{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:40:00Z","timestamp":1760244000180,"version":"build-2065373602"},"reference-count":48,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2009,11,20]],"date-time":"2009-11-20T00:00:00Z","timestamp":1258675200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/3.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Model-free tracking is important for solving tasks such as moving-object tracking and action recognition in cases where no prior object knowledge is available. For this purpose, we extend the concept of spatially synchronous dynamics in spin-lattice models to the spatiotemporal domain to track segments within an image sequence. The method is related to synchronization processes in neural networks and based on superparamagnetic clustering of data. Spin interactions result in the formation of clusters of correlated spins, providing an automatic labeling of corresponding image regions. The algorithm obeys detailed balance. This is an important property as it allows for consistent spin-transfer across subsequent frames, which can be used for segment tracking. Therefore, in the tracking process the correct equilibrium will always be found, which is an important advance as compared with other more heuristic tracking procedures. In the case of long image sequences, i.e., movies, the algorithm is augmented with a feedback mechanism, further stabilizing segment tracking.<\/jats:p>","DOI":"10.3390\/s91109355","type":"journal-article","created":{"date-parts":[[2009,11,20]],"date-time":"2009-11-20T10:10:17Z","timestamp":1258711817000},"page":"9355-9379","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Segment Tracking via a Spatiotemporal Linking Process including Feedback Stabilization in an n-D Lattice Model"],"prefix":"10.3390","volume":"9","author":[{"given":"Babette","family":"Dellen","sequence":"first","affiliation":[{"name":"Bernstein Center for Computational Neuroscience G\u00f6ttingen, Max-Planck Institute for Dynamics and Self-Organization, Bunsenstrasse 10, 37073 G\u00f6ttingen, Germany"},{"name":"Institut de Rob\u00f2tica i Inform\u00e0tica Industrial (CSIC-UPC), Llorens i Artigas 4-6, 08028 Barcelona, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eren","family":"Erdal Aksoy","sequence":"additional","affiliation":[{"name":"Bernstein Center for Computational Neuroscience G\u00f6ttingen, Department for Computational Neuroscience, III. Physikalisches Institut, Georg-August University G\u00f6ttingen - Biophysik, Friedrich-Hund Platz 1, 37077 G\u00f6ttingen, Germany;"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Florentin","family":"W\u00f6rg\u00f6tter","sequence":"additional","affiliation":[{"name":"Bernstein Center for Computational Neuroscience G\u00f6ttingen, Department for Computational Neuroscience, III. Physikalisches Institut, Georg-August University G\u00f6ttingen - Biophysik, Friedrich-Hund Platz 1, 37077 G\u00f6ttingen, Germany;"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2009,11,20]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1177352.1177355","article-title":"Object tracking: a survey","volume":"38","author":"Yilmaz","year":"2006","journal-title":"ACM Comput. Surv."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1109\/76.564107","article-title":"Spatio-temporal video segmentation using a joint similarity measure","volume":"7","author":"Choi","year":"1997","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1147","DOI":"10.1109\/76.809153","article-title":"Region-based representations of image and video: Segmentation tools for multimedia services","volume":"9","author":"Salembier","year":"1999","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"776","DOI":"10.1109\/76.856454","article-title":"Utilization of the recursive shortest spanning tree algorithm for video-object segmentation by 2-D affine motion modeling","volume":"10","author":"Tuncel","year":"2000","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"800","DOI":"10.1109\/34.946985","article-title":"Unsupervised segmentation of color-texture regions in images and video","volume":"23","author":"Deng","year":"2001","journal-title":"IEEE Trans. Pattern Anal. Machine Intell."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"326","DOI":"10.1109\/34.910886","article-title":"Video segmentation by MAP labeling of watershed segments","volume":"23","author":"Patras","year":"2001","journal-title":"IEEE Trans. Pattern Anal. Machine Intell."