{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T22:40:02Z","timestamp":1745966402427,"version":"3.40.4"},"publisher-location":"Berlin, Heidelberg","reference-count":52,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642075476"},{"type":"electronic","value":"9783662046197"}],"license":[{"start":{"date-parts":[[2001,1,1]],"date-time":"2001-01-01T00:00:00Z","timestamp":978307200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2001]]},"DOI":"10.1007\/978-3-662-04619-7_10","type":"book-chapter","created":{"date-parts":[[2013,2,26]],"date-time":"2013-02-26T23:38:51Z","timestamp":1361921931000},"page":"203-225","source":"Crossref","is-referenced-by-count":9,"title":["Joint Audio-Video Signal Processing for Object Localization and Tracking"],"prefix":"10.1007","author":[{"given":"Norbert","family":"Strobel","sequence":"first","affiliation":[]},{"given":"Sascha","family":"Spors","sequence":"additional","affiliation":[]},{"given":"Rudolf","family":"Rabenstein","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"10_CR1","volume-title":"Signal Processing (J. Griffiths, P. Stocklin, and C. Schooneveld, eds.), pp. 577-591, Academic Press","author":"W Bangs","year":"1973","unstructured":"W. Bangs and P. Schultheiss, \u201cSpace-time processing for optimal parameter estimation,\u201d in Signal Processing (J. Griffiths, P. Stocklin, and C. Schooneveld, eds.), pp. 577\u2013591, Academic Press, 1973."},{"issue":"5","key":"10_CR2","doi-asserted-by":"publisher","first-page":"608","DOI":"10.1109\/TIT.1973.1055077","volume":"19","author":"W Hahn","year":"1973","unstructured":"W. Hahn and S. Tretter, \u201cOptimum processing for delay-vector estimation in passive signal arrays,\u201d IEEE Trans. on Information Theory, vol. 19, no. 5, pp. 608\u2013614, 1973.","journal-title":"IEEE Trans. on Information Theory"},{"key":"10_CR3","unstructured":"W. Hahn, \u201cOptimum signal processing for passive sonar range and bearing estimation,\u201d Journal of the Acoustical Society of America, vol. 58, no. 1, pp. 201207, 1975."},{"issue":"3","key":"10_CR4","first-page":"463","volume":"29","author":"G Carter","year":"1981","unstructured":"G. Carter, \u201cTime delay estimation for passive sonar signal processing,\u201d IEEE Trans. on Acoustics, Speech, and Signal Processing, vol. 29, no. 3, pp. 463\u2013470, 1981.","journal-title":"and Signal Processing"},{"issue":"3","key":"10_CR5","first-page":"519","volume":"29","author":"N Owsley","year":"1981","unstructured":"N. Owsley and G. Swope, \u201cTime delay estimation in a sensor array,\u201d IEEE Trans. on Acoustics, Speech, and Signal Processing, vol. 29, no. 3, pp. 519\u2013523, 1981.","journal-title":"and Signal Processing"},{"key":"10_CR6","first-page":"3581","volume-title":"Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing (ICASSP-91), Toronto, Canada","author":"W Kellermann","year":"1991","unstructured":"W. Kellermann, \u201cA self-steering digital microphone array,\u201d in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing (ICASSP-91), Toronto, Canada, pp. 3581\u20133584, June 1991."},{"issue":"2","key":"10_CR7","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1016\/0885-2308(92)90023-W","volume":"6","author":"H Silverman","year":"1992","unstructured":"H. Silverman and S. Kirtman, \u201cA two-stage algorithm for determining talker location from linear microphone array data,\u201d Computer Speech and Language, vol. 6, no. 2, pp. 129\u2013152, 1992.","journal-title":"Computer Speech and Language"},{"key":"10_CR8","volume-title":"Proceedings Vision, Modeling, and Visualization 99 (B. Girod, H. Niemann, and H.-P. Seidel, eds.), (Erlangen), pp. 195202","author":"N Strobel","year":"1999","unstructured":"N. Strobel, T. Meier, and R. Rabenstein, \u201cSpeaker localization using steered filtered-and-sum beamformers,\u201d in Proceedings Vision, Modeling, and Visualization \u201889 (B. Girod, H. Niemann, and H.-P. Seidel, eds.), (Erlangen), pp. 195202, 1999."