IDNet: Smartphone-based gait recognition with convolutional neural networks

• Published in: Pattern recognition Vol. 74; pp. 25 - 37
• Main Authors: Gadaleta, Matteo, Rossi, Michele
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.02.2018
• Subjects: Accelerometer; Biometric gait analysis; Classification methods; Convolutional neural networks; Feature extraction; Gyroscope; Inertial sensors; Signal processing; Support vector machines; Target recognition; Support vector machines; Target recognition; Inertial sensors; Signal processing; Accelerometer; Biometric gait analysis; Feature extraction; Gyroscope; Convolutional neural networks; Classification methods
• ISSN: 0031-3203; 1873-5142
• DOI: 10.1016/j.patcog.2017.09.005

•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. 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.