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1109\/76.475892","article-title":"Very low bit rate video coding using arbitrarily shaped region-based motion compensation","volume":"5","author":"Yokoyama","year":"1995","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1109\/76.718501","article-title":"Unsupervised video segmentation based on waterheds and temporal tracking","volume":"8","author":"Wang","year":"1998","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"782","DOI":"10.1109\/TCSVT.2004.828341","article-title":"Video object segmentation using Bayes-based temporal tracking and trajectory-based region merging","volume":"14","author":"Mezaris","year":"2004","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_10","unstructured":"Cremers, D. (,  2003). A variational framework for image segmentation combining motion estimation and shape regularization. Madison, WI, USA."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1017\/S0305004100027419","article-title":"Some generalized order-disorder transformations","volume":"48","author":"Potts","year":"1952","journal-title":"Proc. Cambridge Philos. Soc."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"609","DOI":"10.1109\/34.56204","article-title":"Boundary detection by constrained optimization","volume":"12","author":"Geman","year":"1990","journal-title":"IEEE Trans. Patt. Anal. Mach. Int."},{"key":"ref_13","unstructured":"Vorbr\u00fcggen, J.C. (1995). Zwei Modelle zur datengetriebenen Segmentierung visueller Daten, Harri Deutsch."},{"key":"ref_14","unstructured":"Eckes, C., and Vorbr\u00fcggen, J.C. (,  1996). Combining data-driven and model-based cues for segmentation of video sequences. San Diego, CA, USA."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"3251","DOI":"10.1103\/PhysRevLett.76.3251","article-title":"Superparametric clustering of data","volume":"76","author":"Blatt","year":"1996","journal-title":"Phys. Rev. Lett."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1547","DOI":"10.1162\/089976698300017304","article-title":"A fast and robust cluster update algorithm for image segmentation in spin-lattice models without annealing \u2013 visual latencies revisited","volume":"10","author":"Opara","year":"1998","journal-title":"Neural Comput."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1461","DOI":"10.1103\/PhysRevE.62.R1461","article-title":"Cluster update algorithm and recognition","volume":"62","year":"2000","journal-title":"Phys. Rev. E"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1007\/BF02980577","article-title":"Beitrag zur Theorie des Ferromagnetismus","volume":"31","author":"Ising","year":"1925","journal-title":"Zeitschrift f\u00fcr Physik"},{"key":"ref_19","first-page":"2001","article-title":"Fast Approximate Energy Minimization via Graph Cuts","volume":"23","author":"Boykov","year":"1999","journal-title":"IEEE Trans. Patt. Anal. Mach. Int."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1124","DOI":"10.1109\/TPAMI.2004.60","article-title":"An experimental comparison of min-cut\/max-flow algorithms for energy minmization in vision","volume":"26","author":"Boykov","year":"2004","journal-title":"IEEE Trans. PAMI"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"721","DOI":"10.1109\/TPAMI.1984.4767596","article-title":"Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images","volume":"6","author":"Geman","year":"1984","journal-title":"IEEE Trans. Patt. Anal. Mach. Int."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1103\/PhysRevLett.58.86","article-title":"Nonuniversal critical dynamics in Monte Carlo simulations","volume":"76","author":"Swendsen","year":"1987","journal-title":"Phys. Rev. Lett."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1103\/PhysRevLett.62.361","article-title":"Collective Monte Carlo updating for spin systems","volume":"62","author":"Wolff","year":"1989","journal-title":"Phys. Rev. Lett."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1007\/BF01420984","article-title":"Performance of optical flow techniques","volume":"12","author":"Barron","year":"1994","journal-title":"Int. J. Comput. Vis."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Aksoy, E.E., W\u00f6rg\u00f6tter, F., and Dellen, B. (2009). Recognizing object-action relations from semantic scene graphs. submitted.","DOI":"10.1109\/ROBOT.2010.5509319"},{"key":"ref_26","unstructured":"Sabatini, S.P., Gastaldi, G., Solari, F., Diaz, J., Ros, E., Pauwels, K., Hulle, K.M.M.V., Pugeault, N., and Kr\u00fcger, N. (,  2007). Compact and Accurate Early Vision Processing in the Harmonic Space. Barcelona, Spain."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1087","DOI":"10.1063\/1.1699114","article-title":"Equations of state calculations by fast computing machines","volume":"21","author":"Metropolis","year":"1953","journal-title":"J. Chem. Phys."},{"key":"ref_28","unstructured":"Felzenszwalb, P., and Huttenlocher, D.P. (,  2004). Efficient Belief Propagation for Early Vision. Washington, DC, USA."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1239","DOI":"10.1109\/TPAMI.2005.161","article-title":"Generalizing Swendson-Wang to sampling arbitrary posterior probabilities","volume":"27","author":"Barbu","year":"2005","journal-title":"Trans. Pattern Anal. Mach. Intell."