},{"key":"10_CR9","first-page":"I","volume-title":"Proceedings of the X European Signal Processing Conference, vol","author":"N Strobel","year":"2000","unstructured":"N. Strobel and R. Rabenstein, \u201cRobust speaker localization using a microphone array,\u201d in Proceedings of the X European Signal Processing Conference, vol. I II, 2000."},{"issue":"2","key":"10_CR10","first-page":"91","volume":"11","author":"M Brandstein","year":"1997","unstructured":"M. Brandstein and H. Silverman, \u201cA practical methodology for speech source localization with microphone arrays,\u201d Computer Speech and Language, vol. 11, no. 2, pp. 91\u2013126, April 1997.","journal-title":"vol"},{"key":"10_CR11","first-page":"371","volume-title":"Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing (ICASSP-97), Munich, Germany","author":"D Sturim","year":"1997","unstructured":"D. Sturim, M. Brandstein, and H. Silverman, \u201cTracking multiple talkers using microphone-array measurements,\u201d in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing (ICASSP-97), Munich, Germany, pp. 371\u2013374, April 1997."},{"issue":"8","key":"10_CR12","doi-asserted-by":"publisher","first-page":"1905","DOI":"10.1109\/78.301830","volume":"42","author":"Y Chan","year":"1994","unstructured":"Y. Chan and K. Ho, \u201cA simple and efficient estimator for hyperbolic location,\u201d IEEE Trans. on Signal Processing, vol. 42, no. 8, pp. 1905\u20131915, 1994.","journal-title":"IEEE Trans. on Signal Processing"},{"key":"10_CR13","first-page":"187","volume-title":"Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing (ICASSP-97), Munich, Germany","author":"H Wang","year":"1997","unstructured":"H. Wang and P. Chu, \u201cVoice source localization for automatic camera pointing system in videoconferencing,\u201d in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing (ICASSP-97), Munich, Germany, pp. 187\u201390, April 1997."},{"key":"10_CR14","unstructured":"D. Rabinkin, R. Renomeron, A. Dahl, et al.,\u201cA DSP implementation of source location using microphone arrays,\u201d in SPIE Proceedings \u201886,vol. 2846, pp. 8898, 1996."},{"issue":"5","key":"10_CR15","doi-asserted-by":"publisher","first-page":"705","DOI":"10.1109\/5.381842","volume":"83","author":"R Chellappa","year":"1995","unstructured":"R. Chellappa, C. Wilson, and A. Sirohey, \u201cHuman and machine recognition of faces: A survey,\u201d IEEE Proceedings, vol. 83, no. 5, pp. 705\u2013740, 1995.","journal-title":"IEEE Proceedings"},{"issue":"3","key":"10_CR16","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1016\/0923-5965(95)00028-U","volume":"7","author":"A Eleftheriadis","year":"1995","unstructured":"A. Eleftheriadis and A. Jacquin, \u201cAutomatic face location, detection and tracking for model-assisted coding of video teleconferencing sequences at low bit-rates,\u201d Signal Processing: Image Communication, vol. 7, no. 3, pp. 231\u2013248, 1995.","journal-title":"Signal Processing: Image Communication"},{"key":"10_CR17","first-page":"251","volume-title":"Proceedings of the 1997 Picture Coding Symposium, no. 143 in ITG-Fachberichte","author":"L Bala","year":"1997","unstructured":"L. Bala, K. Talmi, and J. Liu, \u201cAutomatic detection and tracking of faces and facial features in video sequences,\u201d in Proceedings of the 1997 Picture Coding Symposium, no. 143 in ITG-Fachberichte, pp. 251\u2013256, 1997."},{"key":"10_CR18","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1109\/CVPR.1997.609292","volume-title":"Proceedings of the 1997 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","author":"P Fieguth","year":"1997","unstructured":"P. Fieguth and D. Terzopoulos, \u201cColor-based tracking of heads and other mobile objects at video frame rates,\u201d in Proceedings of the 1997 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 21\u201327, 1997."