تشخيص تغييرات صحنه به روش زمينه گيري هوشمند
محورهای موضوعی : مهندسی برق و کامپیوتر
محمود فتحی
1
(دانشگاه علم و صنعت ایران)
حسن شكوري
2
(جهاد دانشگاهي صنعتي شريف)
کلید واژه: بلوك بندي تصاويرتركيبي از گوسين‌هاتفاضل زمينهجداسازي رو زمينه,
چکیده مقاله :
جداسازي روزمينه از زمينه، در بسياري از كاربردهاي نظارت تصويري به عنوان اولين و مهمترين قدم شناخته ميشود و "تفاضل زمينه" روشي است كه معمولاً براي اين منظور استفاده ميشود. اين روش، هر فريم را با مدلي از صحنة خالي مقايسه كرده و ناحيههايي از آنرا كه بطور قابل ملاحظهاي متفاوت به نظر ميرسند به عنوان نواحي روزمينه مشخص ميكند. اين مقاله روش جديدي براي تفاضل زمينه ارائه ميكند كه در آن ابتدا هر تصوير به بلوكهاي يكساني تفكيك شده و سپس ويژگيهاي تعيينكنندهاي از بلوكها محاسبه شده و سابقة مقادير هر يك از اين ويژگيها، به صورت تركيبي از توزيعهاي گوسين مدل ميگردد. با ورود هر فريم جديد، اين توزيعها با روش سريعي بهنگام ميشوند آنگاه توزيعهاي گوسين مدلهاي تركيبي، براي يافتن توزيعهايي كه بيانكنندة زمينه هستند ارزيابي ميشوند و هر بلوك بر اساس اينكه مقادير ويژگيهاي آن جزو كداميك از توزيعها باشد در دو كلاس زمينه و روزمينه دستهبندي ميشود. پيادهسازي نرمافزاري اين روش روي كامپيوتر شخصي، حاكي از عملكرد قابل قبول سيستم در برابر اجسام متجاوز به صحنه (مستقل از سرعت حركت آنها)، اضافه يا كاسته شدن اجسام داخل صحنه، نويز تصويربرداري و تغييرات ناخواستة صحنه است و سرعت بالا و نياز به حافظة كم، آنرا براي درصد بالايي از كاربردهاي بلادرنگ مناسب ميسازد.
The segmentation of foreground regions in image sequences is the first and the most important stage in many automated visual surveillance applications; and background subtraction is a method typically used for such applications. In this method, each new frame is compared with a model of the empty scene (which we call it ‘Background’), then those regions in the image that differ significantly from the background are identified as foreground. This paper presents a new background subtraction approach. In this method, each image is divided into similar NN blocks; then, some features are extracted from every block and the history of each feature are modeled as a combination of gaussian distributions. These distributions are updated after reception of every frame information. Then the gaussian distributions of the adaptive mixture models are evaluated to determine which one most likely describes the background and each block is classified as background or foreground based on the gaussians distributions which represents its feature value most effectively. The software implementations on personal computers show accepting capability of this approach for handling intruders to the scene, objects being introduced or removed from the scene, noises and unwanted changes in the background. Also, high speed of execution and reduced memory requirements makes this approach as a suitable method for high percentage of real-time applications
[1] E. Durucan, J. Snoeckx, and Y. Weilenmann, "Illumination invariant background extraction," in Proc. 10th Int. Conference on Image Analysis and Processing (ICIAP '99), pp. 1136-1139, 1999.
[2] A. Iketani, Y. Kuno, N. Shimada, and Y. Shirai, "Real-time surveillance system detecting persons in complex scenes", in Proc. IAPR Int. Conf. on Image Analysis and Processing, pp. 1112-1115, 1999.
[3] حسن شكوري، برآورد بلادرنگ حركت، سمينار كارشناسي ارشد، دانشكدة . مهندسي كامپيوتر، دانشگاه علم و صنعت ايران، 1378.
[4] P. A. Laplant and D. Stoyenko, Real-time Imaging: Theory, Techniques and Applications, IEEE PRESS, New York, 1996.
[5] L. J. Leroux and J. J. D. Van Schalkwyk, "An overview of moving object segmentation in video images," in Proc. South African Symposium on Communication and Signal Processing, pp. 53-57, Aug. 30, 1991.
[6] R. Cucchiara, P. Onfiani, A. Prati, and N. Scarabottolo, "Segmentation of moving objects at frame rate: a dedicated hardware solution," in Proc. of 7th IEE Conf. on Image Processing and Its Applications (IPA 99), Manchester UK, 12-15 Jul. 1999.
[7] A. T. Ali and E. L. Dagless, "Alternative practical methods for moving object detection," in Proc. 4th Int. Conf. on Image Processing and Its Applications, Publication no. 354, Maastricht, 1992.
[8] A. T. Ali and E. L. Dagless, "Computer vision for security surveillance and movement control," Electronic Images and Image Processing in Security and Forensic Science, IEE Colloquium on, pp. 6/1-6/7, 1990.
[9] P. Voles, M. Teal, and J. Sanderson, "Target identification in complex maritime scene," IEE Colloquium on Motion Analysis and Tracking, London, UK, pp. 15/1-15/4, May 10, 1999.
[10] A. Utsumi and J. Ohya, "Image segmentation for human tracking using sequential-image-based hierarchical adaptation," in Proc. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, pp. 911-916, 1998.
