Robust tracking and posture description for laboratory rodents using active shape models
Tóm tắt
We are in the process of developing an automated image analysis system, which uses deformable models of shape, learned from image examples, to interpret video images of rodents. Active shape models provide a compact description of the shape of the animal in a way that enables the postures that differentiate various behaviors to be distinguished. They also model the image profile across the shape boundary. We show how these features allow automatic, robust segmentation of the explicit object of interest. Rather than just detecting movement or changes from background in the image, the system can focus on objects that are of the correct shape and appearance. The modeling of the image profiles also allows the system to distinguish between the actual animal and image artifacts. We show how these techniques are being extended to extract postural information, which can then be integrated with positional data to produce a model of behavior.
Tài liệu tham khảo
Anderson, T. W. (1984).An introduction to multivariate statistical analysis (2nd ed.). New York: Wiley.
Baumberg, A, &Hogg, D. (1994). An efficient method for contour tracking using active shape models. InProceedings of the 1994 IEEE Workshop on Motion of Non-Rigid and Articulated Objects (pp. 194–199). Los Alamitos, CA: IEEE Computer Society Press.
Brown, R. E., Stanford, L., &Schellinck, H. M. (2000). Developing standardised behavioral tests for knockout and mutant mice.Institute for Laboratory Animal Research Journal,41, 163–174.
Bulpitt, A. J., Boyle, R. D., & Forbes, J. M. (2000, August).Monitoring behavior of individuals in crowded scenes. Paper presented at Measuring Behavior 2000, 3rd International Conference on Methods and Techniques in Behavioral Research, Nijmegen, The Netherlands.
Butcher, D., Cootes, T. F., Courtney, P., Gill, M., &Lithgow, G. J. (1999). Model-based image analysis of a model organismfor life science research. InProceedings of the IEE 7th International Conference on Image Processing and Its Applications (pp. 392–396). London: Institution of Electrical Engineers.
Cootes, T.F., Hill, A., &Taylor, C. J. (1994). Theuse of active shape models for locating structure in medical images.Image & Vision Computing,12, 355–366.
Cootes, T. F., &Taylor, C. J. (1993). Active shape model search using local grey-level models: A quantitative evaluation. In J. Illingworth (Ed.),Proceedings of the 4th British Machine Vision Conference, 1993 (pp. 639–648). Guildford, U.K.: BMVA Press.
Cootes, T. F., &Taylor, C. J. (1999). A mixture model for representing shape variation.Image & Vision Computing,17, 567–573.
Cootes, T. F., & Taylor, C. J. (2000).Statistical models of appearance for computer vision [On-line document]. Available: www.isbe.man. ac.uk/~bim/Models/app_model.ps.gz.
Eisenberg, J. E. (1968). Behavior patterns. In J. A. King (Ed.),Biology of Peromyscus (rodentia) (pp. 451–495). Washington, DC: American Society of Mammologists.
Geisler, H. C., Westerga, J., &Gramsbergen, A (1993). Development of posture in the rat.Acta Neurobiologiae Experimentalis,53, 517–523.
Goodall, C. (1991). Procrustes methods in the statistical analysis of shape.Journal of the Royal Statistical Society: Series B,53, 285–339.
Grant, R. C., &Mackintosh, J. H. (1963). A description of the social postures of some laboratory rodents.Behaviour,21, 246–259.
Grewal, S. S., Shepherd, J. K., Bill, D. J., Fletcher, A., &Dourish, C. T. (1997). Behavioural and pharmacological characterisation of the canopy stretched attend posture test as a model of anxiety in mice and rats.Psychopharmacology,133, 29–38.
Heeren, D. J., &Cools, A. R. (2000). Classifying postures of freely moving rodents with the help of Fourier descriptors and a neural network.Behavior Research Methods, Instruments, & Computers,32, 56–62.
Hogg, S. (1996). A review of the validity and variability of the elevated plus-maze as an animal model of anxiety.Pharmacology Biochemistry & Behavior,54, 21–30.
Lister, R. G. (1987). The use of a plus-maze to measure anxiety in the mouse.Psychopharmacology,92, 180–185.