},{"key":"10_CR19","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1109\/CVPR.1997.609393","volume-title":"Proceedings of the 1997 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","author":"J Crowley","year":"1997","unstructured":"J. Crowley and P. Berard, \u201cMulti-modal tracking of faces for video communications,\u201d in Proceedings of the 1997 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 640\u2013645, 1997."},{"key":"10_CR20","first-page":"131","volume-title":"Proceedings of the 1998 IEEE International Conference on Image Processing, vol. 1","author":"R Quian","year":"1998","unstructured":"R. Quian, M. Sezan, and K. Matthews, \u201cA robust real-time face tracking algorithm,\u201d in Proceedings of the 1998 IEEE International Conference on Image Processing, vol. 1, pp. 131\u2013135, 1998."},{"key":"10_CR21","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1109\/JRA.1987.1087109","volume":"3","author":"R Tsai","year":"1987","unstructured":"R. Tsai, \u201cA versatile camera calibration technique for high accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses,\u201d IEEE Trans. Robot. Autom., vol. 3, pp. 323\u2013344, 1987.","journal-title":"IEEE Trans. Robot. Autom."},{"key":"10_CR22","volume-title":"MIT Press","author":"O","year":"1993","unstructured":"O. Faugeras, Three-Dimensional Computer Vision: A Geometric Viewpoint, MIT Press, 1993."},{"issue":"3","key":"10_CR23","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1007\/BF01539538","volume":"10","author":"D Koller","year":"1993","unstructured":"D. Koller, D. Daniilidis, and H. Nagel, \u201cModel-based object tracking in monocular image sequences and road traffic scenes,\u201d International Journal of Computer Vision, vol. 10, no. 3, pp. 257\u2013281, 1993.","journal-title":"International Journal of Computer Vision"},{"key":"10_CR24","first-page":"682","volume-title":"Proceedings of the 1996 IEEE Intelligent Vehicle Symposium","author":"P Arnoul","year":"1996","unstructured":"P. Arnoul, M. Viala, J. Guerin, and M. Mergy, \u201cTraffic signs localisation for highway inventory from a video camera on board a moving collecting van,\u201d in Proceedings of the 1996 IEEE Intelligent Vehicle Symposium, pp. 682\u2013687, 1996."},{"issue":"7","key":"10_CR25","doi-asserted-by":"publisher","first-page":"1045","DOI":"10.1109\/76.795058","volume":"9","author":"GL Foresti","year":"1999","unstructured":"G. L. Foresti, \u201cObject recognition and tracking for remote video surveillance,\u201d IEEE Trans. on Circuits and Systems for Video Technology, vol. 9, no. 7, pp. 1045\u20131062, 1999.","journal-title":"IEEE Trans. on Circuits and Systems for Video Technology"},{"key":"10_CR26","first-page":"848","volume-title":"Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing (ICASSP-95), Detroit MI, USA","author":"U Bub","year":"1995","unstructured":"U. Bub, M. Hunke, and A. Waibel, \u201cKnowing who to listen to in speech recognition: Visually guided beamforming,\u201d in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing (ICASSP-95), Detroit MI, USA, pp. 848\u2013851, May 1995."},{"key":"10_CR27","doi-asserted-by":"crossref","unstructured":"M. Collobert, R. Freauc, G. Tourneur, et al.,\u201cLISTEN: a system for locating and tracking individual speakers,\u201d in Proceedings of the Second International Conference on Automatic Face and Gesture Recognition,pp. 283\u2013288, 1996.","DOI":"10.1109\/AFGR.1996.557278"},{"key":"10_CR28","first-page":"206","volume-title":"Proceedings of the SPIE, vol. 3310","author":"G Pingali","year":"1997","unstructured":"G. Pingali, \u201cIntegrated audio-visual processing for object localization and tracking,\u201d in Proceedings of the SPIE, vol. 3310, pp. 206\u2013213, 1997."},{"key":"10_CR29","first-page":"3737","volume-title":"Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing (ICASSP-98), Seattle WA, USA","author":"C Wang","year":"1998","unstructured":"C. Wang and M. Brandstein, \u201cA hybrid real-time face tracking system,\u201d in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing (ICASSP-98), Seattle WA, USA, pp. 3737\u20133740, May 1998."