Do Not Return Your Form to the above Organization
نویسنده
چکیده
In this just completed research program, we developed several new directions for our work in controlled active vision. We have developed a general framework for geometric observer-like structures based on nonparametric implicit (level set) curve descriptions of dynamically varying shapes. Special emphasis was given to the geometric nature of the dynamical system as well as the key issue of robustness. In particular, we formulated an approach to the problem of information transport and filtering from a measurement curve to an estimated curve. We also formulated a methodology to assess measurement reliability that allows for the selection of a local observer-gain. We should note that the dynamical nature of the evolving curves described implicitly allows for the observation of objects changing topology (i.e., objects breaking and merging during propagation) for which shape priors can be naturally incorporated. The proposed observer structure is continuous/discrete, with continuous-time system dynamics and discrete-time measurements. Its state space consists of an estimated curve position augmented by additional states (e.g., velocities) associated with every point on the estimated curve. Multiple simulation models were proposed for state prediction. Measurements are performed through segmentation algorithms and optical flow computations. In this framework, we may naturally incorporate several different tools such as particle filtering as well as various segmentation procedures. Accordingly, we described a novel information-based segmentation algorithm, which because of its local/global nature seems ideal for tracking and was combined with particle filtering for robust tracking in our geometric observer approach. Papers of Allen Tannenbaum and Collaborators under AFOSR Support Since 2008 1. “Fast approximation of smooth functions from samples of partial derivatives with applications to phase unwrapping” (with O. Michailovich), Signal Processing 88 (2008), pp. 358-374. 2. “Finsler active contours” (with E. Pichon and J. Melonakos), IEEE PAMI 30 (2008), pp. 412-423. 3. “Geometric observers for dynamically evolving curves” (with P. Vela and M. Niethammer), IEEE PAMI 30 (2008), pp. 1093-1108. 4. “Knowledge-based segmentation for tracking through deep turbulence” (with P. Vela, M. Niethammer, G. Pryor, R. Butts, and D. Washburn), IEEE Trans. Control Technology 16 (2008), pp. 469-475. 5. “A framework for image segmentation using shape models and kernel space shape priors” (with S. Dambreville and Y. Rathi), IEEE PAMI 30 (2008), pp. 1385-1399. 6. “Dynamic denoising of tracking sequences” (with O. Michailovich and Y. Rathi), IEEE Trans. Image Processing 17 (2008), pp. 847-857. 7. “Segmentation of tracking sequences using dynamically updated adaptive learning” (with O.Michailovich), IEEE Trans. on Image Processing 17 (2008), pp. 2403-2413. 8. “Localizing region-based active contours” (with S. Lankton), IEEE Trans. Image Processing 17 (2008), pp. 2029-2039. 9. “Choice of in vivo versus idealized velocity boundary conditions influences the flow field in subjectspecific models of the human carotid bifurcation” (with A. Wake, D. Giddens, J. Oshinsky), Journal of Biomedical Engineering 131 (2009). 10. “Real-time visual tracking using geometric active contours and particle filters” (with Jincheol Ha and E. Johnson), Journal of American Institute of Aeronautics and Astronautics 5(10) (2008), pp. 361-379. 11. “Vision-based range regulation of a leader-follower formation” (with P. Vela, A. Betser, J. Malcolm), IEEE Trans. Control Technology 17 (2009), pp. 442-449. 12. “Near tubular fiber bundle segmentation for diffusion weighted imaging: segmentation through frame reorientation” (with M. Niethammer and C. Zach), NeuroImage 45 (2009), pp. 123-132. 13. “An efficient numerical method for the solution of the L optimal mass transfer problem” (with E. Haber and T. Rehmen), SIAM Journal on Scientific Computation 32 (2010), pp. 197-211. 14. “3D nonrigid registration via optimal mass transport on the GPU” (with E. Haber, T. Rehman, G. Pryor, and J. Melonakos),MedIA 13 (2009), pp. 931-940. 