Abstract
Biologically-inspired computer vision is a research area that offers prominent directions in a large variety of fields. Several processing algorithms inspired in natural vision enable detecting moving objects from video sequences so far. One example is lateral interaction in accumulative computation (LIAC), a classical bioinspired method that has been applied to numerous environments and applications. LIAC is the implementation for computer vision of two biologically-inspired methods denominated algorithmic lateral interaction and accumulative computation. The method has traditionally reached high precision but unfortunately requires high computing times. This paper introduces a proposal based on graphics processing units in order to speed up the original sequential code. This way not only excellent performance in terms of accuracy is maintained, but also real-time is obtained. A speed-up of 67× from the parallel over its sequential counterpart is achieved for several tested video sequences.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Bayerl P, Neumann H (2004) Disambiguating visual motion through contextual feedback modulation. Neural Comput 16(10):2041–2066. https://doi.org/10.1162/0899766041732404
Bouecke J, Tlapale E, Kornprobst P, Neumann H (2011) Neural mechanisms of motion detection, integration, and segregation: from biology to artificial image processing systems. EURASIP J Adv Signal Process 2011:781561. https://doi.org/10.1155/2011/781561
Chakraborty DB, Pal SK (2016) Neighborhood granules and rough rule-base in tracking. Nat Comput 15:359–370. https://doi.org/10.1007/s11047-015-9493-6
Clifford CWG, Ibbotson MR (2003) Fundamental mechanisms of visual motion detection: models, cells and functions. Prog Neurobiol 68:409–437. https://doi.org/10.1016/S0301-0082(02)00154-5
Cox DD, Dean T (2014) Neural networks and neuroscience-inspired computer vision. Curr Biol 24(18):R921–R929. https://doi.org/10.1016/j.cub.2014.08.026
Delgado AE, Mira J, Moreno-Díaz R (1989) A neurocybernetic model of modal co-operative decision in the Kilmer–McCulloch space. Kybernetes 18(3):48–57
Delgado AE, López MT, Fernández-Caballero A (2010) Real-time motion detection by lateral inhibition in accumulative computation. Eng Appl Artif Intell 23(1):129–139. https://doi.org/10.1016/j.engappai.2009.08.006
Fernández MA, Mira J, López MT, Álvarez JR, Manjarrés A, Barro S (1995) Local accumulation of persistent activity at synaptic level: application to motion analysis. Lect Notes Comput Sci 930:137–143
Fernández-Caballero A, Fernández MA, Mira J, Delgado AE (2003a) Spatio-temporal shape building from image sequences using lateral interaction in accumulative computation. Pattern Recognit 36(5):1131–1142. https://doi.org/10.1016/S0031-3203(02)00116-4
Fernández-Caballero A, Mira J, Delgado AE, Fernández MA (2003b) Lateral interaction in accumulative computation: a model for motion detection. Neurocomputing 50:341–364. https://doi.org/10.1016/S0925-2312(02)00571-4
Fernández-Caballero A, Mira J, Fernández MA, Delgado AE (2003c) On motion detection through a multi-layer neural network architecture. Neural Netw 16(2):205–222. https://doi.org/10.1016/S0893-6080(02)00233-2
Fernández-Caballero A, López MT, Castillo JC, Maldonado S (2009) Real-time accumulative computation motion detectors. Sensors 9(12):10044–10065. https://doi.org/10.3390/s91210044
Fernández-Caballero A, López MT, Carmona EJ, Delgado AE (2011) A historical perspective of algorithmic lateral inhibition and accumulative computation in computer vision. Neurocomputing 74(8):1175–1181. https://doi.org/10.1016/j.neucom.2010.07.028
