آشکارسازی الگوهای ترافیکی در نظارت تصویری با استفاده از الگوریتم شار نوری و مدل موضوعی
محورهای موضوعی : مهندسی برق و کامپیوترامین مرادی 1 , اسداله شاه بهرامی 2 , علیرضا آکوشیده 3
1 - دانشگاه گیلان
2 - دانشگاه گیلان
3 - دانشگاه فنی و حرفه ای استان گیلان
کلید واژه: الگوهای ترافیکیمدل موضوعی (TM)شار نوری کدگذاری موضوعی تُنُک گروهی (GSTC),
چکیده مقاله :
نیاز روزافزون به نظارت، کنترل و مدیریت هوشمند باعث پیشرفت تحقیقات در حوزه سامانه‌های نظارت تصویری برای مثال در سیستم‌های حمل و نقل هوشمند شده است. با توجه به مقدار زیاد داده‌های این سامانه‌ها، استخراج الگوها و برچسب‌گذاری خودکار آنها از چالش‌های پیش رو است. در این مقاله به منظور آشکارسازی و استخراج الگوهای ترافیکی در تقاطع‌ها از مدل موضوعی استفاده گردید به طوری که الگوهای بصری به کلمات بصری تبدیل می‌شوند. ابتدا ویدئوی ورودی به کلیپ‌ها تقسیم می‌شوند. سپس ویژگی‌های شار نوری کلیپ‌ها که مبتنی بر اطلاعات فراوان بردار حرکات محلی هستند، با استفاده از الگوریتم شار نوری محاسبه و به کلمات بصری تبدیل می‌شوند. بعد از آن، با یک مدل موضوعی غیر احتمالی به روش کدگذاری موضوعی تُنُک گروهی، الگوهای ترافیکی به سیستم طراحی‌شده آموزش داده می‌شود. این الگوها، نشان‌دهنده حرکت قابل مشاهده هستند که می‌تواند برای توصیف یک صحنه، با پاسخ به سؤال رفتاری مانند "یک وسیله نقلیه به کجا می‌رود؟" مورد استفاده قرار بگیرند. نتایج پیاده‌سازی روش پیشنهادی بر روی بانک داده ویدئوی QMUL نشان داد که روش پیشنهادی می‌تواند الگوهای معنادار ترافیکی مانند گردش به چپ، گردش به راست و گذر از چهارراه را به درستی آشکار کند و نمایش دهد.
Research in the field of video surveillance systems has been improving because of the increasing need for intelligent monitoring, control and management. Given the large amount of data on these intelligent transportation systems, extracting patterns and automatically labeling them is a challenging task. In this paper, a topic model was used to detect and extract traffic patterns at intersections so that visual patterns are transformed into visual words. The input video is first split into clips. Then, the flow characteristics of the clips, which are based on abundant local motion vector information, are computed using optical flow algorithms and converted to visual words. After that, with a non-probabilistic topic model, the traffic patterns are extracted to the designed system by a group sparse topical coding method. These patterns represent visible motion that can be used to describe a scene by answering a behavioral question such as: Where does a vehicle go? The results of the implementation of the proposed method on the QMUL video database show that the proposed method can correctly detect and display meaningful traffic patterns such as turn left, turn right and crossing a roundabout.
[1] W. Fu, J. Wang, H. Lu, and S. Ma, "Dynamic scene understanding by improved sparse topical coding," Pattern Recogn., vol. 46, no. 7, pp. 1841-1850, Jul. 2013.
[2] W. Fu, J. Wang, Z. Li, H. Lu, and S. Ma, "Learning semantic motion patterns for dynamic scenes by improved sparse topical coding," in Proc. IEEE Int. Conf. on Multimedia and Expo, pp. 296-301, Melbourne, Australia, 9-13 Jul. 2012.
[3] A. Basharat, A. Gritai, and M. Shah, "Learning object motion patterns for anomaly detection and improved object detection," in Proc. IEEE Conf. on Computer Vision and Pattern Recognition, 8 pp., Anchorage, AK, USA, 23-28 Jun. 2008.
[4] H. Weiming, et al., "A system for learning statistical motion patterns," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 28, no. 9, pp. 1450-1464, Jul. 2006.
[5] D. Lin, E. Grimson, and J. Fisher, "Modeling and estimating persistent motion with geometric flows," in Proc. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, 8 pp., San Francisco, CA, USA, 13-18 Jun. 2010.
[6] M. Enzweiler and D. M. Gavrila, "Integrated pedestrian classification and orientation estimation," in Proc. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, pp. 982-989, San Francisco, CA, USA, 13-18 Jun. 2010.
[7] D. Fortun, P. Bouthemy, and C. Kervrann, "Optical flow modeling and computation: a survey," Computer Vision and Image Understanding, vol. 134, no. 1, pp. 1-21, May 2015.
[8] X. Wang, "Action recognition using topic models," in Visual Analysis of Humans: Looking at People, T. B. Moeslund, A. Hilton, V. Krüger, and L. Sigal Eds. London: Springer London, pp. 311-332, 2011.