15. “Deform PF-MT (Particle Filter with Mode Tracker) for tracking nonaffine contour deformations,” (with N. Vaswani, Y. Rathi, and A. Yezzi), IEEE Trans. Image Processing 19 (2010), pp. 841-857. 16. “A geometric approach to joint 2D region-based segmentation and 3D pose estimation using a 3D shape prior” (with S. Dambreville, R. Sandhu, A. Yezzi), SIAM Imaging Science 3 (2010), pp. 110132. 17. “Targeting of PbSe-Fe2O3 nanoplatforms by external magnetic field under viscous flow conditions,” (with Lioz Etgar, Arie Nakhmani, Efrat Lifshitz, and Rina Tannenbaum), Sensor Lett. 8 (2010), pp. 383-386. 18. “Trajectory control of PbSe γ−Fe2O3 nanoplatforms under viscous flow and an external magnetic field” (with L. Etgar, A. Nakhmani, E. Lifshitz, R. Tannenbaum), Nanotechnology 21 (2010), pp. 19. 19. “Texture mapping via optimal mass transport” (with A. Dominitz), IEEE TVCG 16 (2010), pp. 419433. 20. “Imaging of meningioma progression by matrix-assisted laser desorption/ionization time-of-flight mass spectrometry” (with N. Agar, J. Malcolm, V. Mohan, H. Yang, M. Johnson, J. Agar, P. Black), Analytical Chemistry 82 (2010), pp. 2621-2625. 21. “Affine registration of label maps in label space” (with Y. Rathi, J. Malcolm, S. Bouix, M. E. Shenton), Journal of Computing 2:4 (2010), pp. 1–11. 22. “Relevance vector machine learning for neonate pain intensity assessment using digital imaging” (with B. Gholami and W. Haddad), IEEE Trans. Biomedical Engineering 57 (2010), pp. 1457-1466. 23. “Point set registration via particle filtering and stochastic dynamics,” (with R. Sandhu and S. Dambreville), IEEE PAMI 32 (2010), pp. 1459-1473. 24. “A non-rigid kernel based framework for 2D/3D pose estimation and 2D image segmentation” (with R. Sandhu and S. Dambreville), IEEE PAMI 33, pp. 1098-1115. 25. “Tubular surface segmentation for extracting anatomical structures from medical imagery” (with V. Mohan and G. Sundaramoorthi), IEEE Trans. Medical Imaging 29 (2010), pp. 1945-1958.
منابع مشابه
Do Not Return Your Form to the above Organization
The public lllporting burden for this colleelion of Information Is eslimated to average 1 hour per response, Including the lime for reviewing instructions, sean::hing existing data sources, gathei1ng and maintaining the data naeded, and completing and reviewing the colleelion Of information. Send comments regarding this burden eslimate or any other aspect of this collection of lnfolrnation, InC...
متن کاملDo Not Return Your Form to the above Organization
The public reportmg burden for th1s collection of mformation is estimated to average 1 hour per response. includmg the time for rev>ewing instruct>ons. searclhing existing data sources. gathering and mmnta1mng the data needed. and completing and rev1ew1ng the collection of 1nforma t1 on. Send comments regarding th1s burden est1mate or any other aspect o fth1s collection of mformat1on . 1nclud1n...
متن کاملDo Not Return Your Form to the above Organization
The public reportmg burden for th1s collection of mformation is estimated to average 1 hour per response. includmg the time for rev>ewing instruct>ons. searclhing existing data sources. gathering and mmnta1mng the data needed. and completing and rev1ew1ng the collection of 1nforma t1 on. Send comments regarding th1s burden est1mate or any other aspect o fth1s collection of mformat1on . 1nclud1n...
متن کاملDo Not Return Your Form to the above Organization . 1 . Report Date ( Dd - Mm - Yyyy
The public reportmg burden for th1s collection of mformation is estimated to average 1 hour per response. includmg the time for rev>ewing instruct>ons. searclhing existing data sources. gathering and mmnta1mng the data needed. and completing and rev1ew1ng the collection of 1nforma t1 on. Send comments regarding th1s burden est1mate or any other aspect o fth1s collection of mformat1on . 1nclud1n...
متن کاملNot Return Your Form to the above Organization
The public reporting burden for this collection of information is estimated to average 1 hour per response, including the time for reviewing instructions, searching existing data sources, gathering and maintaining the data needed, and completing and reviewing the collection of information. Send comments regarding this burden estimate or any other aspect of this collection of information, includ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2012