Abstract
The analysis of moving objects in video sequences has been a paramount issue in applications related to intelligent surveillance systems, robotics, and medicine. Although several works aimed to analyze objects in video sequences have been reported, many of them need manual parameter adjustments and they are not tolerant to illumination changes and dynamic backgrounds. Therefore, a novel scheme termed Dynamic Retinotopic SOM based on an adaptive artificial neural network, to detect moving objects is proposed in this work. The neural network is a model based on the mechanisms of the visual cortex that we called Retinotopic SOM (RESOM) and it is also proposed in this paper. Furthermore, RESOM is a real-time neural network that can adapt its learning parameters based on the scene behavior and it mimics perception abilities. A quantitative comparison with other segmentation methods reported in the literature using real video scenes showed that the proposed DR-SOM segmentation method automatically adjusts its parameters and outperforms the reported methods in condition of dynamic backgrounds, and gradual and sudden illumination changes.
Similar content being viewed by others
References
Hao JY, Li C, Kim Z, Xiong Z (2013) Spatio-temporal traffic scene modeling for object motion detection. IEEE Trans Intell Transp Syst 14:295–302. doi:10.1109/TITS.2012.2212432
Chacon-Murguia MI, Gonzalez-Duarte S (2012) An adaptive neural-fuzzy approach for object detection in dynamic backgrounds for surveillance systems. IEEE Trans Ind Electron 59:3286–3298. doi:10.1109/TIE.2011.2106093
Dotu I, Patricio MA, Molina J (2011) Boosting video tracking performance by means of Tabu Search in intelligent visual surveillance systems. Springer J Heuristics 17(415):440. doi:10.1007/s10732-010-9140-4
Ravier D (2010) A service oriented framework architecture for intelligent video surveillance systems. In: Fifth international conference on digital telecommunications, pp 123–127. doi:10.1109/ICDT.2010.30
Ko T (2008) A survey on behavior analysis in video surveillance for homeland security applications. In: Workshop applied imagery pattern recognition, pp 1–8. doi:10.1109/AIPR.2008.4906450
Reddy V, Sanderson C, Lovell BC, Bigdeli A (2009) An efficient background estimation algorithm for embedded smart cameras. In:Third international conference on distributed smart cameras, pp 1–7. 10.1109/ICDSC.2009.5289348
Cottini N, Gottardi M, Massari N, Passerone R, Smilansky Z (2013) A 33 \(\mu \)W \(64\times 64\) pixel vision sensor embedding robust dynamic background subtraction for event detection and scene interpretation. IEEE J Solid-State Circuits 48:850–863. doi: 10.1109/JSSC.2012.2235031
Chellappa R, Cavallaro A, Wu Y, Shan C, Fu Y, Pulli K (2011) Special issue on video analysis on resource-limited systems. IEEE Trans Circuits Syst Video Technol 21:1349–1352. doi:10.1109/TCSVT.2010.2084830
Lin W-S, Liu A-T, Fang C-H (2005) Computational autonomous visual perception using cellular neural networks. In: IEEE international conference on computational intelligence for measurement systems and applications, pp 198–202. doi:10.1109/CIMSA.2005.1522860
Yu B, Zahng L (2004) Pulse-coupled neural networks for contour and motion matchings. IEEE Trans Neural Networks 15:1186–1201. doi:10.1109/TNN.2004.832830
Avila-Mora IM, Castellanos-Sanchez C (2009) Bio-inspired clustering of moving objects. Glob Congr Intell Syst 58–62. doi:10.1109/GCIS.2009.445
Baier V (2005) Motion perception with recurrent self-organizing maps based models. In: International joint conference on neural networks, pp 1182–1186. doi:10.1109/IJCNN.2005.1556021
Mario I, Chacon M, Sergio Gonzalez D, Javier Vega P (2009) Simplified SOM-neural model for video segmentation of moving object. In: International joint conference on neural networks, pp 474–480. doi:10.1109/IJCNN.2005.1556021
Ghasemi A, Safabakhsh R (2011) Unsupervised foreground–background segmentation using growing self organizing map in noisy backgrounds. In: International conference on computer research and development, pp 334–338. doi:10.1109/ICCRD.2011.5764031
Maddalena L, Petrosino A (2008) A self-organizing approach to background subtraction for visual surveillance applications. IEEE Trans Image Proces 17:1168–1177. doi:10.1109/TIP.2008.924285
