Abstract
This work proposes a model of visual bottom-up attention for dynamic scene analysis. Our work adds motion saliency calculations to a neural network model with realistic temporal dynamics [(e.g., building motion salience on top of De Brecht and Saiki Neural Networks 19:1467–1474, (2006)]. The resulting network elicits strong transient responses to moving objects and reaches stability within a biologically plausible time interval. The responses are statistically different comparing between earlier and later motion neural activity; and between moving and non-moving objects. We demonstrate the network on a number of synthetic and real dynamical movie examples. We show that the model captures the motion saliency asymmetry phenomenon. In addition, the motion salience computation enables sudden-onset moving objects that are less salient in the static scene to rise above others. Finally, we include strong consideration for the neural latencies, the Lyapunov stability, and the neural properties being reproduced by the model.
Similar content being viewed by others
References
Abbott LF, Varela JA, Sen K, Nelson SB (1997) Synaptic depression and cortical gain control. Science 275:220–224
Bergen JR, Julesz B (1983) Parallel versus serial processing in rapid pattern discrimination. Nature 303:696–698
Bollman M, Hoischen R, Mertsching B (1997) In: Berlin et al. (ed) Integration of static and dynamic scene features guiding visual attention. Springer, Berlin, pp 483–490
Borst A (2000) Models of motion detection. Nature neuroscience 3:1168
Burt PJ (1988) Proceedings of the 9th international conference on attention mechanisms for vision in dynamic world. Patt Recog 1:977–987
Burt PJ, Adelson EH (1983) The Laplacian pyramid as a compact image code. IEEE Trans Commun 31:532–540
Cauller L (1995) Layer I of primary sensory neocortex: where top–down converges upon bottom-up. Behav Brain Res 71:163–170
Chen B (2005) Mathematical models of motion detection in the fly’s visual cortex. Dissertation, Texas Tech University, Texas
Chen LQ, Xie X, Fan X, Ma WY, Zhang HJ, Zhou HQ (2003) A visual attention model for adapting images on small displays. Multimed Syst 9:1–12
Coen-Cagli R, Dayan P, Schwartz O (2012) Cortical surround interactions and perceptual salience via natural scene statistics. PLoS Comput Biol 8(3):e1002405
Connor CE, Egeth HE, Yantis S (2004) Visual attention: bottom-up versus top–down. Curr Biol 14:R850–R852
Conway BR (2001) Spatial structure of cone inputs to color cells in alert macaque primary visual cortex (V-1). J Neurosci 21:2768–2783
Conway BR (2009) Color vision, cones and color-coding in the cortex. The Neuroscientist 15:274–290
De Brecht M, Saiki J (2006) A neural network implementation of a saliency map model. Neural Networks 19:1467–1474
Deco G, Rolls ET (2004) A neurodyamical cortical model of visual attention and invariant object recognition. Vis Res 44:621–642
Desimone R, Duncan J (1995) Neural mechanisms of selective visual attention. Ann Rev Neurosci 18:193–222
Desimone R, Ungerleider LG (1989) Neural mechanisms of visual processing in monkeys. Elsevier, New York, pp 267–299
EC Funded CAVIAR project/IST 2001 37540 http://homepages.inf.ed.ac.uk/rbf/CAVIAR/. Accessed Jan 2011
Engel S, Zhang X, Wandell B (1997) Colour tuning in human visual cortex measured with functional magnetic resonance imaging. Nature 388:68–71
Fahy FL, Riches IP, Brown MW (1993) Neuronal activity related to visual recognition memory: long-term memory and the encoding of recency and familiarity information in the primate anterior and medial inferior and rhinal cortex. Exp Brain Res 96:457–472
Fix J, Rougier N, Alexandre F (2010) A dynamic neural field approach to the covert and overt deployment of spatial attention. Cogn Comput 3:279–293
Gao D, Vasconcelos N (2007) Bottom-up saliency is a discriminant process. Proceedings of the IEEE international conference on computer vision, Rio de Janeiro
Gonzalez Andino SL, de Peralta Grave (2012) Coding of saliency by ensemble bursting in the amygdala of primates. Front Behav Neurosci 6(38):1–16
Greenspan H, Belongie S, Goodman R, Perona P, Rakshit S, Anderson CH (1994) Overcomplete steerable pyramid filters and rotation invariance. Proc IEEE Comput Vis Patt Recog 1:222–228