},{"key":"10_CR30","first-page":"169","volume-title":"IEEE Int. Workshop on Multimedia Signal Processing, Copenhagen, Denmark","author":"C Wang","year":"1999","unstructured":"C. Wang and M. Brandstein, \u201cMulti-source face tracking with audio and visual data,\u201d in IEEE Int. Workshop on Multimedia Signal Processing, Copenhagen, Denmark, pp. 169\u2013174, September 1999."},{"key":"10_CR31","first-page":"1384","volume-title":"Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing (ICASSP-2000), Instanbul, Turkey","author":"Y Huang","year":"2000","unstructured":"Y. Huang, J. Benesty, and G. Elko, \u201cPassive acoustic source localization for video camera steering,\u201d in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing (ICASSP-2000), Instanbul, Turkey, pp. 1384\u20131387, June 2000."},{"key":"10_CR32","volume-title":"Principles of 3D Image Analysis and Synthesis (B. Girod, G. Greiner, and H. Niemann, eds.), pp. 309-322, Kluwer","author":"N Strobel","year":"2000","unstructured":"N. Strobel and R. Rabenstein, \u201cFusion of multisensor data,\u201d in Principles of 3D Image Analysis and Synthesis (B. Girod, G. Greiner, and H. Niemann, eds.), pp. 309\u2013322, Kluwer, 2000."},{"issue":"6","key":"10_CR33","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1177\/027836498800700607","volume":"7","author":"J Richardson","year":"1988","unstructured":"J. Richardson and K. Marsh, \u201cFusion of multisensor data,\u201d International Journal of Robotics Research, vol. 7, no. 6, pp. 78\u201396, 1988.","journal-title":"International Journal of Robotics Research"},{"key":"10_CR34","volume-title":"Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing (ICASSP-2000), Istanbul, Turkey, pp. 37813784","author":"N Strobel","year":"2000","unstructured":"N. Strobel, S. Spors, and R. Rabenstein, \u201cJoint audio-video object localization using a recursive multi-state, multi-sensor estimator,\u201d in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing (ICASSP-2000), Istanbul, Turkey, pp. 37813784, June 2000."},{"key":"10_CR35","volume-title":"IEEE Signal Processing Magazine","author":"N Strobel","year":"2001","unstructured":"N. Strobel, S. Spors, and R. Rabenstein, \u201cJoint audio-video object localization and tracking,\u201d IEEE Signal Processing Magazine, Jan. 2001."},{"key":"10_CR36","volume-title":"Prentice Hall","author":"DH Johnson","year":"1993","unstructured":"D. H. Johnson and D. E. Dudgeon, Array Signal Processing - Concepts and Techniques, Prentice Hall, 1993."},{"key":"10_CR37","volume-title":"Addison-Wesley","author":"L Scharf","year":"1991","unstructured":"L. Scharf, Statistical Signal Processing-Detection, Estimation, and Time Series Analysis, Addison-Wesley, 1991."},{"key":"10_CR38","volume-title":"Lessons in Estimation Theory for Signal Processing","author":"J Mendel","year":"1995","unstructured":"J. Mendel, Lessons in Estimation Theory for Signal Processing, Communications, and Control, Prentice Hall, 1995."},{"key":"10_CR39","volume-title":"Wiley","author":"RG Brown","year":"1997","unstructured":"R. G. Brown and P. Y. Hwang, Introduction to random signals and applied Kalman filtering, Wiley, 1997."},{"key":"10_CR40","volume-title":"Data Fusion in Robotics and Machine Intelligence (Abidi and Gonzales, eds.), pp. 311-365, Academic Press","author":"T Broida","year":"1992","unstructured":"T. Broida, \u201cKinematic and statistical models for data fusion using Kalman filtering,\u201d in Data Fusion in Robotics and Machine Intelligence (Abidi and Gonzales, eds.), pp. 311\u2013365, Academic Press, 1992."},{"key":"10_CR41","unstructured":"A. Jazwinski, Stochastic Processes and Filtering Theory, Academic Press, 1970."