Abstract
Current computer vision algorithms can process video sequences and perform key low-level functions, such as motion detection, motion tracking, and object classification. This motivates activity detection (e.g. recognizing people’s behavior and intent), which is becoming increasingly important. However, they all have severe performance limitations when used over an extended range of applications. They suffer from high false detection rates and missing detection rates, or loss of track due to partial occlusions, etc. Also, activity detection is limited to 2D image domain and is confined to qualitative activities (such as a car entering a region of interest). Adding 3D information will increase the performance of all computer vision algorithms and the activity detection system. In this paper, we propose a unique approach which creates a 3D site model via sensor fusion of laser range finder and a single camera, which then can convert the symbolic features (pixel based) of each object to physical features (e.g. feet or yards). We present experimental results to demonstrate our 3D site model.
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
Preview
Unable to display preview. Download preview PDF.
References
Medioni, G., Cohen, I., Bremond, F., Hongeng, S., Nevatia, R.: Event Detection and Analysis from Video Streams. IEEE Trans. on Pattern Analysis and Machine Intelligence 23(8), 873–889 (2001)
Hongeng, S., Nevatia, R.: Multi-Agent Event Recognition. In: Proceedings of the 8th IEEE International Conference on Computer Vision, Vancouver, Canada (2001)
Zhang, Z.: A flexible new technique for camera calibration. IEEE Trans. on Pattern Analysis and Machine Intelligence 22(11), 1330–1334 (2000)
Heikkila, J., Silven, O.: A Four-Step Camera Calibration Procedure with Implicit Image Correction. In: IEEE Proc. Computer Vision and Pattern Recognition, pp. 1106–1112 (1997)
Faugeras, O.: Three-Dimensional Computer Vision. MIT Press, Cambridge (1993)
Martinec, D., Pajdla, T.: 3D Reconstruction by Fitting Low rank Matrices with Missing Data. In: IEEE Proc. Computer Vision and Pattern Recognition, pp. 198–205 (2005)
Sturm, P.: Multi-View Geometry for General Camera Models. In: IEEE Proc. Computer Vision and Pattern Recognition, 206–212 (2005)
Bradshaw, K., Reid, I., Murray, D.: The active recovery of 3d motion trajectories and their use in prediction. IEEE Trans. on Pattern Analysis and Machine Intelligence 19(3), 219–234 (1997)
Collins, R., Lipton, A., Kanade, T.: A system for Video Surveillance and Monitoring. In: 8th International Topical Meeting on Robotics and Remote System (April 1999)
Johnson, A.Y., Bobick, A.F.: A Multi-view Method for Gait Recognition Using Static Body Parameters. AVBPA, 301–311 (2001)
Porikli, F., Haga, T.: Event detection by Eigenvector Decomposition using object and feature frame. In: CVPR workshop (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ma, Y., Bazakos, M., Wang, Z., Au, W. (2005). 3D Scene Modeling for Activity Detection. In: Akoka, J., et al. Perspectives in Conceptual Modeling. ER 2005. Lecture Notes in Computer Science, vol 3770. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11568346_32
Download citation
DOI: https://doi.org/10.1007/11568346_32
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-29395-8
Online ISBN: 978-3-540-32239-9
eBook Packages: Computer ScienceComputer Science (R0)