Abstract
In the field of pedestrian dead reckoning (PDR), the zero velocity update (ZUPT) method with an inertial measurement unit (IMU) is a mature technology to calibrate dead reckoning. However, due to the complex walking modes of different individuals, it is essential and challenging to determine the ZUPT conditions, which has a direct and significant influence on the tracking accuracy. In this research, we adopted an adaptive zero velocity update (AZUPT) method based on convolution neural networks to classify the ZUPT conditions. The AZUPT model was robust regardless of the different motion types of various individuals. AZUPT was then implemented on the Zynq-7000 SoC platform to work in real time to validate its computational efficiency and performance superiority. Extensive real-world experiments were conducted by 60 different individuals in three different scenarios. It was demonstrated that the proposed system could work equally well in different environments, making it portable for PDR to be widely performed in various real-world situations.
Highlights
There is great demand for precise navigation systems for pedestrians in both indoor and outdoor environments [1,2]
We proposed a method based on convolution neural networks (CNNs), which could adaptively pick zero velocity update (ZUPT) points from different motion types of different pedestrians
Adaptive ZUPT points’ selection: We proposed a method based on convolutional neural networks (CNNs), which could adaptively pick ZUPT points from different motion types of different pedestrians; Sensors 2021, 21, 3808
Summary
There is great demand for precise navigation systems for pedestrians in both indoor and outdoor environments [1,2]. The stance phases (ZUPT points) of each gait cycle play an important role in the reckoning of the long-term trajectory, so they have to be detected accurately [13] (details shown on the first page). This paper adopted a deep neural network to solve this long-standing problem in ZUPT, which was the adaptive zero velocity update (AZUPT) [14] model, to determine moments when ZUPT should be conducted. Adaptive ZUPT points’ selection: We proposed a method based on convolutional neural networks (CNNs), which could adaptively pick ZUPT points from different motion types of different pedestrians (e.g., walking, fast walking, and running); Sensors 2021, 21, 3808.
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.
