Anatomical Landmark Tracking for the Analysis of Animal Locomotion in X-ray Videos Using Active Appearance Models

X-ray videography is one of the most important techniques for the locomotion analysis of animals in biology, motion science and robotics. Unfortunately, the evaluation of vast amounts of acquired data is a tedious and time-consuming task. Until today, the anatomical landmarks of interest have to be located manually in hundreds of images for each image sequence. Therefore, an automatization of this task is highly desirable. The main difficulties for the automated tracking of these landmarks are the numerous occlusions due to the movement of the animal and the low contrast in the x-ray images. For this reason, standard tracking approaches fail in this setting. To overcome this limitation, we analyze the application of Active Appearance Models for this task. Based on real data, we show that these models are capable of effectively dealing with occurring occlusions and low contrast and can provide sound tracking results.

[1]  D HagerGregory,et al.  Efficient Region Tracking With Parametric Models of Geometry and Illumination , 1998 .

[2]  Timothy F. Cootes,et al.  Active Appearance Models , 1998, ECCV.

[3]  Timothy F. Cootes,et al.  Automatically Building Appearance Models from Images Sequences using Salient Features , 1999, BMVC.

[4]  L. Quassinti,et al.  Comparison of ACE activity in amphibian tissues: Rana esculenta and Xenopus laevis. , 2007, Comparative biochemistry and physiology. Part A, Molecular & integrative physiology.

[5]  Joachim Denzler,et al.  Markerless real-time 3-D target region tracking by motion backprojection from projection images , 2005, IEEE Transactions on Medical Imaging.

[6]  Milan Sonka,et al.  Multi-view active appearance models for consistent segmentation of multiple standard views: application to long and short-axis cardiac MR images , 2003, CARS.

[7]  Gregory D. Hager,et al.  Efficient Region Tracking With Parametric Models of Geometry and Illumination , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Timothy F. Cootes,et al.  Face Recognition Using Active Appearance Models , 1998, ECCV.

[9]  A method for accurate 3-D reconstruction of skeletal morphology and movement , 2007 .

[10]  Simon Baker,et al.  Lucas-Kanade 20 Years On: A Unifying Framework , 2004, International Journal of Computer Vision.

[11]  Stephen M Gatesy,et al.  Guineafowl hind limb function. II: Electromyographic analysis and motor pattern evolution , 1999, Journal of morphology.

[12]  Petros Maragos,et al.  Tongue tracking in Ultrasound images with Active Appearance Models , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

[13]  Bernd Neumann,et al.  Computer Vision — ECCV’98 , 1998, Lecture Notes in Computer Science.

[14]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[15]  Michel Dhome,et al.  Hyperplane Approximation for Template Matching , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Xiaoming Liu,et al.  Video-based face model fitting using Adaptive Active Appearance Model , 2010, Image Vis. Comput..

[17]  Scott Tashman,et al.  Validation of a new model-based tracking technique for measuring three-dimensional, in vivo glenohumeral joint kinematics. , 2006, Journal of biomechanical engineering.

[18]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[19]  Daijin Kim,et al.  Adaptive active appearance model with incremental learning , 2009, Pattern Recognit. Lett..

[20]  D. B. Baier,et al.  X-ray reconstruction of moving morphology (XROMM): precision, accuracy and applications in comparative biomechanics research. , 2010, Journal of experimental zoology. Part A, Ecological genetics and physiology.

[21]  Stephen M Gatesy,et al.  Guineafowl hind limb function. I: Cineradiographic analysis and speed effects , 1999, Journal of morphology.