Magee, D., &Boyle, R. (1999). Feature tracking in real world scenes (or how to track a cow). InProceedings of the IEE Colloquium on Motion Analysis and Tracking (pp. 21–27). London: Institution of Electrical Engineers.
Marchant, J. A., &Onyango, C. M. (1995). Fitting grey level point distribution models to animals in scenes.Image & Vision Computing,13, 3–12.
Noldus, L. (2000). Digital imaging, ultra-sound measurement and infrared thermography: New techniques to refine behavioral observation.Noldus News,7, 1–6.
Pellow, S., &File, S. E. (1986). Anxiolytic and anxiogenic drug effects on exploratory activity in an elevated plus-maze: A novel test of anxiety in therat.Pharmacology, Biochemistry & Behavior,24, 525–529.
Redhead, A. L., Kotcheff, A. C. W., Taylor, C. J., Porter, M. L., &Hukins, D. W. L. (1997). An automated method for assessing routine radiographs of patients with total hip replacements.Journal of Engineering in Medicine,211, 145–154.
Renner, M. J., &Seltzer, C. P. (1991). Molar characteristics of exploratory and investigatory behavior in the rat (Rattus norvegicus).Journal of Comparative Psychology,105, 326–339.
Rodgers, R. J., &Dalvi, A. (1997). Anxiety, defence and the elevated plus-maze.Neuroscience & Biobehavioral Reviews,21, 801–810.
Rogers, D. C., Fisher, E. M., Brown, S. D., Peters, J., Hunter, A. J., &Martin, J. E. (1997). Behavioral and functional analysis of mouse phenotype: SHIRPA, a proposed protocolfor comprehensive phenotype assessment.Mammalian Genome,8, 711–713.
Rousseau, J. B. I., Van Lochem, P. B. A, Gispen, W. H., &Spruijt, B. M. (2000). Classification of rat behavior with an image-processing method and a neural network.Behavior Research Methods, Instruments, & Computers,32, 63–71.
Sams-Dodd, F. (1995). Automation of the social interaction test by a video-tracking system: Behavioural effects of repeated phencyclidine treatment.Journal of Neuroscience Methods,59, 157–167.
Schlingmann, F., Van de Weerd, H. A., Baumans, V., Remie, R., &Van Zutphen, L. F. M. (1998). A balance device for the analysis of behavioural patterns of the mouse.Animal Welfare,7, 177–188.
Shepherd, J. K., Grewal, S. S., Fletcher, A., Bill, D. J., &Dourish, C. T. (1994). Behavioural and pharmacological characterisation of the elevated zero-maze as an animal model of anxiety.Psychopharmacology,116, 56–64.
Solloway, S., Hutchinson, C. E., Waterton, J. C., &Taylor, C. J. (1997). The use of active shape models for making thickness measurements of articular cartilage from MR images.Magnetic Resonance in Medicine,37, 943–952.
Spinka, M., Sustr, P., &Newberry, R. (1999). A colorful Ethovision masquerade, or how to trace pig maneuvering automatically.Noldus News,6, 6–7.
Sumpter, N., &Bulpitt, A. J. (1998). Learning spatio-temporal patterns for predicting object behaviour. In P. H. Lewis & M. S. Nixon (Eds.),Proceedings of the 9th British Machine Vision Conference, 1998 (Vol. 2, pp. 649–658). Guildford, U.K.: BMVA Press.
Timmermans, P. J. A. (1978).Social behaviour in the rat. Unpublished doctoral dissertation, KatholiekeUniversiteit Nijmegen, The Netherlands.
Van Abeelen, J. H. F. (1963). Mouse mutants studied by means of ethological methods: 1. Ethogram.Genetica,34, 79–94.
Weiss, S. M., Wadsworth, G., Fletcher, A., &Dourish, C. T. (1998). Utility of ethological analysis to overcome locomotor confounds in elevated maze models of anxiety.Neuroscience & Biobehavioral Reviews,23, 265–271.
Zangrossi, H., &Graeff, F. G. (1997). Behavioral validation of the elevated T-maze: A new animal model of anxiety.Brain Research Bulletin,44, 1–5.