Abstract
Person re-identification (re-ID) is among the essential components that play an integral role in constituting an automated surveillance environment. Majorly, the problem is tackled using data acquired from vision sensors using appearance-based features, which are strongly dependent on visual cues such as color, texture, etc., consequently limiting the precise re-identification of an individual. To overcome such strong dependence on visual features, many researchers have tackled the re-identification problem using human gait, which is believed to be unique and provide a distinctive biometric signature that is particularly suitable for re-ID in uncontrolled environments. However, image-based gait analysis often fails to extract quality measurements of an individual’s motion patterns owing to problems related to variations in viewpoint, illumination (daylight), clothing, worn accessories, etc. To this end, in contrast to relying on image-based motion measurement, this paper demonstrates the potential to re-identify an individual using inertial measurements units (IMU) based on two common sensors, namely gyroscope and accelerometer. The experiment was carried out over data acquired using smartphones and wearable IMUs from a total of 86 randomly selected individuals including 49 males and 37 females between the ages of 17 and 72 years. The data signals were first segmented into single steps and strides, which were separately fed to train a sequential deep recurrent neural network to capture implicit arbitrary long-term temporal dependencies. The experimental setup was devised in a fashion to train the network on all the subjects using data related to half of the step and stride sequences only while the inference was performed on the remaining half for the purpose of re-identification. The obtained experimental results demonstrate the potential to reliably and accurately re-identify an individual based on one’s inertial sensor data.
Highlights
Person re-identification is an important and active research area with potential applications in the field of automated surveillance/monitoring, robotics, human–computer interaction, and digital forensics
This paper demonstrates the potential of re-identification of an individual by using inertial measurements units (IMU) based on two common sensors, namely gyroscope and accelerometer
In-depth analysis of previous research has shown that Re-id is an important area that has been well explored, various challenges in the vision-based method limit the potential of the application. This research addressed this problem through the usage of inertial sensors for analysis of human gait and we propose human gait as a suitable candidate for person re-identification
Summary
Person re-identification (re-ID) is an important and active research area with potential applications in the field of automated surveillance/monitoring, robotics, human–computer interaction, and digital forensics. Sequential modeling using deep neural networks is mainly performed using RNNs. The architecture of RNNs is similar to traditional multilayer perceptrons except that they include feedback loops, which means that output of the network is fed back together with the input. Similar to conventional deep neural network architectures, they suffer from the gradient vanishing problem [51], especially when the input sequences are long. In such scenarios, the use of RNNs potentially poses such an issue where the back propagated gradients, which are used to update the weights of the neural network, become too small during the backpropagation process and no longer contribute in learning
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
