Abstract
Video processing algorithms present a necessary tool for various domains related to computer vision such as motion tracking, videos indexation and event detection. However, the new video standards, especially those in high definitions, cause that current implementations, even running on modern hardware, no longer respect the needs of real-time processing. Several solutions have been proposed to overcome this constraint, by exploiting graphic processing units (GPUs). Although, they present a high potential of GPU, any is able to treat high definition videos efficiently. In this work, we propose a development scheme enabling an efficient exploitation of GPUs, in order to achieve real-time processing of Full HD videos. Based on this scheme, we developed GPU implementations of several methods related to motion tracking such as silhouette extraction, corners detection and tracking using optical flow estimation. These implementations are exploited for improving performances of an application of real-time motion detection using mobile camera.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
AMD Fusion, Family of APUs. The Future brought to you by AMD introducing the AMD APU Family, http://sites.amd.com/us/fusion/au/Pages/fusion.aspx
Fonseca, A., Mayron, L., Socek, D., Marques, O.: Design and im-plementation of an optical flow-based autonomous video surveillance system. In: Proceedings of the IASTED, p. 209 (2008)
Mahmoudi, S.A., Sharif, H., Ihaddadene, N., Djerabe, C.: Abnormal event detection in real time video. In: 1st International Workshop on Multimodal Interactions Analysis of Users in a Controlled Environment, ICMI (2008)
NVIDIA, NVIDIA CUDA: Compute Unified Device Architecture (2007), http://www.nvidia.com/cuda
Khronos-Group, The Open Standard for Parallel Programming of Heterogeneous Systems (2009), http://www.khronos.org/opencl
Bimbo, A.D., Nezi, P., Sanz, J.L.C.: Optical flow computation using extended constraints. IEEE Transaction on Image Processing, 720 (1996)
Kitt, B., Ranft, B., Lategahn, H.: Block-matching based optical flow estimation with reduced search space based on geometric constraints. In: 13th International Conference on Intelligent Transportation Systems, p. 1140 (2010)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision (IJCV) 60(2), 91 (2004)
Marzat, J., Dumortier, Y., Ducrot, A.: Real-time dense and accurate parallel optical flow using CUDA. In: In Proceedings of WSCG, p. 105 (2009)
Mizukami, Y., Tadamura, K.: Optical Flow Computation on Compute Unified Device Architecture. In: ICIAP’14, p. 179 (2007)
Mizukami, Y., Tadamura, K.: Optical Flow Computation on Compute Unified Device Architecture. In: ICIAP’14, p. 179 (2007)
Sinha, S.N., Fram, J.-M., Pollefeys, M., Genc, Y.: Gpu-based video feature tracking and matching. In: Edge Computing Using New Commodity Architectures (2006)
Tomasi, C., Kanade, T.: Detection and tracking of point features. Technical Report CMU-CS-91-132, CMU, p. 1 (1991)
OpenGL, OpenGL Architecture Review Board: ARB vertex program, Revision 45 (2004), http://oss.sgi.com/projects/ogl-sample/registry/
Lecron, F., Mahmoudi, S.A., Benjelloun, M., Mahmoudi, S., Manneback, P.: Heterogeneous Computing for Vertebra Detection and Segmentation in X-Ray Images. International Journal of Biomedical Imaging (2011)
OpenCV, OpenCV computer vision library, http://www.opencv.org
Bouguet, J.Y.: Pyramidal Implementation of the Lucas Kanade Feature Tracker, Description of the algorithm. Intel Corporation Microprocessor Research (2000)
Mahmoudi, S.A., et al.: Traitements d’images sur architectures parallèles et hétérogènes. Technique et Science Informatiques 31, 1183 (2012)
Mahmoudi, S.A., Manneback, P., Augonnet, C., Thibault, S.: Détection optimale des coins et contours dans des bases d’images volumineuses sur architectures multicœurs hétérogènes. 20ème Rencontres Francophones du Parallélisme (2012)
Mahmoudi, S.A., Manneback, P.: Efficient Exploitation of Heterogeneous Platforms for Images Features Extraction. In: International Conference on Image Processing Theory, Tools and Applications, IPTA (2012)
Horn, B.K.P., Schunk, B.G.: Determining Optical Flow. Artificial Intelligence 2, 185 (1981)
Mahmoudi, S.A., Lecron, F., Manneback, P., Benjelloun, M., Mahmoudi, S.: GPU-Based Segmentation of Cervical Vertebra in X-Ray Images. In: IEEE International Conference on Cluster Computing, p. 1 (2010)
Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: Imaging Understanding Workshop, p. 121 (1981)
Harris, C.: A combined corner and edge detector. In: Alvey Vision Conference, p. 147 (1988)
Mahmoudi, S.A., Lecron, F., Manneback, P., Benjelloun, M., Mahmoudi, S.: Efficient Exploitation of Heterogeneous Platforms for Vertebra Detection in X-Ray Images. In: Biomedical Engineering International Conference, Biomeic 2012, Tlemcen, Algeria, p. 1 (2012)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 ICST Institute for Computer Science, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Mahmoudi, S.A., Kierzynka, M., Manneback, P. (2013). Real-Time GPU-Based Motion Detection and Tracking Using Full HD Videos. In: Mancas, M., d’ Alessandro, N., Siebert, X., Gosselin, B., Valderrama, C., Dutoit, T. (eds) Intelligent Technologies for Interactive Entertainment. INTETAIN 2013. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 124. Springer, Cham. https://doi.org/10.1007/978-3-319-03892-6_2
Download citation
DOI: https://doi.org/10.1007/978-3-319-03892-6_2
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-03891-9
Online ISBN: 978-3-319-03892-6
eBook Packages: Computer ScienceComputer Science (R0)