Patient MoCap: Human Pose Estimation Under Blanket Occlusion for Hospital Monitoring Applications

详细信息    查看全文

• 关键词：Pose estimation ; Motion capture ; Occlusion ; CNN ; RNN ; Random forest
• 刊名：Lecture Notes in Computer Science
• 出版年：2016
• 出版时间：2016
• 年：2016
• 卷：9900
• 期：1
• 页码：491-499
• 全文大小：1,127 KB
• 参考文献：1.Stone, E.E., Skubic, M.: Unobtrusive, continuous, in-home gait measurement using the microsoft kinect. IEEE Trans. Biomed. Eng. 60(10), 2925–2932 (2013)CrossRef
  2.Kontschieder, P., Dorn, J.F., Morrison, C., Corish, R., Zikic, D., Sellen, A., D’Souza, M., Kamm, C.P., Burggraaff, J., Tewarie, P., Vogel, T., Azzarito, M., Glocker, B., Chin, P., Dahlke, F., Polman, C., Kappos, L., Uitdehaag, B., Criminisi, A.: Quantifying progression of multiple sclerosis via classification of depth videos. In: Golland, P., Hata, N., Barillot, C., Hornegger, J., Howe, R. (eds.) MICCAI 2014, Part II. LNCS, vol. 8674, pp. 429–437. Springer, Heidelberg (2014)
  3.Cunha, J., Choupina, H., Rocha, A., Fernandes, J., Achilles, F., Loesch, A., Vollmar, C., Hartl, E., Noachtar, S.: NeuroKinect: a novel low-cost 3Dvideo-EEG system for epileptic seizure motion quantification. PLOS ONE 11(1), e0145669 (2015)CrossRef
  4.Benbadis, S.R., LaFrance, W., Papandonatos, G., Korabathina, K., Lin, K., Kraemer, H., et al.: Interrater reliability of eeg-video monitoring. Neurology 73(11), 843–846 (2009)CrossRef
  5.Li, Y., Berkowitz, L., Noskin, G., Mehrotra, S.: Detection of patient’s bed statuses in 3D using a microsoft kinect. In: EMBC. IEEE (2014)
  6.Yu, M.-C., Wu, H., Liou, J.-L., Lee, M.-S., Hung, Y.-P.: Multiparameter sleep monitoring using a depth camera. In: Schier, J., Huffel, S., Conchon, E., Correia, C., Fred, A., Gamboa, H., Gabriel, J. (eds.) BIOSTEC 2012. CCIS, vol. 357, pp. 311–325. Springer, Heidelberg (2013)CrossRef
  7.Shotton, J., Sharp, T., Kipman, A., Fitzgibbon, A., Finocchio, M., Blake, A., Cook, M., Moore, R.: Real-time human pose recognition in parts from single depth images. Commun. ACM 56(1), 116–124 (2013)CrossRef
  8.Girshick, R., Shotton, J., Kohli, P., Criminisi, A., Fitzgibbon, A.: Efficient regression of general-activity human poses from depth images. In: ICCV. IEEE (2011)
  9.Belagiannis, V., Rupprecht, C., Carneiro, G., Navab, N.: Robust optimization for deep regression. In: ICCV. IEEE (2015)
  10.Fragkiadaki, K., Levine, S., Felsen, P., Malik, J.: Recurrent network models for human dynamics. In: ICCV. IEEE (2015)
  11.Graves, A.: Generating sequences with recurrent neural networks. arXiv preprint arXiv:​1308.​0850 (2013)
  12.Museth, K., Lait, J., Johanson, J., Budsberg, J., Henderson, R., Alden, M., Cucka, P., Hill, D., Pearce, A.: OpenVDB: an open-source data structure and toolkit for high-resolution volumes. In: ACM SIGGRAPH 2013 Courses. ACM (2013)
  13.Bouaziz, S., Martin, S., Liu, T., Kavan, L., Pauly, M.: Projective dynamics: fusing constraint projections for fast simulation. ACM Trans. Graph. (TOG) 33(4), 154 (2014)CrossRef
  
• 作者单位：Felix Achilles (18) (19)
  Alexandru-Eugen Ichim (20)
  Huseyin Coskun (18)
  Federico Tombari (18) (21)
  Soheyl Noachtar (19)
  Nassir Navab (18) (22)
  
  18. Computer Aided Medical Procedures, Technische Universität München, Munich, Germany
  19. Department of Neurology, Ludwig-Maximilians-University of Munich, Munich, Germany
  20. Graphics and Geometry Laboratory, EPFL, Lausanne, Switzerland
  21. DISI, University of Bologna, Bologna, Italy
  22. Computer Aided Medical Procedures, Johns Hopkins University, Baltimore, USA
  
• 丛书名：Medical Image Computing and Computer-Assisted Intervention ¨C MICCAI 2016
• ISBN：978-3-319-46720-7
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349
• 卷排序：9900

文摘

Motion analysis is typically used for a range of diagnostic procedures in the hospital. While automatic pose estimation from RGB-D input has entered the hospital in the domain of rehabilitation medicine and gait analysis, no such method is available for bed-ridden patients. However, patient pose estimation in the bed is required in several fields such as sleep laboratories, epilepsy monitoring and intensive care units. In this work, we propose a learning-based method that allows to automatically infer 3D patient pose from depth images. To this end we rely on a combination of convolutional neural network and recurrent neural network, which we train on a large database that covers a range of motions in the hospital bed. We compare to a state of the art pose estimation method which is trained on the same data and show the superior result of our method. Furthermore, we show that our method can estimate the joint positions under a simulated occluding blanket with an average joint error of 7.56 cm.