الگوريتم رديابي بالا به پايين بر اساس يادگيري مسير حركت وسايل نقليه در صحنة ترافيك
محورهای موضوعی : مهندسی برق و کامپیوتر
هادی صدوقی یزدی
1
,
مجتبی لطفي‌زاد
2
,
محمود فتحی
3
,
احسان‌اله کبیر
4
1 - دانشگاه تربیت معلم سبزوار
2 - دانشگاه تربیت مدرس
3 - دانشگاه علم و صنعت ایران
4 - دانشگاه تربیت مدرس
کلید واژه: پايگاه دادة مكاني-زمانيپيش‌بين RLS ماتريس گذر مراكزردياب بالا به پايين,
چکیده مقاله :
در اين مقاله، يك الگوريتم جديد رديابي بالا به پايين بر اساس يادگيري مسير حركت وسايل نقليه ارائه مي‌شود. به اين منظور يك ماتريس گذر مراكز، CTM، كه يك پايگاه دادة مكاني-زماني جديد است، پيشنهاد مي‌شود. براي ايجاد اين ماتريس ابتدا با خوشه‌بندي فازي روي مسيرهاي حركت وسايل نقليه بدست آمده، مراكزي بدست مي‌آيد سپس ماتريس CTM روي اين مراكز تعريف مي‌شود. عنصر i, j ام اين ماتريس بيان كنندة آن است كه شيئي در دو فريم متوالي از مركز i به مركز j گذر كرده است كه تكميل درايه‌هاي اين ماتريس با رديابي چند شيئي وسايل نقليه به مرور انجام مي‌شود. ماتريس CTM در افزايش سرعت همگرايي پيش‌بين RLS و جستجوي بهتر موقعيت وسيلة نقليه موثر است. الگوريتم رديابي پيشنهادي در مكانهاي مختلفي در صحنة ترافيك آزمون شد كه نتايج حاصله حاكي از افزايش كارايي در الگوريتم رديابي است.
In this paper, a trajectory learning-based vehicle tracking algorithm is presented which is a new top-down vehicle tracker. The history of trajectory is learnt by a novel sptio-temporal data base known center transition matrix, CTM. At first, the CTM is constructed on centers which are obtained using fuzzy clustering on vehicle trajectories. The i, j-th element of CTM indicates passing of the object from center i to center j in two consecutive frames which CTM is completed by multi-object tracking. The CTM is efficient in search of similar blobs in image sequences and can determine the radius and region of search and increasing of convergence rate of RLS predictor. The proposed tracking algorithm is tested in the intersection of a highway to a square which gives good results.
[1] M. Shah and R. Jain, Motion Based Recognition, Kluwer, 1997.
[2] S. Haykin, Adaptive Filter Theory, 3rd. ed., Printice Hall, 1996.
[3] S. Haykin, A. H. Sayed, J. Zeidler, P. Yee, and P. Wei, "Tracking of linear time-variant systems," in Proc. MILCOM, pp. 602-606, San Diego, Nov. 1995.
[4] L. Zhao and C. Thorpe, "Qualitative and quantitative car tracking from a range image sequence," in Proc. CVPR, Santa Barbara, CA, pp. 496-501, Jun. 1998.
[5] R. Karlsson, Simulation Based Methods for Target Tracking, Ph.D. Thesis, Department of Electrical Engineering, Linkopings University, Sweden, 2002.
[6] C. Kervrann and F. Heitz, "A Hierarchical markov modeling approach for the segmentation and tracking of deformable shapes," Graphical Models and Image Processing, vol. 60, no. 3,pp. 173-195, May. 1999.
[7] M. Isard and A. Blake, "A Mixed-State condensation tracker with automatic model switching," in 5th Proc. of Europian Conf. on Computer Vision, vol. 1, pp. 893-908, 1998.
[8] M. Isard and A. Blake, "CONDENSATION- conditional density propagation for visual tracking," Int. Journal Computer Vision, vol. 29, no. 1, pp. 5-28, Aug. 1998.
[9] M. Isard, A. Blake, and D. Raynard, "Learning to track curves in motion," IEEE Int. Conf. on Decision Theory and Control, pp. 3788- 3793, 1994.
[10] C. Wohlera and J. K. Anlaufb, "A time delay neural network algorithm for estimating image-pattern shape and motion," Image and Vision Computing, vol. 17, no. 3/4, pp. 281-294, Mar. 1999.
[11] H. Sadoghi Yazdi, M. Lotfizad, E. Kabir , and M. Fathy, "Application of trajectory learning in tracking vehicles in the traffic scene,"in Proc. 9th Iranian Computer Conf., vol. 1, pp. 180-187,Feb. 2004.