[11] W. E. L. Grimson and C. Stauffer, "Adaptive background mixture models for real-time tracking," in CVPR, 1999.
[12] K. Toyama, J. Krumm, B. Brumitt, and B. Meyers, "Wallflower: principles and practice of background maintenance," in Proc. Seventh Int. Conf. on Computer Vision, pp. 255-261, Sep. 1999.
[13] N. Friedman and S. Russel, "Image segmentation in video sequences: a probabilistic approach," in Proc. 13th Conf. on Uncertainty in Artificial Intelligence (UAI), pp. 175-181, Aug. 1997
[14] S. Arseneau and J. R. Cooperstock, "Real-time image segmentation for action recognition", in Proc. IEEE PACRIM, Pacific Rim Conf. on Communications, Computers, Visualization and Signal Processing, pp. 86-89,Victoria, Aug. 1999.
[15] M. Tsuchikawa, A. Sato, H. Koike, and A. Tomono, "A moving object extraction method robust against illumination level changes for a pedestrian counting system," in Proc. ISCV 95, pp. 563-568, 1995.
[16] G. L. Foresti, "Object recognition and tracking for remote video surveillance," IEEE Trans. on Circuits and Systems for Video Technology, vol. 9, no. 7, pp. 10/45-10/62, Oct. 1999.
[17] G. L. Foresti, "A real-time system for video surveillance of unattended outdoor environments," IEEE Trans. on Circuits and Systems for Video Technology, vol. 8, no. 6, pp. 697-704, Oct. 1998.
[18] S. McKenna, S. Jabri, Z. Duric, and H. Wechsler, "Tracking interacting people," IEEE Int. Conf. on. Automatic Face and Gesture Recognition, pp. 348-353, Grenobe, France, Mar. 2000.
[19] C. Ridder, O. Munakelt, and H. Kirchner, "Adaptive background estimation and foreground detection using kalman-filtering," in Proc. of Int. Conf. on Recent Advances in Mechatronics, ICRAM’95, UNESCO Chair in Mechatronics, pp. 193-199, 1995.
[20] W. Christopher R., A. Azarbayejani, T. Darrell, and A. Pentland, "Pfinder: real-time tracking of the human body," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 19, no. 7, pp. 780-785, Jul. 1997.
[21] D. Koller, J. Weber, T. Huang, J. Malik, G. Ogasawara, B. Rao, andS. Russel, "Toward robust automatic traffic scene analysis in real-time," in Proc. Int. Conf. on Pattern Recognition, pp. 126-131, Jerusalem, Oct. 1994.
[22] W. E. L. Grimson, C. Stauffer, and R. Romano, "Using adaptive tracking to classify and monitor activities in a site," in Proc IEEE Computer Vision and Pattern Recognition (CVPR), pp. 22-29, 1998.
[23] A. Makarov, "Comparison of background extraction based intrusion detection algorithm," in Proc. Int. Conf. Image Processing, pp. 521- 524, 1996.
[24] A. K. Bekhalil, S. S. Ipson, and W. Booth, "Real-time detection and tracking of a moving object using a complex programmable logic device," IEE colloquium on Target Tracking and Data Fusion, Austin Court, Birmingham, pp.10/1-10/7, Jun. 1998.
[25] A. R. Rostampour, O. R. Mitchell, and A. P. Reeves, "The use of temporal variance for moving object extraction," in Proc. Seventh Annual Phoenix Conf. on Computers and Communications, Mar.1988.
[26] K. W. Lee and J. Kim, "Moving object segmentation based on statistical motion model," IEE Electronics Letters, vol. 35, no. 20, pp. 1719-1720, Sep. 1999.
[27] I. Haritaoglu, D. Harwood, and L. Davis, "W4: Who, when, where, what: a real time system for detecting and tracking people," Third Int. Conf. on Automatic Face and Gesture, Nara, Japan, Apr. 1998.
[28] Y. K. Jung and Y. S. Ho, "Traffic parameter extraction using videobased vehicle tracking," ITSC'99 Conference Program (tentative), Oct. 5, 1999.
[29 ] م. فتحي، م. عنايتي نيا، غ. ر. رمضان، ش. كبيري و ا. ر. خوانساري، "سيستم كنترل و نظارت خودكار تصويري،" آزمايشگاه پردازش سريع دانشكدة كامپيوتر دانشگاه علم و صنعت ايران، 1378.
[30] Y. Ivanov, A. Bobick, and J. Liu, "Fast lighting independent background subtraction," in Proc. IEEE Workshop on Visual Surveillance (VS'98), pp. 49-55, Bombay, India, IEEE, New York 1998.
[31] A. Elgammal, D. Harwood, and L. Davis, "Non-parametric model for background subtraction," 6th European Conf. on Computer Vision, Dublin, Ireland, Jun./Jul. 2000.
[32] Y. Yang and M. D. Levise, "The background primal sketch: an approach for tracking moving objects," Machine Vision and Application, vol. 5, no. 1, pp.17-34, 1992.
[33] D. Hepper and H. Li, "Analysis of uncovered background prediction for image sequence coding," in Proc. Picture Coding Symposium, pp. 192-193, 1987.
[34] K. P. Karmann and A.V. Brandt, "Moving object recognition using an adaptive background memory," Time-Varying Image Processing and Moving Object Recognition, V. Cappellini (ed.), pp. 289-296, Elsevier, Amsterdam, The Netherlands, 1990.