Development of an Electronic Shift Lever Control System Using Hand Pose Recognition

In this paper, we introduce an electronic shift lever control system based on hand pose recognition technology to provide a convenient and simple interface to drivers. The hand pose recognition algorithm consists of three processes. The first is hand localization using a simple approach based on deep learning. The second step is the prediction of the 3D hand joint location, and the final step is hand pose recognition. During this process, we define six hand poses and extract feature vectors obtained using the 3D offset from the center of the hand location to the hand joint location. The hand pose is then recognized using a simple KNN classifier.

[1]  Kyoung Mu Lee,et al.  V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[2]  Tae-Kyun Kim,et al.  Latent Regression Forest: Structured Estimation of 3D Articulated Hand Posture , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Jia Deng,et al.  Stacked Hourglass Networks for Human Pose Estimation , 2016, ECCV.

[4]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[5]  Vincent Lepetit,et al.  Hands Deep in Deep Learning for Hand Pose Estimation , 2015, ArXiv.

[6]  Vincent Lepetit,et al.  DeepPrior++: Improving Fast and Accurate 3D Hand Pose Estimation , 2017, 2017 IEEE International Conference on Computer Vision Workshops (ICCVW).