Abstract
This paper describes a logic-based formalism for qualitative spatial reasoning with cast shadows (Perceptual Qualitative Relations on Shadows, or PQRS) and presents results of a mobile robot qualitative self-localisation experiment using this formalism. Shadow detection was accomplished by mapping the images from the robot’s monocular colour camera into a HSV colour space and then thresholding on the V dimension. We present results of self-localisation using two methods for obtaining the threshold automatically: in one method the images are segmented according to their grey-scale histograms, in the other, the threshold is set according to a prediction about the robot’s location, based upon a qualitative spatial reasoning theory about shadows. This theory-driven threshold search and the qualitative self-localisation procedure are the main contributions of the present research. To the best of our knowledge this is the first work that uses qualitative spatial representations both to perform robot self-localisation and to calibrate a robot’s interpretation of its perceptual input.
Notes
This holds if we assume a point light source; in the real world with shadows from larger sources, we can make a distinction between the shadow body (or Umbra) which is totally occluded, and the Penumbra, which is partially occluded by the caster from the viewpoint of the light source. For the current work, with robots, small light sources, and noisy sensors, we can assume a point light source without losing generality.
Note that we are only dealing with cast shadows, and not self-shadows.
References
Balan AO, Black MJ, Haussecker H, Sigal L (2007) Shining a light on human pose: on shadows, shading and the estimation of pose and shape. In: Proc international conference on computer vision (ICCV), pp 1–8
Balbiani P, Condotta JF (2002) Spatial reasoning about points in a multidimensional setting. Appl Intell 17(3):221–238
Bennett B, Cohn AG, Wolter F, Zakharyaschev M (2002) Multi-dimensional modal logic as a framework for spatio-temporal reasoning. Appl Intell 17(3):239–251
Cao X, Foroosh H (2007) Camera calibration and light source orientation from solar shadows. Proc Comput Vis Pattern Recogn 105(1):60–72
Casati R (2004) The shadow knows: a primer on the informational structure of cast shadows. Perception 33(11):1385–1396
Caspi Y, Werman M (2006) Vertical parallax from moving shadows. In: Proc computer vision and pattern recognition (CVPR), New York, USA
Castiello U, Lusher D, Burton C, Disler P (2003) Shadows in the brain. J Cogn Neurosci 15(6):862–872
Cavanagh P (2005) The artist as neuroscientist. Nature 434:301–307
Cheah CC, Liu C, Slotine JJE (2006) Adaptive tracking control for robots with unknown kinematic and dynamic properties. Int J Robot Res 25(3):283–296
Cohn AG, Renz J (2008) Qualitative spatial representation and reasoning. In: Handbook of knowledge representation. Elsevier, Amsterdam, pp 551–596
Cucchiara R, Grana C, Neri G, Piccardi M, Prati A (2001) The sakbot system for moving object detection and tracking. In: Video-based surveillance systems: computer vision and distributed processing (Part II—detection and tracking). Kluwer Academic, Dordrecht, pp 145–158
da Costa Kauffmann T (1979) The perspective of shadows: the history of the theory of shadow projection. J Warburg Courtauld Inst 38:258–287
Davis R, Shrobe H, Szolovits P (1993) What is a knowledge representation? AI Mag 14(1):17–33
Dee H, Santos P (2011) The perception and content of cast shadows: an interdisciplinary review. Spat Cogn Comput 11(3):226–253
dos Santos MV, de Brito RC, Park HH, Santos P (2009) Logic-based interpretation of geometrically observable changes occurring in dynamic scenes. Appl Intell 31(2):161–179
Fitzpatrick P, Torres-Jara E (2004) The power of the dark side: using cast shadows for visually-guided touching. In: Proc of the 4th IEEE/RAS international conference on humanoid robots, pp 437–449
Fogliaroni P, Wallgrün JO, Clementini E, Tarquini F, Wolter D (2009) A qualitative approach to localization and navigation based on visibility information. In: COSIT’09: proceedings of the 9th international conference on spatial information theory. Springer, Berlin, pp 312–329
Freksa C (1991) Conceptual neighbourhood and its role in temporal and spatial reasoning. In: Decision support systems and qualitative reasoning. Elsevier, Amsterdam, pp 181–193
Guesgen HW (2002) Reasoning about distance based on fuzzy sets. Appl Intell 17(3):265–270
Hsieh JW, Hu WF, Chang CJ, Chen JS (2003) Shadow elimination for effective moving object detection by Gaussian shadow modeling. Image Vis Comput 21(6):505–516
Kang JG, Kim S, An, SY, Oh SY (2012) A new approach to simultaneous localization and map building with implicit model learning using neuro evolutionary optimization. Appl Intell 36(1):242–269