},{"issue":"1","key":"10_CR42","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1177\/027836499301200102","volume":"12","author":"B Rao","year":"1993","unstructured":"B. Rao, H. Durrant-Whyte, and J. Sheen, \u201cA fully decentralized multi-sensor system for tracking and surveillance,\u201d International Journal of Robotics Research, vol. 12, no. 1, pp. 20\u201344, 1993.","journal-title":"International Journal of Robotics Research"},{"issue":"6","key":"10_CR43","doi-asserted-by":"publisher","first-page":"3807","DOI":"10.1121\/1.414998","volume":"99","author":"M Brandstein","year":"1996","unstructured":"M. Brandstein, J. Adcock, and H. Silverman, \u201cMicrophone array localization error estimation with application to sensor placement,\u201d J. Acoust. Soc. Am., vol. 99, no. 6, pp. 3807\u20133816, 1996.","journal-title":"J. Acoust. Soc. Am"},{"issue":"1","key":"10_CR44","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1109\/89.554268","volume":"5","author":"M Brandstein","year":"1997","unstructured":"M. Brandstein, J. Adcock, and H. Silverman, \u201cA closed-form location estimator for use with room environment microphone arrays,\u201d IEEE Trans. on Speech and Audio Processing, vol. 5, no. 1, pp. 45\u201350, 1997.","journal-title":"IEEE Trans. on Speech and Audio Processing"},{"key":"10_CR45","volume-title":"Academic Press","author":"Y Bar-Shalom","year":"1988","unstructured":"Y. Bar-Shalom and T. Fortman, Tracking and Data Association, Academic Press, 1988."},{"key":"10_CR46","volume-title":"MultitargetMultisensor Tracking: Advanced Applications (Y. Bar-Shalom, ed.), pp. 187218, Artech House","author":"S Blackman","year":"1990","unstructured":"S. Blackman, \u201cAssociation and fusion of multiple sensor data,\u201d in MultitargetMultisensor Tracking: Advanced Applications (Y. Bar-Shalom, ed.), pp. 187218, Artech House, 1990."},{"key":"10_CR47","volume-title":"Univ. of Conneticutt","author":"Y Bar-Shalom","year":"1995","unstructured":"Y. Bar-Shalom and X. Li, Multitarget-Multisensor Tracking: Principles and Techniques, Univ. of Conneticutt, 1995."},{"issue":"1","key":"10_CR48","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1109\/5.554210","volume":"85","author":"M Yeddanapudi","year":"1997","unstructured":"M. Yeddanapudi, Y. Bar-Shalom, and K. Pittipati, \u201cIMM estimation for multitarget-multisensor air traffic surveillance,\u201d IEEE Proceedings, vol. 85, no. 1, pp. 80\u201394, 1997.","journal-title":"IEEE Proceedings"},{"key":"10_CR49","volume-title":"Seventh Joint Service Data Fusion Symposium","author":"R Mahler","year":"1994","unstructured":"R. Mahler, \u201cA unified foundation for data fusion,\u201d in Seventh Joint Service Data Fusion Symposium, 1994."},{"key":"10_CR50","volume-title":"Tri-Service Data Fusion Symposium","author":"I Goodman","year":"1987","unstructured":"I. Goodman, \u201cA general theory for the fusion of data,\u201d in Tri-Service Data Fusion Symposium, 1987."},{"key":"10_CR51","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1007\/BF01299390","volume":"3","author":"A Poore","year":"1994","unstructured":"A. Poore, \u201cMulti-dimensional assignment formulation of data association problems arising from multi-target and multi-sensor tracking,\u201d Computational Optimization Applicat., vol. 3, pp. 27\u201357, 1994.","journal-title":"Computational Optimization Applicat"},{"key":"10_CR52","unstructured":"G. Wang, R. Rabenstein, N. Strobel, and S. Spors, \u201cObject localization by joint audio-video signal processing,\u201d in Proceedings Vision, Modeling, and Visualization 2000 (B. Girod, G. Greiner, H. Niemann, and H.-P. Seidel, eds.), Saarbr\u00fccken, Germany, pp. 97\u2013104, Nov. 2000."}],"container-title":["Digital Signal Processing","Microphone Arrays"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-662-04619-7_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T22:15:05Z","timestamp":1745964905000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-662-04619-7_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2001]]},"ISBN":["9783642075476","9783662046197"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-662-04619-7_10","relation":{},"ISSN":["1612-1457"],"issn-type":[{"type":"print","value":"1612-1457"}],"subject":[],"published":{"date-parts":[[2001]]}}}