[12] D. Chetverikov and J. Verestoy, "Feature point tracking for incomplete trajectories," Computing, vol. 62, no. 4, pp. 321-338, Apr. 1999.
[13] B. Coifman, D. Beymer, P. McLaunhlan, and J. Malik, "A Real- Time computer system for vehicle tracking and traffic surveillance," Transportation Research, pt C, vol. 6, no. 4, pp. 271-288, Mar. 1998.
[14] U. Neumann and S. You, "Natural feature tracking for augmentedreality," IEEE Trans. on Multimedia, vol. 1, no. 1, pp. 53-64, Mar. 1999.
[15] J. Badenas, J. M. Sanchiz, and F. Pla, "Motion-based segmentation and region tracking in image sequence," Pattern Recognition, vol. 34, no. 8, pp. 661-670, Aug. 2001.
[16] D. Koller, K. Daniilidis, and H. -H. Nagel, "Model-based object tracking in monocular image sequences of road traffic scenes," Int. Journal of Computer Vision, vol. 10, no. 3, pp. 257-281, 1993.
[17] M. Haag and H. -H. Nagel, "Tracking of complex driving maneuvers in traffic image sequences," Image and Computing, vol. 16, no. 8, pp. 517-527, Jun. 1998.
[18 ] ها. صدوقي يزدي، م. فدوي، م. لطفي زاد و ا. كبير، "استخراج زمينة صحنه با فيلتر وفقي LMS با گام حركت فازي در رديابي هدف متحرك،" چهارمين كنفرانس سيستمهاي فازي ايران، صص.، 119-127، خرداد 1382.
[19 ] ها. صدوقي يزدي، م. لطفي زاد و م. فتحي، "تفسير كيفي رفتار جمعي وسايل نقليه در صحنة ترافيك با سيستم استنتاج فازي،" پنجمين كنفرانس سيستمهاي فازی ، صص. 194-199، شهریور 1383، ایران.
[20] H. Sadoghi Yazdi and M. Lotfizad, "A new approach for tracking objectives using combination of RLS and MAP algorithms," in Proc. 11th Iranian Electronic Eng. Conf., vol. 3, pp. 258-266, 2003.
[21] H. Sadoghi.Yazdi, M. Fathy, and M. Lotfizad, "Vehicle tracking at traffic scene with modified RLS," in Proc. Int. Conf. on Image Analysis and Recognition, LNCS.3212, pp. 623-632, Porto,Oct. 2004.
[22] H. Sadoghi.Yazdi, M. Lotfizad, E. Kabir, and M. Fathy, "Clipped input data RLS, CRLS, applied to vehicle tracking," EURASIP Journal on Applied Signal Processing, vol. 2005, no. 8, pp. 1221-1228, 21 May 2005
[23] M. Osadchy and D. Keren, "A Rejection-Based method for event detection in video," IEEE Trans. on Circuits and Systems for Video Technology, vol. 14, no. 4, pp. 534-541, Apr. 2004.
[24] N. Li, S. Dettmer, and M. Shah, "visually recognizing speech using eigensequences, in Motion-Based Recognition., Kluwer, pp. 345- 371, Boston, MA, 1997.
[25] R. V. Babua and K. R. Ramakrishnanb, "Recognition of human actions using motion history information extracted from the compressed video," Image and Vision Computing, vol. 22, no. 8,pp. 597-607, Aug. 2004.
[26] N. Sumpter and A. Bulpitta, "Learning spatio-temporal patterns for predicting object behavior," Image and Vision Computing, vol. 18, no. 9, pp. 697-704, Sep. 2000.
[27] Y. K. Jung,K. W. Lee, and Y. S. Ho, "Content-Based event retrieval using semantic scene interpretation for automated traffic surveillance," IEEE Trans. Intelligent on Transportation System,vol. 2, no. 3, pp. 151-163, Sep. 2001.
[28] S -C. Chen, M -L. Shyu, S. Peeta, and C. Zhang, "Learning-Based spatio-temporal vehicle tracking and indexing for transportation multimedia database systems," IEEE Trans. on Intelligent Transportation Systems, vol. 4, no. 3, pp. 154-167, Sep. 2003.
[29] H. J. Zimmerman, Fuzzy Set Theory and its Application, 3rd. ed. ,Kluwer Academic Publishers, 1998.
[30] S. Gil, R. Milanese, and T. Pun, "Comparing features for target tracking in traffic scenes", Pattern Recognition, vol. 29, no. 8, pp. 1285-1296, Aug. 1996.
