{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T01:17:10Z","timestamp":1722907030052},"reference-count":39,"publisher":"IGI Global","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,10,1]]},"abstract":"<p>Hand pose estimation for a continuous sequence has been an important topic not only in computer vision but also human-computer-interaction. Exploring the feasibility to use hand gestures to replace input devices, e.g., mouse, keyboard, joy-stick and touch screen, has attracted increasing attention from academic and industrial researchers. The fast advancement of hand pose estimation techniques is complemented by the rapid development of smart sensors technology such as Kinect and Leap. We introduce a hand pose estimation multi-sensor system. Two tracking models are proposed based on Deep (Recurrent) Neural Network (DRNN) architecture. Data captured from different sensors are analyzed and fused to produce an optimal hand pose sequence. Experimental results show that our models outperform previous methods with better accuracy, meeting real-time application requirement. Performance comparisons between DNN and DRNN, spatial and spatial-temporal features, and single- and dual- sensors, are also presented.<\/p>","DOI":"10.4018\/ijmdem.2017100101","type":"journal-article","created":{"date-parts":[[2017,8,1]],"date-time":"2017-08-01T07:49:46Z","timestamp":1501573786000},"page":"1-18","source":"Crossref","is-referenced-by-count":2,"title":["Multi-Sensor Motion Fusion Using Deep Neural Network Learning"],"prefix":"10.4018","volume":"8","author":[{"given":"Xinyao","family":"Sun","sequence":"first","affiliation":[{"name":"University of Alberta, Edmonton, Canada"}]},{"given":"Anup","family":"Basu","sequence":"additional","affiliation":[{"name":"University of Alberta, Edmonton, Canada"}]},{"given":"Irene","family":"Cheng","sequence":"additional","affiliation":[{"name":"University of Alberta, Edmonton, Canada"}]}],"member":"2432","reference":[{"key":"IJMDEM.2017100101-0","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., . . . Kaise, L. (2016, July 01). TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed. Retrieved from http:\/\/arxiv.org\/abs\/1603.04467"},{"key":"IJMDEM.2017100101-1","doi-asserted-by":"crossref","unstructured":"Anagnostopoulos, C., & Hadjiefthymiades, S. (2013). Intelligent trajectory classification for improved movement prediction. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 44(10), 1301-1314.","DOI":"10.1109\/TSMC.2014.2316742"},{"key":"IJMDEM.2017100101-2","doi-asserted-by":"crossref","unstructured":"Blaha, J., & Gupta, M. (2014). Diplopia: A virtual reality game designed to help amblyopics.Proceedings of \u201814 IEEE Virtual Reality (VR) conference (pp. 163-164).","DOI":"10.1109\/VR.2014.6802102"},{"key":"IJMDEM.2017100101-3","doi-asserted-by":"publisher","DOI":"10.1016\/j.physio.2013.03.001"},{"key":"IJMDEM.2017100101-4","doi-asserted-by":"publisher","DOI":"10.1109\/IMTC.2007.379068"},{"key":"IJMDEM.2017100101-5","doi-asserted-by":"crossref","unstructured":"Chng, E. (2012). New ways of accessing information spaces using 3D multitouch tables. Proceedings of the 2012 International Conference on Cyberworlds (CW) (pp. 144-150).","DOI":"10.1109\/CW.2012.27"},{"key":"IJMDEM.2017100101-6","doi-asserted-by":"crossref","unstructured":"Ciregan, D., Meier, U., & Schmidhuber, J. (2012). Multi-column deep neural networks for image classification. Proceedings of the 2012 IEEE Conference on, Computer Vision and Pattern Recognition (CVPR) (pp. 3642-3649).","DOI":"10.1109\/CVPR.2012.6248110"},{"key":"IJMDEM.2017100101-7","doi-asserted-by":"publisher","DOI":"10.1016\/j.jofri.2014.05.006"},{"key":"IJMDEM.2017100101-8","unstructured":"Elmenreich, W. (2002). Sensor fusion in time-triggered systems."