CAIP 2009: Computer Analysis of Images and Patterns pp 1061-1069 | Cite as
Stereo Localization Using Dual PTZ Cameras
Abstract
In this paper, we present a cooperative stereo system based on two pant-tilt-zoom (PTZ) cameras that can localize a moving target in a complex environment. Given an approximate target position that can be estimated by a fixed camera with a wide field of view, two PTZ cameras with a large baseline are pointed toward the target in order to estimate precisely its position. The overall method is divided in three parts: offline construction of a look-up-table (LUT) of rectification matrices, use of the LUT in real time for computing the rectification transformations for arbitrary camera positions, and finally 3D target localization. A chain of homographic transformations are used for finding the matching between different pairs of wide baseline stereo images. The proposed stereo localization system has two advantages: improved localization on a partially occluded target and monitoring a large environment using only two PTZ cameras without missing significant information. Finally, through experimental results, we show that the proposed system is able to make required localization of targets with good accuracy.
Keywords
Stereo Image Stereo Vision Stereo Match Zoom Level Monocular CameraPreview
Unable to display preview. Download preview PDF.
References
- 1.Abidi, B., Koschan, A., Kang, S., Mitckes, M., Abidi, M.: Automatic target Acquisition and Tracking with Cooperative Static and PTZ Video Cameras. Multisensors Surveillance Systems: The Fusion Perspective, 43–59 (2003)Google Scholar
- 2.Haritaoglu, S., Harwood, D., Davis, L.: W 4: Real-Time Surveillance of People and their Activities. IEEE Transactions on Pattern Analysis and Machine Intelligence 22(8), 809–830 (2000)CrossRefGoogle Scholar
- 3.Jain, A., Kopell, D., Kakligian, K., Wang, Y.F.: Using Stationary-Dynamic Camera Assemblies for Wide-area Video Surveillance and Selective Attention. In: Proc. of IEEE Int. Conf. of Computer Vision and Pattern Recogination, vol. 1, pp. 537–544 (2006)Google Scholar
- 4.Micheloni, C., Foresti, G.L., Snidaro, L.: A network of Co-operative Cameras for Visual Surveillance. IEE-proc. Vis. Image Signal Process. 152(2), 205–212 (2005)CrossRefGoogle Scholar
- 5.Brown, M., Burschka, D., Hager, G.D.: Advances in Computational Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence 25(8), 993–1008 (2003)CrossRefGoogle Scholar
- 6.Wan, D., Zhaou, J.: Stereo Vision Using Two PTZ Cameras. Computer Vision and Image Understanding 112(2), 184–194 (2008)CrossRefGoogle Scholar
- 7.Hart, J., Scassellati, B., Zucker, S.W.: Epipolar Geometry for Humanoid Robotic Heads. In: Proc. of 4th International Cognitive Vision Workshop, pp. 24–36 (2008)Google Scholar
- 8.Isgro, F., Trucco, E.: On Robust Rectification of Uncalibrated Images. In: Proc. of 10th International Conference on Image Analysis and Processing, pp. 297–302 (1999)Google Scholar
- 9.Lowe, D.G.: Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision 2(60), 91–160 (2004)CrossRefGoogle Scholar
- 10.Meltzer, J., Soatto, S.: Edge descriptors for robust wide-baseline correspondence. In: Proc. of IEEE Int. Conf. on Computer Vision and Pattern Recogination, pp. 1–8 (2008)Google Scholar
- 11.Kumar, S., Micheloni, C., Foresti, G.L.: Stereo Vision in Cooperative Camera Networks, Smart Cameras. Springer Science+Business Media, Inc., Heidelberg (in press, 2009)Google Scholar