Abstract

In this study, a human motion dataset is built and developed based on indoors and outdoors actions through a bounded-on-head camera and Xsens for tracking the motions. The key point here to structuring the dataset is utilized to set the sequence of a Deep Neural Network and order an arrangement of frames in the performed task (washing, eating, etc.). As a final point, a 3D modeling of the person suggested at every frame centered with the comparable structure of the first network. More than 120,000 frames constructed the dataset, taken from 7 different people, each one acting out different tasks in diverse indoor and outdoor scenarios. The sequences of every video frame were 3D synchronized and segmented 23 parts.

References

• Alletto, S., Serra, G., Calderara, S., & Cucchiara, R. (2015). Understanding social relationships in egocentric vision. Pattern Recognition, 48(12), 4082-4096. DOI:10.1016/j.patcog.2015.06.006
• Almasi, M. (2018). Investigating the Effect of Head Movement during Running and Its Results in Record Time Using Computer Vision. International Journal of Applied Engineering Research, 13(11), 9433-9436
• Cao, Z., Simon, T., Wei, S., & Sheikh, Y. (2017). Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). DOI:10.1109/cvpr.2017.143
• Chuankun Li, Pichao Wang, Shuang Wang, Yonghong Hou, & Wanqing Li. (2017). Skeleton-based action recognition using LSTM and CNN. 2017 IEEE International Conference on Multimedia & Expo Workshops (ICMEW). DOI:10.1109/icmew.2017.8026287
• Damen, D., Doughty, H., Farinella, G. M., Fidler, S., Furnari, A., Kazakos, E, Wray, M. (2018). Scaling Egocentric Vision: The Dataset Computer Vision – ECCV 2018, 753-771.doi:10.1007/978-3-030-01225-0_44
• Ekvall, S., & Kragic, D. (2006). Learning Task Models from Multiple Human Demonstrations. ROMAN 2006 - The 15th IEEE International Symposium on Robot and Human Interactive Communication. DOI:10.1109/roman.2006.314460
• El-Yacoubi, M. A., He, H., Roualdes, F., Selmi, M., Hariz, M., & Gillet, F. (2015). Vision-based Recognition of Activities by a Humanoid Robot. International Journal of Advanced Robotic Systems, 1. DOI: 10.5772/61819
• Fathi, A., Li, Y., & Rehg, J. M. (2012). Learning to Recognize Daily Actions Using Gaze. Computer Vision – ECCV 2012, 314-327. DOI: 10.1007/978-3-642-33718-5_23
• Hara, K., Kataoka, H., & Satoh, Y. (2018). Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet? 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. DOI:10.1109/cvpr.2018.00685
• Hochreiter, S. & Schmidhuber, Jü. (1997). Long short-term memory. Neural computation, 9, 1735--1780
• Jiang, H., & Grauman, K. (2017). Seeing Invisible Poses: Estimating 3D Body Pose from Egocentric Video. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). DOI:10.1109/cvpr.2017.373
• Li Y., Lan, C., Xing, J., Zeng, W., Yuan, C., & Liu, J. (2016). Online Human Action Detection Using Joint Classification-Regression Recurrent Neural Networks. Computer Vision – ECCV 2016, 203-220. DOI: 10.1007/978-3-319-46478-7_13
• Majd, M., & Safabakhsh, R. (2019). Correlational Convolutional LSTM for human action recognition. Neurocomputing. DOI:10.1016/j.neucom.2018.10.095
• Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. CoRR, abs/1512.03385, 2015.
• Patel, D., & Upadhyay, S. (2013). Optical Flow Measurement using Lucas Kanade Method. International Journal of Computer Applications, 61(10), 6-10. DOI: 10.5120/9962-4611
• Pirsiavash, H., & Ramanan, D. (2012). Detecting activities of daily living in first-person camera views. 2012 IEEE Conference on Computer Vision and Pattern Recognition. DOI:10.1109/cvpr.2012.6248010
• Squartini, S., Hussain, A., & Piazza, F. (n.d.). Preprocessing based solution for the vanishing gradient problem in recurrent neural networks. Proceedings of the 2003 International Symposium on Circuits and Systems, 2003. ISCAS '03. DOI:10.1109/iscas.2003.1206412
• Yuan, Y., & Kitani, K. (2018). 3D Ego-Pose Estimation via Imitation Learning. Computer Vision – ECCV 2018, 763-778. DOI: 10.1007/978-3-030-01270-0_45
• Zhu, L., & Wan, W. (2018). Human Pose Estimation Based on Deep Neural Network. 2018 International Conference on Audio, Language and Image Processing (ICALIP). DOI:10.1109/icalip.2018.8455245