IDNet: Smartphone-based Gait Recognition with Convolutional Neural Networks

Abstract

Here, we present IDNet, a user authentication framework from smartphone-acquired motion signals. Its goal is to recognize a target user from their way of walking, using the accelerometer and gyroscope (inertial) signals provided by a commercial smartphone worn in the front pocket of the user's trousers. IDNet features several innovations including: i) a robust and smartphone-orientation-independent walking cycle extraction block, ii) a novel feature extractor based on convolutional neural networks, iii) a one-class support vector machine to classify walking cycles, and the coherent integration of these into iv) a multi-stage authentication technique. IDNet is the first system that exploits a deep learning approach as universal feature extractors for gait recognition, and that combines classification results from subsequent walking cycles into a multi-stage decision making framework. Experimental results show the superiority of our approach against state-of-the-art techniques, leading to misclassification rates (either false negatives or positives) smaller than 0.15% with fewer than five walking cycles. Design choices are discussed and motivated throughout, assessing their impact on the user authentication performance.

Cited by in corpus (12)

• DeepSense: A Unified Deep Learning Framework for Time-Series Mobile Sensing Data Processing
• Deep Learning-Based Gait Recognition Using Smartphones in the Wild
• DeepWalking: Enabling Smartphone-based Walking Speed Estimation Using Deep Learning
• Similarity Embedding Networks for Robust Human Activity Recognition
• Human Gait Database for Normal Walk Collected by Smartphone Accelerometer
• Mobile Traffic Classification through Physical Channel Fingerprinting: a Deep Learning Approach
• Seq2Seq RNN based Gait Anomaly Detection from Smartphone Acquired Multimodal Motion Data
• Classification of Pathological and Normal Gait: A Survey
• A Framework for Behavioral Biometric Authentication using Deep Metric Learning on Mobile Devices
• Security and Privacy Enhanced Gait Authentication with Random Representation Learning and Digital Lockers
• Binarized Neural Networks for Resource-Constrained On-Device Gait Identification
• Rotation-Invariant Gait Identification with Quaternion Convolutional Neural Networks