Hand Orientation Estimation in Probability Density Form

Hand orientation is an essential feature required to understand hand behaviors and subsequently support human activities. In this paper, we present a new method for estimating hand orientation in probability density form. It can solve the cyclicity problem in direct angular representation and enables the integration of multiple predictions based on different features. We validated the performance of the proposed method and an integration example using our dataset, which captured cooperative group work.

[1]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[2]  Xiaogang Wang,et al.  Pyramid Scene Parsing Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Yang Liu,et al.  OrieNet: A Regression System for Latent Fingerprint Orientation Field Extraction , 2018, ICANN.

[4]  Christoph Busch,et al.  ConvNet Regression for Fingerprint Orientations , 2017, SCIA.

[5]  Marios Savvides,et al.  Robust Hand Detection and Classification in Vehicles and in the Wild , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[6]  Stefan Lee,et al.  Lending A Hand: Detecting Hands and Recognizing Activities in Complex Egocentric Interactions , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[7]  Yinda Zhang,et al.  Joint Hand Detection and Rotation Estimation by Using CNN , 2016, ArXiv.

[8]  Yang Zhang,et al.  A Light CNN based Method for Hand Detection and Orientation Estimation , 2018, 2018 24th International Conference on Pattern Recognition (ICPR).

[9]  Stefan Lee,et al.  This Hand Is My Hand: A Probabilistic Approach to Hand Disambiguation in Egocentric Video , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[10]  Andrew Zisserman,et al.  Hand detection using multiple proposals , 2011, BMVC.