Wang Z, Bao H (2011) Cooperative neural network background model for multi-modal video surveillance. In: Seventh international conference on computational intelligence and security, pp 249–254. doi:10.1109/CIS.2011.63
Culibrk D, Marques O, Socek D, Kalva H, Furht B (2007) Neural network approach to background modeling for video object segmentation. IEEE Trans Neural Networks 18:1614–1627. doi:10.1109/CIS.2011.63
Chacon-Murguia Mario I, Urias-Zavala JD (2012) A comparison between a DTCNN and SOM like approach for dynamic object detection in videos. North Am Fuzzy Inf Process Soc 1–6. doi:10.1109/NAFIPS.2012.6291048
Faro A, Giordano D, Spampinato C (2008) Evaluation of the traffic parameters in a metropolitan area by fusing visual perceptions and CNN processing of webcam images. IEEE Trans Neural Networks 19:1108–1129. doi:10.1109/TNN.2008.2000392
Misra J, Saha I (2010) Artificial neural networks in hardware: a survey of two decades of progress. Neurocomputing 74:239–255. doi:10.1016/j.bbr.2011.03.031
Cheng F-C, Huang S-C, Ruan S-J (2011) Scene analysis for object detection in advanced surveillance systems using Laplacian distribution model. IEEE Trans Syst Man Cybern-Part C: Appl Rev 41:589–598. doi:10.1109/TSMCC.2010.2092425
Cheng F-C, Huang S-C, Ruan S-J (2011) Illumination-sensitive background modeling approach for accurate moving object detection. IEEE Trans Broadcast 57:794–801. doi:10.1109/TBC.2011.2160106
Paruchuri JK, Sathiyamoorthy EP, Cheung SS, Chen C-H (2011) Spatially adaptive illumination modeling for background subtraction. In: IEEE international conference on computer vision, pp 1745–1752. doi:10.1109/ICCVW.2011.6130460
Intachak T, Kaewapichai W (2011) Real-time illumination feedback system for adaptive background subtraction working in traffic video monitoring. In: International symposium on intelligent signal processing and communications, pp 1–5. doi:10.1109/ISPACS.2011.6146103
Toyama K, Krumm J, Brumitt B, Meyers B (1999) Wallflower: principles and practice of background maintenance. In: International conference on computer vision, pp 255–261. doi:10.1109/ISPACS.2011.6146103
Brutzer S, Höferlin B, Heidemann G (2011) Evaluation of background subtraction techniques for video surveillance. In: Conference on computer vision and pattern recognition, pp 1937–1944. doi:10.1109/CVPR.2011.5995508
Miikkulainen R, Bednar JA, Choe Y, Sirosh J (2005) Computational maps in the visual cortex, Chap. 3 in Springer Sciences Media Inc.
Bednar J (2012) Building a mechanistic model of the development and function of the primary visual cortex. J Physiol 106:194–211
De Paula BJ (2007) Modeling the self-organization of color-selective neurons in the visual cortex, Technical Report AI-TR-07-347
Paplinski AP, Gustafsson L (2006) Feedback in multimodal self-organizing networks enhances perception of corrupted stimuli. Adv Artif Intell 4304:19–28. doi:10.1007/11941439_6
Luciw M, Weng J(J) (2012) Top-down connections in self-organizing Hebbian networks: topographic class grouping. IEEE Trans Auton Ment Dev 2:248–261. doi:10.1109/TAMD.2010.2072150
Li L, Huang W, Gu IY-H, Tian Q (2004) Statistical modeling of complex backgrounds for foreground object detection. IEEE Trans Image Process 13:1459–1472. doi:10.1109/TIP.2004.836169
Vacavant A, Chateau T, Wilhelm A, Lequièvre L (2013) A benchmark dataset for outdoor foreground/background extraction. Lecture notes on computer science, vol. 7728, pp 291–300. doi:10.1007/978-3-642-37410-4_25
Honovich J (2011) Average frame rate used for recording. http://ipvm.com/updates/1100
Vacavant A http://bmc.univ-bpclermont.fr/sites/default/files/results/Results-evaluation-real.png
Yoshinaga S, Shimada A, Nagahara H, Taniguchi R (2014) Object detection based on spatiotemporal background models. Comput Vision Image Underst 122:84–91
Acknowledgments
This work was supported by Fondo Mixto de Fomento a la Investigacion Cientifica y Tecnologica CONACYT- Gobierno del Estado de Chihuahua and DGEST under grants CHIH-2012-C03-193760 and CHI-IET-2012-105, and CHI-MCIET-2013-230.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Ramirez-Quintana, J.A., Chacon-Murguia, M.I. An Adaptive Unsupervised Neural Network Based on Perceptual Mechanism for Dynamic Object Detection in Videos with Real Scenarios. Neural Process Lett 42, 665–689 (2015). https://doi.org/10.1007/s11063-014-9380-7
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-014-9380-7