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1103\/PhysRevLett.62.361","article-title":"Collective monte carlo updating for spin systems","volume":"62","author":"Wolff","year":"1989","journal-title":"Phys. Rev. Lett."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1002\/(SICI)1098-2418(199910\/12)15:3\/4<242::AID-RSA4>3.0.CO;2-C","article-title":"Mixing properties of the Swendsen-Wang process on certain classes of graphs","volume":"15","author":"Cooper","year":"1999","journal-title":"Random Struct. Algorithm"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Gore, V.K., and Jerrum, M.R. (1996). The Swendsen-Wang Process Does Not Always Mix Rapidly, ACM.","DOI":"10.1145\/258533.258662"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1103\/PhysRev.65.117","article-title":"Crystal Statistic. I. Two-dimensional model with an order-disorder transition","volume":"64","author":"Onsager","year":"1944","journal-title":"Phys. Rev."},{"key":"ref_34","unstructured":"Lucas, B.D., and Kanade, T. (,  1981). An iterative image registration technique with an application to stereo vision. Pittsburgh, PA, USA."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Dellen, B., and W\u00f6rg\u00f6tter, F (,  2008). A local algorithm for the computation of optic flow via constructive interference of global Fourier components. Leeds, UK.","DOI":"10.5244\/C.22.79"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1080\/01621459.1963.10500845","article-title":"Hierarchical grouping to optimize an objective function","volume":"58","author":"Ward","year":"1963","journal-title":"J. Am. Statistical Assoc."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1875","DOI":"10.1109\/TPAMI.2006.227","article-title":"Fast agglomerative clustering using a k-nearest neighbor graph","volume":"28","author":"Virmajoki","year":"2006","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Toshev, A., Shi, J., and Daniilidis, K. (,  2007). Image matching via saliency region correspondences. Minneapolis, MN, USA.","DOI":"10.1109\/CVPR.2007.382973"},{"key":"ref_39","unstructured":"Rother, C., Minka, T., Blake, A., and Kolmogorov, V. (,  2006). Cosegmentation of Image Pairs by Histogram Matching - Incorporating a Global Constraint into MRFs, Washington, DC, USA."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1115\/1.3662552","article-title":"A new approach to linear filtering and prediction problems","volume":"82","author":"Kalman","year":"1960","journal-title":"J. Basic Eng."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1109\/7.640267","article-title":"Interacting multiple model methods in target tracking: A survey","volume":"34","author":"Mazor","year":"1998","journal-title":"IEEE Trans. Aerosp. Electron. Syst."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1109\/78.978374","article-title":"A tutorial on particle filters for online nonlinear\/nonGaussian bayesian tracking","volume":"50","author":"Arulampalam","year":"2002","journal-title":"IEEE Trans. Signal Process"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1477","DOI":"10.1109\/TCSVT.2006.885715","article-title":"Cooperative Multitarget Tracking With Efficient Split and Merge Handling","volume":"16","author":"Kumar","year":"2006","journal-title":"IEEE Trans. Circ. Syst. Video. T."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1111\/j.2517-6161.1989.tb01764.x","article-title":"Exact maximum a posteriori estimation for binary images","volume":"31","author":"Greig","year":"1989","journal-title":"Appl. Stat.-J. Roy. Stat. Soc. B"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"485","DOI":"10.1111\/j.2517-6161.1995.tb02043.x","article-title":"Fast approximate maximum a posteriori restoration of multicolour images","volume":"57","author":"Ferrari","year":"1995","journal-title":"Appl. Stat.-J. Roy. Stat. Soc. B"},{"key":"ref_46","unstructured":"Roy, S., and Cox, I. (,  1998). A maximum-flow formulation of the n-camera stereo correspondence problem. Bombay, India."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Ishikawa, H., and Geiger, D. (,  1998). Occlusions, discontinuities, and epipoloar lines in stereo. Freiburg, Germany.","DOI":"10.1007\/BFb0055670"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"1977","DOI":"10.1016\/j.patcog.2008.10.013","article-title":"Fast connected-component labeling","volume":"42","author":"He","year":"2009","journal-title":"Pattern Recognit."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/9\/11\/9355\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T22:11:44Z","timestamp":1760220704000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/9\/11\/9355"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,11,20]]},"references-count":48,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2009,11]]}},"alternative-id":["s91109355"],"URL":"https:\/\/doi.org\/10.3390\/s91109355","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2009,11,20]]}}}