[9] A. Adam, E. Rivlin, I. Shimshoni, and D. Reinitz, "Robust real-time unusual event detection using multiple fixed-location monitors," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 30, no. 3, pp. 555-560, Jan. 2008.
[10] D. Kuettel, M. D. Breitenstein, L. V. Gool, and V. Ferrari, "What's going on? discovering spatio-temporal dependencies in dynamic scenes," in Proc. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, pp. 1951-1958, San Francisco, CA, USA, 13-18 Jun. 2010.
[11] S. Rana, D. Phung, S. Pham, and S. Venkatesh, "Large-scale statistical modeling of motion patterns: a bayesian nonparametric approach," in Proc. of the 8th Indian Conf. on Computer Vision, Graphics and Image Processing, vol. 7, 8 pp., Mumbai, India, Dec. 2012.
[12] L. Song, F. Jiang, Z. Shi, R. Molina, and A. K. Katsaggelos, "Toward dynamic scene understanding by hierarchical motion pattern mining," IEEE Trans. on Intelligent Transportation Systems, vol. 15, no. 3, pp. 1273-1285, Feb. 2014.
[13] J. Varadarajan, R. Emonet, and J. M. Odobez, "A sequential topic model for mining recurrent activities from long term video logs," International J. of Computer Vision, vol. 103, no. 1, pp. 100-126, May 2013.
[14] T. Hofmann, "Probabilistic latent semantic analysis," in Proc. of the 15th Conf. on Uncertainty in Artificial Intelligence, Stockholm, Sweden, vol. 1, pp. 289-296, Stockholm, Sweden, 30 Jul.-1 Aug. 1999.
[15] D. M. Blei, A. Y. Ng, and M. I. Jordan, "Latent dirichlet allocation," J. Mach. Learn. Res., vol. 3, no. 4, pp. 993-1022, Mar. 2003.
[16] Y. W. Teh, M. I. Jordan, M. J. Beal, and D. M. Blei, "Hierarchical dirichlet processes," J. of the American Statistical Association, vol. 101, no. 476, pp. 1566-1581, Jan. 2012.
[17] K. Than and T. B. Ho, "Fully sparse topic models," in Proc. Joint European Conf. on Machine Learning and Knowledge Discovery in Databases, Springer, pp. 490-505, Bristol, UK, 24-28 Sept. 2012.
[18] J. Zhu and E. P. Xing, "Sparse topical coding," in Proc. of the 27th Conf. on Uncertainty in Artificial Intelligence, pp. 831-838, Barcelona, Spain, 14-17 Jul. 2011.
[19] L. Bai, J. Guo, Y. Lan, and X. Cheng, "Group sparse topical coding: from code to topic," in Proc. of the 6th ACM Int. Conf. on Web Search and Data Mining, pp. 315-324, Rome, Italy, 4-8 Feb.2013.
[20] P. Ahmadi, M. Tabandeh, and I. Gholampour, "Abnormal event detection and localisation in traffic videos based on group sparse topical coding," IET Image Processing, vol. 10, no. 3, pp. 235-246, Mar. 2016.
[21] C. Stauffer and W. E. L. Grimson, "Learning patterns of activity using real-time tracking," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 22, no. 8, pp. 747-757, Aug. 2000.
[22] B. T. Morris and M. J. J. O. E. I. Trivedi, "Understanding vehicular traffic behavior from video: a survey of unsupervised approaches," Journal of Electronic Imaging, vol. 22, no. 4, Article No. 041113, 15 pp., Oct./Dec. 2013.
[23] L. Song, F. Jiang, Z. Shi, and A. K. Katsaggelos, "Understanding dynamic scenes by hierarchical motion pattern mining," in Proc. IEEE Int. Conf. on, Multimedia and Expo, 6 pp., Barcelona, Spain, 11-15 Jul. 2011.
[24] X. Wang, X. Ma, and W. E. L. Grimson, "Unsupervised activity perception in crowded and complicated scenes using hierarchical bayesian models," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 31, no. 3, pp. 539-555, Dec. 2008.
[25] R. Khoshabeh, T. Gandhi, and M. M. Trivedi, "Multi-camera based traffic flow characterization & classification," in Proc. IEEE Intelligent Transportation Systems Conf., pp. 259-264, Seattle, WA, USA, 30 Sept.- 3 Oct. 2007.
[26] S. J. Wright, "Coordinate descent algorithms," Mathematical Programming, vol. 151, no. 1, pp. 3-34, Jun. 2015.
[27] J. L. Rodgers and A. W. Nicewander, "Thirteen ways to look at the correlation coefficient," The American Statistician, vol. 42, no. 1, pp. 59-66, Feb. 1988.
[28] A. Omidi, E. Nourani, and M. Jalili, "Forecasting stock prices using financial data mining and neural network," in Proc. 3rd IEEE Int. Conf. on Computer Research and Development, , vol. 3, pp. 242-246, Mar. 2011.
[29] C. Zach, T. Pock, and H. Bischof, "A duality based approach for realtime TV-L1 optical flow," in Pattern Recognition, Lecture Notes in Computer Science, Springer, Berlin, Heidelberg, vol. 4713, pp. 214-223, Sept. 2007.
