Abstract
Computer vision is a great interest field offering relevant information in a wide variety of areas. Different video processing techniques, for instance, allow us to detect moving objects from image sequences of fixed surveillance cameras. Lateral Interaction in Accumulative Computation is a classical bio-inspired method that is usually applied for detecting moving objects in video processing. This method achieves high precision but also requires a high processing time. This paper introduces a parallel code capable of keeping a high performance in terms of accuracy and runtime for the method. For some of the image sequences tested, a speed-up of \(67\times \) over the sequential counterpart is achieved.
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 subscriptionsNotes
- 1.
Note that these numbers have been selected so that all blocks have the same number of threads, i.e. the number of pixels in the images is multiple of these numbers.
References
Ullman, S., Assif, L., Fetaya, E., Harari, D.: Atoms of recognition in human and computer vision. PNAS 113(10), 2744–2749 (2016)
Kriegeskorte, N.: Deep neural networks: a new framework for modeling biological vision and brain information processing. Ann. Rev. Vis. Sci. 1, 417–446 (2015)
Cox, D.D., Dean, T.: Neural networks and neuroscience-inspired computer vision. Curr. Biol. 24(18), R921–R929 (2014)
Medathati, N.V.K., Neumann, H., Masson, G.S., Kornprobst, P.: Bio-inspired computer vision: towards a synergistic approach of artificial and biological vision. Comput. Vis. Image Underst. 150, 1–30 (2016)
Fernández-Caballero, A., Mira, J., Fernández, M.A., Delgado, A.E.: On motion detection through a multi-layer neural network architecture. Neural Netw. 16(2), 205–222 (2003)
Fernández-Caballero, A., Mira, J., Delgado, A.E., Fernández, M.A.: Lateral interaction in accumulative computation: a model for motion detection. Neurocomputing 50, 341–364 (2003)
Fernández-Caballero, A., López, M.T., Carmona, E.J., Delgado, A.E.: A historical perspective of algorithmic lateral inhibition and accumulative computation in computer vision. Neurocomputing 74(8), 1175–1181 (2011)
Delgado, A.E., López, M.T., Fernández-Caballero, A.: Real-time motion detection by lateral inhibition in accumulative computation. Eng. Appl. Artif. Intell. 23(1), 129–139 (2010)
Fernández-Caballero, A., López, M.T., Castillo, J.C., Maldonado, S.: Real-time accumulative computation motion detectors. Sensors 9(12), 10044–10065 (2009)
Kirk, D., Hwu, W.-M.: Programming Massively Parallel Processors, 2nd edn. Morgan Kaufmann, Burlington (2012)
NVIDIA Corporation. CUDA C Best Practices Guide, v8.0, ed. (2017)
Fernández-Caballero, A., Fernández, M.A., Mira, J., Delgado, A.E.: Spatio-temporal shape building from image sequences using lateral interaction in accumulative computation. Pattern Recognit. 36(5), 1131–1142 (2003)
Acknowledgements
This work was partially supported by Spanish Ministerio de Economía, Industria y Competitividad, Agencia Estatal de Investigación (AEI)/European Regional Development Fund under DPI2016-80894-R grant.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Sánchez, J.L., Viana, R., López, M.T., Fernández-Caballero, A. (2017). Acceleration of Moving Object Detection in Bio-Inspired Computer Vision. In: Ferrández Vicente, J., Álvarez-Sánchez, J., de la Paz López, F., Toledo Moreo, J., Adeli, H. (eds) Biomedical Applications Based on Natural and Artificial Computing. IWINAC 2017. Lecture Notes in Computer Science(), vol 10338. Springer, Cham. https://doi.org/10.1007/978-3-319-59773-7_37
Download citation
DOI: https://doi.org/10.1007/978-3-319-59773-7_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-59772-0
Online ISBN: 978-3-319-59773-7
eBook Packages: Computer ScienceComputer Science (R0)