Hamker FH (2004) A dynamic model of how feature cues guide spatial attention. Vis Res 44:501–521
Hamker FH (2006) Modeling feature-based attention as an active top–down inference process. BioSystems 86:91–99
Horowitz TS, Wolfe JM, DiMase JS, Klieger SB (2007) Visual search for type of motion is based on simple motion primitives. Perception 36:1624–1634
Ibbotson M (2001) Identification of mechanisms underlying motion detection in mammals. Springer, Berlin
Itti L (2004) Automatic foveation for video compression using a neurobiological model of visual attention. IEEE Trans Image Proc 13:1304–1318
Itti L, Koch C (2000) A saliency-based search mechanism for overt and covert shifts of visual attention. Vis Res 40:1489–1506
Itti L, Koch C (2001) Computational modeling of visual attention. Nat Rev Neurosci 2:194–203
Itti L, Koch C, Niebur E (1998) A model of saliency-based visual attention for rapid scene analysis. IEEE Trans Patt Anal Mach Intel 20:1254–1259
Jonides J, Yantis S (1988) Uniqueness of abrupt visual onset in capturing attention. Percept Psychophys 43:346–354
Kusunoki M, Gottlieb J, Goldberg ME (2000) The lateral intraparietal area as a salience map: the representation of abrupt onset, stimulus motion, and task relevance. Vis Res 40:1459–1468
Li Z (1999) Contextual influences in V1 as a basis for pop out and asymmetry in visual search. Proc Natl Acad Sci 96(18):10530–10535
Li Z (2002) A saliency map in primary visual cortex. Trend Cogn Sci 6:9–16
Liu T, Sun J, Zheng NN, Tang X, Shum HY (2007) Learning to detect a salient object. Proceedings of IEEE computer society conference on computer and vision pattern recognition, Providence
López MT, Fenández-Caballero A, Fernández MA, Mira J, Delgado AE (2006) Motion features to enhance scene segmentation in active visual attention. Patt Recog Lett 27:469–478
Mahadevan V, Vasconcelos N (2010) Spatiotemporal saliency in dynamic scenes. IEEE Trans Pattern Anal Mach Intell 32: 171–177
Matsuno T, Tomonaga M (2006) Visual search for moving and stationary items in chimpanzees (Pan troglodytes) and humans (Homo sapiens). Behav Brain Res 172:219–232
Maunsell JHR, Treue S (2006) Feature-based attention in visual cortex. Trends Neurosci 29:317–322
Meso AI, Zanker JM (2009) Speed encoding in correlation motion detectors as a consequence of spatial structure. Biological Cybern 100:361–370
Mira J, Delgado AE, Lopez MT, Fernandez-Caballero A, Fernandez MA (2006) A conceptual frame with two neural mechanisms to model selective visual attention processes. Neurocomputing 71:704–720
Mundhenk TN, Itti L (2005) Computational modeling and exploration of contour integration for visual saliency. Biol Cybern 93:188–212
Nagy AL, Cone SM (1996) Asymmetries in simple feature searches for color. Vis Res 36:2837–2847
Navalpakkam V, Itti L (2002) A goal oriented attention guidance model. Lect Notes Comput Sci 2525:453–461
Navalpakkam V, Itti L (2005) Modeling the influence of task on attention. Vision Res. 45:205–231
Navalpakkam V, Itti L (2006) Modeling the influence of task on attention. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit 1:1–8
Nothdurft H (2000) Salience from feature contrast: additivity across dimensions. Vis Res 40:1183–1201
Oliva A, Torralba A, Castelhano MS, Henderson JM (2003) Top–down control of visual attention in object detection. Proc Int Conf Image Proc 1:253–256
Park SJ, An KH, Lee M (2002) Saliency map model with adaptive masking based on independent component analysis. Neurocomputing 49:417–422
Peters RJ, Iyer A, Itti L, Koch C (2005) Components of bottom-up gaze allocation in natural images. Vis Res 45:2397–2416
Pointing Gestures: Video Sequence Database (ICPR Workshop, Cambridge, United Kingdom). http://www.cvmt.dk/. Accessed Jan 2011
Pomplun M (2007) Advancing area activation towards a general model of eye movements in visual search. In: Gray WD (ed) Integrated models of cognitive systems. Oxford University Press, New York, pp 120–131
Ramirez-Villegas JF, Ramirez-Moreno DF (2012) Color coding in the cortex: a modified approach to bottom-up visual attention. Biol Cybern. doi:10.1007/s00422-012-0522-6. Accessed on 28 Sept 2012
Rapantzikos K, Tsapatsoulis N, Avrithis Y, Kollias S (2007) Bottom-up spatiotemporal visual attention model for video analysis. Image Proc IET 1:237–248