Formosa-Jordan P, Ibañes M, Ares S, Frade J-M (2013) Lateral inhibition and neurogenesis: novel aspects in motion. Int J Dev Biol 57:341–350. https://doi.org/10.1387/ijdb.120259jf
Francis G (1996) Cortical dynamics of lateral inhibition: visual persistence and ISI. Percept Psychophys 58(7):1103–1109. https://doi.org/10.3758/BF03206836
Kar AK (2016) Bio inspired computing—a review of algorithms and scope of applications. Exp Syst Appl 59:20–32. https://doi.org/10.1016/j.eswa.2016.04.018
Kirk D, Hwu W-M (2012) Programming massively parallel processors, 2nd edn. Morgan Kaufmann, Burlington
Kriegeskorte N (2015) Deep neural networks: a new framework for modeling biological vision and brain information processing. Annu Rev Vis Sci 1:417–446. https://doi.org/10.1146/annurev-vision-082114-035447
Marcus CM, Waugh FR, Westervelt RM (1991) Connection topology and dynamics in lateral inhibition networks. In: Moody JE, Hanson SJ, Lippmann RP (eds) Advances in neural information processing systems. Neural Information Processing Systems Foundation, Inc., La Jolla, pp 98–104
Martínez-del-Amor MA, Macías-Ramos LF, Valencia-Cabrera L, Pérez-Jiménez MJ (2016) Parallel simulation of population dynamics P systems: updates and roadmap. Nat Comput 15:565–573. https://doi.org/10.1007/s11047-016-9566-1
Medathati NVK, Neumann H, Masson GS, Kornprobst P (2016) Bio-inspired computer vision: towards a synergistic approach of artificial and biological vision. Comput Vis Image Underst 150:1–30. https://doi.org/10.1016/j.cviu.2016.04.009
Millo J-V, de Simone R (2013) Explicit routing schemes for implementation of cellular automata on processor arrays. Nat Comput 12:353–368. https://doi.org/10.1007/s11047-013-9378-5
Mira J, Delgado AE (2001) What can we compute with lateral inhibition circuits? Lect Notes Comput Sci 2084:38–46
Mira J, Fernández MA, López MT, Delgado AE, Fernández-Caballero A (2003) A model of neural inspiration for local accumulative computation. Lect Notes Comput Sci 2809:427–435
NVIDIA Corporation (2017) CUDA C Best Practices Guide. http://docs.nvidia.com/cuda/cuda-c-best-practices-guide/index.html. Accessed 2 April 2018
O’Carroll DC, Wiederman SD (2017) Contrast sensitivity and the detection of moving patterns and features. Philos Trans R Soc Lond B Biol Sci 369(1636):20130043. https://doi.org/10.1098/rstb.2013.0043
Skowron A, Jankowski A (2016) Interactive computations: toward risk management in interactive intelligent systems. Nat Comput 15:465–476. https://doi.org/10.1007/s11047-015-9486-5
Ullman S, Assif L, Fetaya E, Harari D (2016) Atoms of recognition in human and computer vision. Proc Natl Acad Sci USA 113(19):2744–2749. https://doi.org/10.1073/pnas.1513198113
Vadlamudi SG, Aine S, Chakrabarti PP (2016) Anytime pack search. Nat Comput 15:395–414. https://doi.org/10.1007/s11047-015-9490-9
Zhong X, Ma L (2013) A neuro-inspired adaptive motion detector. Opt Photonics J 3:94–98. https://doi.org/10.4236/opj.2013.32B024
Acknowledgements
This work was partially supported by Spanish Ministerio de Economía, Industria y Competitividad, Agencia Estatal de Investigación (AEI) / European Regional Development Fund (FEDER, UE) under DPI2016-80894-R and TIN2015-66972-C5-2-R grants.
Author information
Authors and Affiliations
Corresponding author
Additional information
Homage to the memory of Prof José Mira, our close master and friend, 10 years after his death.
Rights and permissions
About this article
Cite this article
Sánchez, J.L., López, M.T., Pastor, J.M. et al. Accelerating bioinspired lateral interaction in accumulative computation for real-time moving object detection with graphics processing units. Nat Comput 18, 217–227 (2019). https://doi.org/10.1007/s11047-018-9690-1
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11047-018-9690-1