علوم رایانش و فناوری اطلاعات

ردیابی ابربی‌درنگی اهداف همزمانِ‌متحرک در تصاویر ویدئویی

نویسندگان

دانشکده فنی مهندسی، دانشگاه شاهد، تهران، ایران

چکیده

اکنون نیاز به پردازش ابربی‌درنگ و استفاده از الگوریتم‌های موازی، سریع و کارا در ردیابی همزمان اشیاء برای پردازشسریع داده‌های عظیم تصویری اجتناب‌ناپذیر است. در این مقاله روش موازی مبتنی‌بر توصیف‌کننده‌های باینری محلی برای ردیابی همزمان 50 شیء با سرعت بی‌درنگ ارائه می‌شود. روش پیشنهادی ضمن مدل‌سازی چندنخی ردیابی و تشخیص اشیاء با استفاده از مدل FREAK در تصاویر ویدئویی، عمل ردیابی همزمان بی‌درنگِ برخط را انجام می‌دهد. نتایج آزمایش‌های تجربی در تصاویر با 330 فریم بر ثانیه نشان می‌دهد که این روش ضمن برخورداری از سرعت زیاد و ردیابی همزمان اشیاء با سناریوهای مختلف در مقایسه با چهار الگوریتم مهم توصیف‌کننده، دارای بهترین کارایی و عملکرد است. سیستم ردیابی سریال مبتنی بر توصیف‌کننده FREAK، قادر به ردیابی یک شیء با سرعت 60 فریم بر ثانیه است درحالی‌که در ردیابی موازی پیشنهادی با سرعت 330 فریم بر ثانیه و تا 5.5 برابر سریع‌تر ردیابی می‌کند. همچنین این ردیاب قادر به ردیابی بی‌درنگ در حالت سریال حداکثر تا 7 شیء همزمان و در حالت موازی قادر به ردیابی ابربی‌درنگ تا 50 شیء است. 

