Refining the Pose: Training and Use of Deep Recurrent Autoencoders for Improving Human Pose Estimation

作者: Niall McLaughlin , Jesus Martinez del Rincon

DOI: 10.1007/978-3-319-94544-6_2

关键词:

摘要: In this paper, a discriminative human pose estimation system based on deep learning is proposed for monocular video-sequences. Our approach combines simple but efficient Convolutional Neural Network that directly regresses the 3D with recurrent denoising autoencoder provides refinement using temporal information contained in sequence of previous frames. architecture also able to provide an integrated training between both parts order better model space activities, where noisy realistic poses produced by partially trained CNN are used enhance autoencoder. The has been evaluated two standard datasets, HumanEva-I and Human3.6M, comprising more than 15 different activities. We show our can state art results.

参考文章(25)
Juergen Gall, Bodo Rosenhahn, Thomas Brox, Hans-Peter Seidel, Optimization and Filtering for Human Motion Capture International Journal of Computer Vision. ,vol. 87, pp. 75- 92 ,(2010) , 10.1007/S11263-008-0173-1
Sepp Hochreiter, Jürgen Schmidhuber, Long short-term memory Neural Computation. ,vol. 9, pp. 1735- 1780 ,(1997) , 10.1162/NECO.1997.9.8.1735
Leonid Sigal, Alexandru O. Balan, Michael J. Black, HumanEva: Synchronized Video and Motion Capture Dataset and Baseline Algorithm for Evaluation of Articulated Human Motion International Journal of Computer Vision. ,vol. 87, pp. 4- 27 ,(2010) , 10.1007/S11263-009-0273-6
Catalin Ionescu, Dragos Papava, Vlad Olaru, Cristian Sminchisescu, Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 36, pp. 1325- 1339 ,(2014) , 10.1109/TPAMI.2013.248
Michal Lewandowski, Jesus Martinez-del-Rincon, Dimitrios Makris, Jean-Christophe Nebel, Temporal Extension of Laplacian Eigenmaps for Unsupervised Dimensionality Reduction of Time Series international conference on pattern recognition. pp. 161- 164 ,(2010) , 10.1109/ICPR.2010.48
Alexander Toshev, Christian Szegedy, DeepPose: Human Pose Estimation via Deep Neural Networks computer vision and pattern recognition. pp. 1653- 1660 ,(2014) , 10.1109/CVPR.2014.214
Pascal Vincent, Hugo Larochelle, Isabelle Lajoie, Yoshua Bengio, Pierre-Antoine Manzagol, Léon Bottou, Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion Journal of Machine Learning Research. ,vol. 11, pp. 3371- 3408 ,(2010)
Liefeng Bo, Cristian Sminchisescu, Twin Gaussian Processes for Structured Prediction International Journal of Computer Vision. ,vol. 87, pp. 28- 52 ,(2010) , 10.1007/S11263-008-0204-Y
Alejandro Newell, Kaiyu Yang, Jia Deng, Stacked Hourglass Networks for Human Pose Estimation european conference on computer vision. pp. 483- 499 ,(2016) , 10.1007/978-3-319-46484-8_29
Bugra Tekin, Isinsu Katircioglu, Mathieu Salzmann, Vincent Lepetit, Pascal Fua, None, Structured Prediction of 3D Human Pose with Deep Neural Networks british machine vision conference. ,(2016) , 10.5244/C.30.130