},{"key":"IJMDEM.2017100101-9","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2015.7322485"},{"key":"IJMDEM.2017100101-10","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks.","volume":"9","author":"X.Glorot","year":"2010","journal-title":"Aistats"},{"key":"IJMDEM.2017100101-11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"IJMDEM.2017100101-12","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"IJMDEM.2017100101-13","article-title":"An empirical exploration of recurrent network architectures.","author":"R.Jozefowicz","year":"2015","journal-title":"Journal of Machine Learning Research"},{"key":"IJMDEM.2017100101-14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"IJMDEM.2017100101-15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33783-3_61"},{"key":"IJMDEM.2017100101-16","unstructured":"Kingma, D. P., & Ba, J. (2014). Adam: A Method for Stochastic Optimization. Retrieved from http:\/\/arxiv.org\/abs\/1412.6980"},{"key":"IJMDEM.2017100101-17","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks.","author":"A.Krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems"},{"key":"IJMDEM.2017100101-18","first-page":"437","author":"G.Lic","year":"2011","journal-title":"Conversational speech transcription using context-dependent deep neural networks"},{"key":"IJMDEM.2017100101-19","unstructured":"Oberweger, M., Wohlhart, P., & Lepetit, V. (2015). Hands deep in deep learning for hand pose estimation. arXiv preprint arXiv:1502.06807"},{"key":"IJMDEM.2017100101-20","first-page":"3","article-title":"Efficient model-based 3D tracking of hand articulations using Kinect.","volume":"1","author":"I.Oikonomidis","year":"2011","journal-title":"BmVC"},{"key":"IJMDEM.2017100101-21","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2015.2467212"},{"key":"IJMDEM.2017100101-22","doi-asserted-by":"publisher","DOI":"10.1142\/9781783269877_0019"},{"key":"IJMDEM.2017100101-23","unstructured":"Schmidhuber, J. (2014). Deep Learning in Neural Networks: An Overview. Retrieved from http:\/\/arxiv.org\/abs\/1404.7828"},{"key":"IJMDEM.2017100101-24","author":"F.Seide","year":"2011","journal-title":"Conversational Speech Transcription Using Context-Dependent Deep Neural Networks"},{"key":"IJMDEM.2017100101-25","doi-asserted-by":"crossref","unstructured":"Seo, K. T.-Y.-Y.-J. (2014). Performance comparison analysis of linux container and virtual machine for building cloud. Advanced Science and Technology Letters, 2.","DOI":"10.14257\/astl.2014.66.25"},{"key":"IJMDEM.2017100101-26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.450"},{"key":"IJMDEM.2017100101-27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298941"},{"key":"IJMDEM.2017100101-28","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting.","volume":"15","author":"N.Srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"IJMDEM.2017100101-29","doi-asserted-by":"publisher","DOI":"10.1109\/ISM.2016.0098"},{"key":"IJMDEM.2017100101-30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.217"},{"key":"IJMDEM.2017100101-31","first-page":"3104","article-title":"Sequence to sequence learning with neural networks.","author":"I.Sutskever","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"key":"IJMDEM.2017100101-32","doi-asserted-by":"publisher","DOI":"10.1145\/2735952"},{"key":"IJMDEM.2017100101-33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.490"},{"key":"IJMDEM.2017100101-34","unstructured":"Tian, G., & Zhou, M.-z. (2013). Pedestrian Detection Algorithm Based on the Movement Trend Estimation. Computer Knowledge and Technology, 43."},{"key":"IJMDEM.2017100101-35","doi-asserted-by":"publisher","DOI":"10.1145\/2629500"},{"key":"IJMDEM.2017100101-36","doi-asserted-by":"publisher","DOI":"10.1145\/971478.971513"},{"key":"IJMDEM.2017100101-37","doi-asserted-by":"publisher","DOI":"10.3390\/s130506380"},{"key":"IJMDEM.2017100101-38","unstructured":"Zhou, X., Wan, Q., Zhang, W., Xue, X., & Wei, Y. (2016). Model-based deep hand pose estimation. arXiv preprint arXiv:1606.06854."}],"container-title":["International Journal of Multimedia Data Engineering and Management"],"original-title":[],"language":"ng","link":[{"URL":"https:\/\/www.igi-global.com\/viewtitle.aspx?TitleId=187137","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,6]],"date-time":"2022-05-06T18:35:37Z","timestamp":1651862137000},"score":1,"resource":{"primary":{"URL":"https:\/\/services.igi-global.com\/resolvedoi\/resolve.aspx?doi=10.4018\/IJMDEM.2017100101"}},"subtitle":[""],"short-title":[],"issued":{"date-parts":[[2017,10,1]]},"references-count":39,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2017,10]]}},"URL":"https:\/\/doi.org\/10.4018\/ijmdem.2017100101","relation":{},"ISSN":["1947-8534","1947-8542"],"issn-type":[{"value":"1947-8534","type":"print"},{"value":"1947-8542","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,10,1]]}}}