کلیدواژه‌ها

  • [1] YouTube Processes 100 Hours of Video Each Minute. Available: http://thenextweb.com/google/2013/05/19/youtube-100-million-hours-per-minute/
  • [2] T. Acharya and A. K. Ray, Image processing: principles and applications: John Wiley & Sons, 2005.
  • [3] S. X. Guo, J. X. Chen, and B. Peng, "Research of Object Tracking Algorithm Based on BRISK," in Advanced Materials Research, pp. 1496-1501, 2014.
  • [4] B. Minnehan, H. Spang, and A. E. Savakis, "Robust and Efficient Tracker using Dictionary of Binary Descriptors and Locality Constraints," in Advances in Visual Computing, Springer, pp. 589-598, 2014.
  • [5] K. Chen, C. Lin, S. Zhong, and L. Guo, "A Parallel SRM Feature Extraction Algorithm for Steganalysis Based on GPU Architecture," in Parallel Architectures, Algorithms and Programming (PAAP), 2014 Sixth International Symposium on, pp. 178-182, 2014.
  • [6] S. Heymann, K. Müller, A. Smolic, B. Froehlich, and T. Wiegand, "SIFT implementation and optimization for general-purpose GPU," in WSCG"2007 International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, 2007.
  • [7] D. A. Forsyth and J. Ponce, Computer Vision: A Modern Approach, pp. 88-101, 2003.
  • [8] Y. Yuan, S. Emmanuel, W. Lin, and Y. Fang, "Visual object tracking based on appearance model selection," in Multimedia and Expo Workshops (ICMEW), IEEE International Conference on, pp. 1-4, 2013.
  • [9] T. Hachaj and M. R. Ogiela, "Rule-based approach to recognizing human body poses and gestures in real time," Multimedia Systems, vol. 20, pp. 81-99, 2014.
  • [10] Z. Kalal, K. Mikolajczyk, and J. Matas, "Tracking-learning-detection," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 34, pp. 1409-1422, 2012.
  • [11] S.-W. Ha and Y.-H. Moon, "Multiple object tracking using SIFT features and location matching," International Journal of Smart Home, vol. 5, pp. 17-26, 2011.
  • [12] H. Zhou, Y. Yuan, and C. Shi, "Object tracking using SIFT features and mean shift," Computer vision and image understanding, vol. 113, pp. 345-352, 2009.
  • [13] C. Harris and M. Stephens, "A combined corner and edge detector," in Alvey vision conference, p. 50, 1988.
  • [14] H. P. Moravec, Obstacle avoidance and navigation in the real world by a seeing robot rover, STANFORD UNIV CA DEPT OF COMPUTER SCIENCE, 1980.
  • [15] D. G. Lowe, "Object recognition from local scale-invariant features," in Computer vision, The proceedings of the seventh IEEE international conference on, pp. 1150-1157, 1999.
  • [16] J. Xing and Z. Miao, "An improved algorithm on image stitching based on SIFT features," in Innovative Computing, Information and Control, ICICIC"07. Second International Conference on, pp. 453-453, 2007.
  • [17] W. He, et al. "Spatiotemporal local compact binary pattern for background subtraction in complex scenes." Multimedia Tools and Applications, vol.78, no.22, pp. 31415-31439, 2019.
  • [18] H. Bay, T. Tuytelaars, and L. Van Gool, "Surf: Speeded up robust features," in Computer vision–ECCV 2006, pp. 404-417, 2006.
  • [19] D. Wagner, G. Reitmayr, A. Mulloni, T. Drummond, and D. Schmalstieg, "Real-time detection and tracking for augmented reality on mobile phones," Visualization and Computer Graphics, IEEE Transactions on, vol. 16, pp. 355-368, 2010.
  • [20] M. Calonder, V. Lepetit, C. Strecha, and P. Fua, "Brief: Binary robust independent elementary features," in Computer Vision–ECCV, Springer, pp. 778-792, 2010.
  • [21] E. Rosten and T. Drummond, "Fusing points and lines for high performance tracking," in Computer Vision, ICCV Tenth IEEE International Conference on, pp. 1508-1515, 2005.
  • [22] E. Rosten and T. Drummond, "Machine learning for high-speed corner detection," in Computer Vision–ECCV, Springer, pp. 430-443, 2006.
  • [23] S. Leutenegger, M. Chli, and R. Y. Siegwart, "BRISK: Binary robust invariant scalable keypoints," in Computer Vision (ICCV), IEEE International Conference on, pp. 2548-2555, 2011.
  • [24] C. J. Veenman, M. J. Reinders, and E. Backer, "Resolving motion correspondence for densely moving points," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 23, pp. 54-72, 2001.
  • [25] T. J. Broida and R. Chellappa, "Estimation of object motion parameters from noisy images," Pattern Analysis and Machine Intelligence, IEEE Transactions on, pp. 90-99, 1986.
  • [26] M. J. Deilamani and R. N. Asli, "Moving object tracking based on mean shift algorithm and features fusion," in Artificial Intelligence and Signal Processing (AISP), International Symposium on, pp. 48-53, 2011.
  • [27] G. R. Bradski, "Real time face and object tracking as a component of a perceptual user interface," in Applications of Computer Vision, Fourth IEEE Workshop on, pp. 214-219, 1998.
  • [28] J. Zhang, S. Luo, and X. Liu, "Weighted Mean Shift Object Tracking Implemented on GPU for Embedded Sustems," in Proceedings of the 2012 International Conference on Control Engineering and Communication Technology, pp. 982-985, 2012.
  • [29] G. D. Hager and P. N. Belhumeur, "Efficient region tracking with parametric models of geometry and illumination," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 20, pp. 1025-1039, 1998.
  • [30] I. Matthews, T. Ishikawa, and S. Baker, "The template update problem," IEEE transactions on pattern analysis and machine intelligence, vol. 26, pp. 810-815, 2004.
  • [31] N. Alt, S. Hinterstoisser, and N. Navab, "Rapid selection of reliable templates for visual tracking," in Computer Vision and Pattern Recognition (CVPR), IEEE Conference on, pp. 1355-1362, 2010.
  • [32] G. Tsagkatakis and A. Savakis, "Online distance metric learning for object tracking," Circuits and Systems for Video Technology, IEEE Transactions on, vol. 21, pp. 1810-1821, 2011.
  • [33] B. Babenko, M.-H. Yang, and S. Belongie, "Robust object tracking with online multiple instance learning," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 33, pp. 1619-1632, 2011.
  • [34] D.-N. Ta, W.-C. Chen, N. Gelfand, and K. Pulli, "Surftrac: Efficient tracking and continuous object recognition using local feature descriptors," in Computer Vision and Pattern Recognition, IEEE Conference on, pp. 2937-2944, 2009.
  • [35] N. Whitehead and A. Fit-Florea, "Precision & performance: Floating point and IEEE 754 compliance for NVIDIA GPUs," rn (A+ B), vol. 21, pp. 1-1874919424, 2011.
  • [36] HTTPS://github.com/MohammadRezaNajafi/.
  • [37] http://cvlab.hanyang.ac.kr/tracker_benchmark/datasets.html.
علوم رایانش و فناوری اطلاعات
دوره 18، شماره 1
بهار و تابستان
اردیبهشت 1399