Abstract
In this chapter, an active stereo vision system composed of two pan-tilt-zoom (PTZ) cameras is proposed for estimating multiresolution depth map for a large and complex scene. The rectification of stereo images is performed based on the sigmoid interpolation with a set of neural networks. The orientation parameters (pan and tilt values) and the rectification transformations of corresponding images are used as the input-output pairs for network training. The input data is read from cameras directly, whereas the output data is computed offline. The trained neural network is used to interpolate rectification transformations in real time for the stereo images captured at arbitrary pan and tilt settings. The correspondence between the stereo images is obtained using a chain of homographies based scheme. Non-homogeneity between the intrinsic parameters of two cameras is treated by means of zoom compensation to improve the quality of stereo rectification. Experimental results are given for estimating multiresolution depth map for a scene.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abidi, B., Koschan, A., Kang, S., Mitckes, M., Abidi, M.: Automatic target acquisition and tracking with cooperative static and PTZ video cameras. In: Multisensors Surveillance Systems: The Fusion Perspective, pp. 43–59. Kluwer Academic, Dordrecht (2003)
Brown, M., Burschka, D., Hager, G.: Advances in computational stereo. IEEE Trans. Pattern Anal. Mach. Intell. 25(8), 993–1008 (2003)
Chen, C.H., Yao, Y., Page, D., Abidi, B., Koschan, A., Abidi, M.: Heterogeneous fusion of omnidirectional and PTZ cameras for multiple object tracking. IEEE Trans. Circuits Syst. Video Technol. 18(8), 1052–1063 (2008)
Foresti, G., Micheloni, C., Piciarelli, C.: Detecting moving people in video streams. Pattern Recognit. Lett. 26, 2232–2243 (2005)
Fusiello, A., Israra, L.: Quasi epipolar unclaibrated rectification. In: IEEE Int. Conf. on Image Processing (ICPR), pp. 1–4 (2008)
Gallup, D., Frahm, J., Mordobhai, P., Pollefeys, M.: Variable baseline/resolution stereo. In: IEEE Int Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 1–8 (2008)
Haritaoglu, S., Harwood, D., Davis, L.: Real-time surveillance of people and their activities. IEEE Trans. Pattern Anal. Mach. Intell. 22(8), 809–830 (2000)
Hart, J., Scassellati, B., Zucker, S.: Epipolar geometry for humanoid robotic heads. In: International Cognitive Vision Workshop, pp. 24–36 (2008)
Jain, A., Kopell, D., Kakligian, K., Wang, Y.: Using stationary-dynamic camera assemblies for wide-area video surveillance and selective attention. In: IEEE Int. Conf. of Computer Vision and Pattern Recogination (CVPR), pp. 537–544 (2006)
Kannala, J.T., Salo, M., Heikkila, J.: Algorithms for computing a planar homography from conics in correspondence. In: Proceedings of the British Machine Vision Conference (BMVC 2006), pp. 9.1–9.10 (2006)
Kumar, S., Micheloni, C., Piciarelli, C.: Stereo localization using dual PTZ cameras. In: Computer Analysis of Images and Patterns. LNCS, pp. 1061–1069. Springer, Berlin (2009)
Kumar, S., Micheloni, C., Piciarelli, C., Foresti, G.: Stereo localization based on network’s uncalibrated camera pairs. In: Sixth IEEE International Conference on Advanced Video and Signal Based Surveillance, pp. 502–507 (2009)
Kumar, S., Micheloni, C., Piciarelli, C., Forestia, G.: Stereo rectification of uncalibrated and heterogeneous images. Pattern Recognit. Lett. 31, 1445–1452 (2010)
Lowe, D.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 2(60), 91–160 (2004)
Meltzer, J., Soatto, S.: Edge descriptors for robust wide-baseline correspondence. In: IEEE Int. Conf. on Computer Vision and Pattern Recogination, pp. 1–8 (2008)
Micheloni, C., Foresti, G., Snidaro, L.: A network of co-operative cameras for visual surveillance. IEE Proc., Vis. Image Signal Process. 152(2), 205–212 (2005)
Micheloni, C., Lestuzzi, M., Foresti, G.: Adaptive video communication for an intelligent distributed system: tuning sensors parameters for surveillance purposes. Mach. Vis. Appl. 19(5–6), 1432–1769 (2008)
Morris, B., Trivedi, M.: A survey of vision-based trajectory learning and analysis for surveillance. IEEE Trans. Circuits Syst. Video Technol. 18(8), 1114–1127 (2008)
Piciarelli, C., Foresti, G.: On-line trajectory clustering for anomalous events detection. Pattern Recognit. Lett. 27, 1835–1842 (2006)
Piciarelli, C., Micheloni, C., Foresti, G.: Trajectory-based anomalous event detection. IEEE Trans. Circuits Syst. Video Technol. 18(11), 1544–1554 (2008)
Qureshi, F., Terzopoulos, D.: Planning ahead for PTZ camera assignment and handoff. In: Third ACM/IEEE International Conf. on Distributed Smart Cameras (ICDSC’09), Como, Italy (2009)
Trajkovic, M.: Interactive calibration of a PTZ camera for surveillance applications. In: Asian Conference on Computer Vision (ACCV) (2002)
Wan, D., Zhaou, J.: Stereo vision using two PTZ cameras. Comput. Vis. Image Underst. 112(2), 184–194 (2008)
Wan, D., Zhou, J.: Multiresolution and wide-scope depth estimation using a dual-PTZ-camera system. IEEE Trans. Image Process. 18(3), 677–682 (2009)
Yang, J., Arifb, O., Velab, P., Teizerc, J., Shia, Z.: Tracking multiple workers on construction sites using video cameras. Adv. Eng. Inform. 24, 428–434 (2010)
Zhu, Z., Hanson, A.R.: Mosaic-based 3D scene representation and rendering. Signal Process. Image Commun. 21(9), 739–754 (2006)
Acknowledgements
One of the authors, Sanjeev Kumar is thankful to IIT Roorkee for providing partially financial support through grant number FIG-100550 under New Faculty Initiation Grant Scheme-A to carry out this research work. The authors are also thankful to the AVIRES Lab, University of Udine, Italy for providing access to their image grabbing system.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Kumar, S., Micheloni, C., Raman, B. (2013). Multiresolution Depth Map Estimation in PTZ Camera Network. In: Atrey, P., Kankanhalli, M., Cavallaro, A. (eds) Intelligent Multimedia Surveillance. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-41512-8_8
Download citation
DOI: https://doi.org/10.1007/978-3-642-41512-8_8
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-41511-1
Online ISBN: 978-3-642-41512-8
eBook Packages: Computer ScienceComputer Science (R0)