A scene-adaptive motion detection model based on machine learning and data clustering

详细信息    查看全文

• 作者：Tao Hu (1)
  Minghui Zheng (1)
  Jun Li (1)
  Li Zhu (1)
  Jia Hu (2)
  
  1. School of Information Engineering ; Hubei University for Nationalities ; Enshi ; Hubei ; China
  2. Department of Mathematics and Computer Science ; Liverpool Hope University ; Liverpool ; L16 9JD ; UK
  
• 关键词：Motion detection ; Clustering ; Machine learning ; Scene ; adaptive
• 刊名：Multimedia Tools and Applications
• 出版年：2015
• 出版时间：April 2015
• 年：2015
• 卷：74
• 期：8
• 页码：2821-2839
• 全文大小：1,154 KB
• 参考文献：1. Alpaydm, E (2004) Introduction to machine learning. The MIT Press, MD
  2. Barron, JL, Fleet, DJ, Beauchemin, SS (1994) Performance of optical flow techniques. Int J Comput Vis 12: pp. 43-77 CrossRef
  3. Bishop, CM (2006) Pattern recognition and machine learning. Springer, MD
  4. Chan PK, Mahoney MV, Arshad MH (2003) 鈥淎 machine learning approach to anomaly detection.鈥?Technical Report, CS-2003-06
  5. Chaudhary, A, Raheja, JL, Das, K, Raheja, S (2011) Intelligent approaches to interact with machines using hand gesture recognition in natural way: a survey. Int J Comput Sci Eng Surv 2: pp. 122-133 CrossRef
  6. Chen, D, Yang, J (2007) Robust object tracking via online dynamic spatial bias appearance models. IEEE Trans Pattern Anal Mach Intell 29: pp. 2157-2169 CrossRef
  7. Comaniciu, D, Meer, P (2002) Mean shift: a robust approach toward feature space analysis. IEEE Trans Pattern Anal Mach Intell 24: pp. 603-619 CrossRef
  8. Comanicu D, Ramesh V, Meer P (2000) 鈥淩eal-time tracking of non-rigid objects using mean shift.鈥?Proc of International Conference on Computer Vision and Pattern Recognition: 142鈥?49
  9. Cutler R, Davis L (1998) 鈥淰iew-based detection and analysis of periodic motion.鈥?Proc. of the Fourteenth International Conference on Pattern Recognition(ICPR98) 1:495鈥?00
  10. Dixon KR, Lippitt CE, Forsythe JC (2005) 鈥淪upervised machine learning for modeling human recognition of vehicle-driving situation.鈥?Proc. of the IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS鈥?5): 604鈥?09
  11. Dong, H, Giakoumidis, N, Juma, JB, Tretyakov, DA, Mavridis, N (2012) A fast laser motion detection and approaching behavior monitoring method of moving object alarm system(MOAS). Procedia Eng 41: pp. 749-756 CrossRef
  12. Elhabian, SY, El-Sayed, KM, Ahmed, SH (2008) Moving object detection in spatial domain using background removal techniques鈥搒tate-of-art. Recent Patents Comput Sci 1: pp. 32-54 CrossRef
  13. Fablet R, Bouthemy P, Gelgon M (1999) 鈥淢oving object detection in color image sequences using region-level graph labeling.鈥?Proc. of the IEEE International Conference on Image Processing(ICIP鈥?9) 2:939鈥?43
  14. Fung G (2001) 鈥淎 comprehensive overview of basic clustering algorithm鈥?/span>
  15. Gall, J, Yao, A, Razavi, N, Gool, L, Lempitsky, V (2011) Hough forests for object detection, tracking and action recognition. IEEE Trans Pattern Anal Mach Intell 33: pp. 2188-2202 CrossRef
  16. Guanglong, H, Shiyin, Q (2012) High precision detection of a mobile object under dynamic imaging based on SURF and mean shift. CAAI Trans Intell Syst 7: pp. 61-68
  17. Haritaoglu I, Harwood D, Davis LS (1998) 鈥淲4: who? when? where? what? a real time system for detecting and tracking people.鈥?Proc. of the Third IEEE International Conference on Automatic Face and Gesture Recognition(ICAFGR鈥?8): 222鈥?27
  18. Hu T, Zhu L (2010) 鈥淭he moving detection algorithm based on clustering technology.鈥?Proc. of the International Conference on Computer and Communication Technologies in Agriculture Engineering(CCTAE鈥?0): 83鈥?86
  19. Jain, R, Kasturi, R, Schunck, BG (1995) Machine vision. McGraw-Hill Inc, MD
  20. Kentaro T, Krumm J, Brumitt B, Meyers B (1999) 鈥淧rinciples and practice of background maintenance.鈥?Proc. of the Seventh IEEE International Conference on Computer Vision(ICCV鈥?9) 1:255鈥?61
  21. Olson, CF (1995) Parallel algorithm for hierarchical clustering. Parallel Comput 21: pp. 1313-1325 CrossRef
  22. Piciarelli, C, Foresti, GL (2011) Surveillance-oriented event detection in video streams. Intell Syst 26: pp. 32-41 CrossRef
  23. Richard, J, Radke, S, AI-Kofahi, O, Roysam, B (2005) Image change detection algorithms: a systematic survey. IEEE Trans Image Process 14: pp. 294-307 CrossRef
  24. Scott, DW (1992) Multivariate density estimation: theory, practice, and visualization. A Wiley-Interscience Publication, MD
  25. Shafe, AA, Hafz, F, Ali, MH (2009) Motion detection techniques using potical flow. World Acad Sci Eng Technol 32: pp. 559-561
  26. Stenger B, Ramesh V, Paragios N, Coetzee F, Buhmann JM (2001) 鈥淭opology free hidden Markov models: application to back-ground modeling.鈥?Proc. of the Eighth IEEE International Conference on Computer Vision(ICCV鈥?1) 1:294鈥?01
  27. Witten, I, Frank, E (2005) Data mining. Morgan Kaufmann press, MD
  28. Zhou Z, Niu B, Ke C, Wu W (2010) 鈥淪tatic object tracking in road panoramic videos.鈥?Proc. of 2010 I.E. International Symposium on Multimedia: 57鈥?4
  
• 刊物类别：Computer Science
• 刊物主题：Multimedia Information Systems
  Computer Communication Networks
  Data Structures, Cryptology and Information Theory
  Special Purpose and Application-Based Systems
  
• 出版者：Springer Netherlands
• ISSN：1573-7721

文摘

Due to its wide applications and importance in computer vision, motion detection has been receiving considerable attention from industry and academy. However, previous motion detection algorithms fail to achieve the flexibility and accuracy simultaneously for good detection results. In the present work, a scene-adaptive motion detection model based on machine learning and clustering technology is proposed. This model begins with training to the system by a group of testing images, in terms of various accurate parameters of one certain scene. Significant modifications have been reserved in the same area during motion detection, which are considered as a change clustering. Then, the model takes advantage of clustering technology to generate a minimum spanning tree (MST), which is one kind of average linkage clustering. The average shortest distance of the minimum spanning tree serves as a benchmark to identify the change in images. Finally the training parameters and detection algorithm are combined to monitor the scene. The clustering is introduced to this model during sample training, in order to obtain factors of higher quality followed by more accurate detection results. Finally, the experiment confirms the excellent adaptability and precision of the proposed motion detection model.