Kunii Y, Gotoh T (2003) Evaluation of shadow range finder: SRF for planetary surface exploration. In: Proc of the IEEE international conference on robotics and automation (ICRA), pp 2573–2578
Lee JS, Roh SG, Kim DW, Moon H, Choi HR (2009) In-pipe robot navigation based upon the landmark recognition system using shadow images. In: Proc of the IEEE international conference on robotics and automation (ICRA), pp 1857–1862
Levitt TS, Lawton DT (1990) Qualitative navigation for mobile robots. Artif Intell 44:305–360
Mamassian P (2004) Impossible shadows and the shadow correspondence problem. Perception 33:1279–1290
Mamassian P, Goutcher R (2001) Prior knowledge on the illumination position. Cognition 81(1):B1–B9
Mamassian P, Knill DC, Kersten D (1998) The perception of cast shadows. Trends Cogn Sci 2(8):288–295
Martel-Brisson N, Zaccarin A (2007) Learning and removing cast shadows through a multidistribution approach. IEEE Trans Pattern Anal Mach Intell 29(7):1134–1146
Mendonça M, de Arruda LVR, Neves F Jr. (2012) Autonomous navigation system using event driven-fuzzy cognitive maps. Appl Intell 37(2):175–188
Otsu N (1979) A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern 9:62–66
Porikli F, Thornton J (2005) Shadow flow: a recursive method to learn moving cast shadows. In: Proc international conference on computer vision (ICCV)
Prati A, Mikic I, Trivedi M, Cucchiara R (2003) Detecting moving shadows: algorithms and evaluation. IEEE Trans Pattern Anal Mach Intell 25(7):918–923
Randell D, Cui Z, Cohn A (1992) A spatial logic based on regions and connection. In: International conference on knowledge representation and reasoning, Cambridge, US, pp 165–176
Randell D, Witkowski M, Shanahan M (2001) From images to bodies: modeling and exploiting spatial occlusion and motion parallax. In: International joint conference on artificial intelligence, Seattle, US, pp 57–63
Renno JRR, Orwell J, Thirde DJ, Jones GA (2004) Shadow classification and evaluation for soccer player detection. In: Proc British machine vision conference, Kingston upon Thames, UK, pp 839–848
Salvador E, Cavallaro A, Ebrahimi T (2004) Cast shadow segmentation using invariant color features. Comput Vis Image Underst 95(2):238–259
Santos P, Dee H, Fenelon V (2009) Qualitative robot localisation using information from cast shadows. In: Proc of the IEEE international conference on robotics and automation (ICRA), pp 220–225
Sapena O, Onaindäa E (2008) Planning in highly dynamic environments: an anytime approach for planning under time constraints. Appl Intell 29(1):90–109
Schlieder C (1993) Representing visible locations for qualitative navigation. In: Qualitative reasoning and decision technologies, pp 523–532. CIMNE
Stauder J, Mech R, Ostermann J (1999) Detection of moving cast shadows for object segmentation. IEEE Trans Multimed 1(1):65–76
Tompkins P, Stentz A, Whittaker WL (2001) Automated surface mission planning considering terrain, shadows, resources and time. In: Proceedings of the 6th international symposium on artificial intelligence, robotics and automation in space (i-SAIRAS’01), Montreal, Canada
Troccoli A, Allen PK (2004) A shadow-based method for model registration. In: IEEE computer vision and pattern recognition workshop (CVPRM)
van Benthem J (1991) The logic of time: a model theoretic investigation into the varieties of temporal ontology and temporal discourse. Kluwer Academic, Dordrecht
Wagner T, Huebner K (2004) Egocentric qualitative spatial knowledge representation for physical robots. In: 8th international workshop on RoboCup 2004 (Robot World Cup Soccer Games and Conferences). Lecture notes in artificial intelligence. Springer, Berlin, pp 134–149
Wang Y, Loe KF, Tan T, Wu JK (2005) A dynamic hidden Markov random field model for foreground and shadow segmentation. In: Proc IEEE workshop on applications of computer vision
Zimmermann K, Freksa C (1996) Qualitative spatial reasoning using orientation, distance, and path knowledge. Appl Intell 6(1):49–58
Acknowledgements
Paulo Santos acknowledges support from FAPESP project 2012/04089-3, São Paulo and bolsa PQ, CNPq 303331/2011-9; Hannah Dee acknowledges support from EPSRC project LAVID, EP/D061334/1, UK; Valquiria Fenelon is a graduate student sponsored by CAPES, Brazil; Fabio Cozman acknowledges FAPESP and bolsa PQ, CNPq 305395/2010-6.
Many thanks are also due to the anonymous reviewers for their thoughtful comments and to Roger Boyle for proof reading a final version of this paper.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Fenelon, V., Santos, P.E., Dee, H.M. et al. Reasoning about shadows in a mobile robot environment. Appl Intell 38, 553–565 (2013). https://doi.org/10.1007/s10489-012-0385-5
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-012-0385-5