in the Munsell space," Color Research & Application, vol. 20, pp. 364-376, 1995.
[17] R. Bourezak and G. Bilodeau, "Object detection and tracking using iterative division and correlograms," in The 3rd Canadian Conference on Computer and Robot Vision (CRV'06), 2006, pp. 38-38.
[18] W. Hu, W. Li, X. Zhang, and S. Maybank, "Single and multiple object tracking using a multi-feature joint sparse representation," IEEE transactions on pattern analysis and machine intelligence, vol. 37, pp. 816-833, 2015.
[19] S. Zhang, H. Yao, and S. Liu, "Robust visual tracking using feature-based visual attention," in 2010 IEEE International Conference on Acoustics, Speech and Signal Processing, 2010, pp. 1150-1153.
[20] X. Jia, H. Lu, and M.-H. Yang, "Visual tracking via adaptive structural local sparse appearance model," in Computer vision and pattern recognition (CVPR), 2012 IEEE Conference on, 2012, pp. 1822-1829.
[21] F. Chang, L. Ma, and Y. Qiao, "Target tracking under occlusion by combining integral-intensity-matching with multi-block-voting," in International Conference on Intelligent Computing, 2005, pp. 77-86.
[22] K. Nummiaro, E. Koller-Meier, and L. Van Gool, "An adaptive color-based particle filter," Image and vision computing, vol. 21, pp. 99-110, 2003.
[23] P.-F. Cheng, W. Wang, and C. Lin, "Adaptive Object Detection and Tracking," ICL Technical Journal, vol. 20, pp. 78-84, 2007.
[24] R. C. Eberhart and J. Kennedy, "A new optimizer using particle swarm theory," in Proceedings of the sixth international symposium on micro machine and human science, 1995, pp. 39-43.
[25] Y.-W. Bai, Z.-L. Xie, and Z.-H. Li, "Design and implementation of a home embedded surveillance system with ultra-low alert power," IEEE Transactions on Consumer Electronics, vol. 57, pp. 153-159, 2011.
[26] H.-N. Nguyen and A.-C. Lee, "Real time tracking multiple YUV 24-bit color objects with 8-bit MCU-based embedded vision system," in Innovative Computing, Information and Control (ICICIC), 2009 Fourth International Conference on, 2009, pp. 160-164.
[27] N.-J. Li, C.-F. Weng, W.-J. Wang, H.-C. Chen, and P.-J. Lee, "The people number estimation based on the embedded DSP system with surveillance camera," in System Science and Engineering (ICSSE), 2013 International Conference on, 2013, pp. 57-61.
[28] M. Lemmou and N. Dahnoun, "Real-time object detection for a panning/tilting surveillance camera using an embedded DSP platform," in Education and Research Conference (EDERC), 2010 4th European, 2010, pp. 225-230.
[29] A. Muscoloni and S. Mattoccia, "Real-time tracking with an embedded 3D camera with FPGA processing," in 2014 International Conference on 3D Imaging (IC3D), 2014, pp. 1-7.
[30] J. Albo-Canals, S. Ortega, S. Perdices, A. Badalov, and X. Vilasis-Cardona, "Embedded low-power low-cost Camera Sensor based on FPGA and its applications in mobile robots," in Electronics, Circuits and Systems (ICECS), 2012 19th IEEE International Conference on, 2012, pp. 336-339.
[31] C.-H. Chen, C.-M. Kuo, C.-Y. Chen, and J.-H. Dai, "The design and synthesis using hierarchical robotic discrete-event modeling," Journal of Vibration and Control, p. 1077546312449645, 2012.
[32] ADSP-BF707 Available: http://www.analog.com/en/products/processors-dsp/blackfin/adsp-bf707.html#product-overview
[33] ADZS-BF707-BLIP2. Available: http://www.analog.com/en/design-center/evaluation-hardware-and-software/evaluation-boards-kits/adzs-bf707-blip2.html#eb-overview