IDNet: Smartphone-based gait recognition with convolutional neural networks
作者：
Highlights：
• A deep-learning based authentication system from inertial signals is proposed.
• This framework relies on new transform to make inertial signals rotation invariant.
• We propose a robust walking-cycle extraction algorithm with template adaptation.
• We combine neural networks with SVM into a new multi-step authentication technique.
• An extensive experimental campaign is presented, to validate the proposed system.
摘要
•A deep-learning based authentication system from inertial signals is proposed.•This framework relies on new transform to make inertial signals rotation invariant.•We propose a robust walking-cycle extraction algorithm with template adaptation.•We combine neural networks with SVM into a new multi-step authentication technique.•An extensive experimental campaign is presented, to validate the proposed system.
论文关键词：Biometric gait analysis,Target recognition,Classification methods,Convolutional neural networks,Support vector machines,Inertial sensors,Feature extraction,Signal processing,Accelerometer,Gyroscope
论文评审过程：Received 19 October 2016, Revised 14 June 2017, Accepted 5 September 2017, Available online 6 September 2017, Version of Record 15 September 2017.
论文官网地址：https://doi.org/10.1016/j.patcog.2017.09.005