Reynolds JH, Heeger DJ (2009) The normalization model of attention. Neuron 61:168–185
Royden CS, Wolfe JM, Klempen N (2001) Visual search asymmetries in motion and optic flow fields. Percept Psychophys 63:436–444
Santos A, Mier D, Kirsch P, Meyer-Lindenberg A (2011) Evidence for a general face salience signal in human amygdala. Neuroimage 54:3111–3116
Schrater PR, Knill DC, Simoncelli EP (2000) Mechanisms of visual motion detection. Nature Neuroscience 3:64–68
Sejnowski TJ, Koch C, Churchland PS (1988) Computational neuroscience. Science 241:1299–1306
Serre T, Wolf L, Bileschi S, Riesenhuber M, Poggio T (2006) Robust object recognition with cortex-like mechanisms. IEEE Trans Patt Anal Mach Intell 29:1–17
Shen K, Martin P (2007) Neuronal activity in superior colliculus signals both stimulus identity and saccade goals during visual conjunction search. J Vis 7(5):15: 1–13
Shormaker PA, O’Carroll DC, Straw AD (2001) Implementation of visual motion detection with contrast adaptation. Proc SPIE 4591:316–327
Sobel KV, Pickard MD, Acklin WT (2009) Using feature preview to investigate the roles of top-down and bottom-up processing in conjunction search. Acta Psychol 132:22–30
Thompson KG, Bichot NP (2005) A visual salience map in the primate frontal eye field. Prog Brain Res 147:251–262
T’so DY, Gilbert CD (1988) The organization of chromatic and spatial interactions in the primate striate cortex. J Neurosci 8:1712–1727
Torralba A, Castelhano MS, Oliva A, Henderson JM (2006) Contextual guidance of eye movements and attention in real-world scenes: the role of global features in object search. Psychol Rev 113:766–786
Trapp S, Schroll H, Hamker FH (2012). Open and closed loops: A computational approach to attention and consciousness. Adv Cogn Psychol 8(1):1–8. doi:10.2478/v10053-008-0096-y
Treisman A, Sykes M, Gelade G (1977) Selective attention stimulus integration. In: Dornic S (ed) Attention and performance VI. Lawrence Erlbaum Associates, New Jersey, pp 333–361
Treisman AM, Gelade G (1980) A feature-integration theory of attention. Cogn Psychol 12:97–136
Treisman AM, Gormican S (1988) Feature analysis in early vision: evidence from search asymmetries. Psychol Rev 95:15–48
Tsodyks M, Pawelzik K, Markram H (1998) Neural networks with dynamic synapses. Neural Comput 10:821–835
Tsotsos JK (2001) Motion uniderstanding: task-directed attention and representation that link perception with action. Int J Comput Vis 45:265–280
Tsotsos JK, Liu Y, Matinez-Trujillo JC, Pomplun M, Simine E, Zhou K (2005) Attending to visual motion. Comput Vis Image Underst 100:3–40
Walther D, Koch C (2006) Modeling attention to salient proto-objects. Neural Networks 19:1395–1407
Wilson HR (2004) Spikes, decisions and actions: the dynamical foundations of neuroscience. Oxford University Press, New York
Wilson HR, Cowan JD (1973) A mathematical theory of the functional dynamics of cortical and thalamic nervous system. Kybernetik 13:55–80
Wolfe J, Butcher SJ, Lee C, Hyle M (2003) Changing your mind: on the contributions of top-down and bottom-up guidance in visual search for feature singletons. J Exp Psychol Hum Percept Perform 29:483–502
Wolfe JM (2001) Asymmetries in visual search: an introduction. Percept Psychophys 63:381–389
Yantis S (1993) Stimulus-driven attentional capture and attentional control settings. J Exp Psychol Hum Percept Perform 19:676–681
Zhaoping L (2006) Theoretical understanding of the early visual processes by data compression and data selection. Network: Comput Neural Syst 17:301–334
Acknowledgments
The authors of this work acknowledge the support of Ruben Coen-Cagli, Albert Einstein College of Medicine, NY, USA.
Author information
Authors and Affiliations
Corresponding author
Additional information
David F. Ramirez-Moreno and Juan F. Ramirez-Villegas contributed equally to the research reported in this work.
Rights and permissions
About this article
Cite this article
Ramirez-Moreno, D.F., Schwartz , O. & Ramirez-Villegas, J.F. A saliency-based bottom-up visual attention model for dynamic scenes analysis. Biol Cybern 107, 141–160 (2013). https://doi.org/10.1007/s00422-012-0542-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00422-012-0542-2