Next Article in Journal
Field Test of Excess Pore Water Pressure at Pile–Soil Interface Caused by PHC Pipe Pile Penetration Based on Silicon Piezoresistive Sensor
Previous Article in Journal
A Fuzzy Analytic Hierarchy Process and Cooperative Game Theory Combined Multiple Mobile Robot Navigation Algorithm
Open AccessArticle

Real-Time Energy Efficient Hand Pose Estimation: A Case Study

1
Microelectronic Systems Design Research Group, Department of Electrical and Computer Engineering, Technische Universität Kaiserslautern, 67663 Kaiserslautern, Germany
2
German Research Center for Artificial Intelligence, DFKI, 67663 Kaiserslautern, Germany
3
Department of Informatics, Technische Universität Kaiserslautern, 67663 Kaiserslautern, Germany
4
School of Electrical Engineering and Computer Science (SEECS), National University of Sciences and Technology (NUST), Islamabad 44000, Pakistan
*
Author to whom correspondence should be addressed.
Sensors 2020, 20(10), 2828; https://doi.org/10.3390/s20102828
Received: 14 February 2020 / Revised: 4 May 2020 / Accepted: 12 May 2020 / Published: 16 May 2020
(This article belongs to the Section Intelligent Sensors)
The estimation of human hand pose has become the basis for many vital applications where the user depends mainly on the hand pose as a system input. Virtual reality (VR) headset, shadow dexterous hand and in-air signature verification are a few examples of applications that require to track the hand movements in real-time. The state-of-the-art 3D hand pose estimation methods are based on the Convolutional Neural Network (CNN). These methods are implemented on Graphics Processing Units (GPUs) mainly due to their extensive computational requirements. However, GPUs are not suitable for the practical application scenarios, where the low power consumption is crucial. Furthermore, the difficulty of embedding a bulky GPU into a small device prevents the portability of such applications on mobile devices. The goal of this work is to provide an energy efficient solution for an existing depth camera based hand pose estimation algorithm. First, we compress the deep neural network model by applying the dynamic quantization techniques on different layers to achieve maximum compression without compromising accuracy. Afterwards, we design a custom hardware architecture. For our device we selected the FPGA as a target platform because FPGAs provide high energy efficiency and can be integrated in portable devices. Our solution implemented on Xilinx UltraScale+ MPSoC FPGA is 4.2× faster and 577.3× more energy efficient than the original implementation of the hand pose estimation algorithm on NVIDIA GeForce GTX 1070. View Full-Text
Keywords: hardware architecture; FPGA; Zynq; UltraScale+; HLS; PyTorch; CNN; deep learning; hand pose estimation hardware architecture; FPGA; Zynq; UltraScale+; HLS; PyTorch; CNN; deep learning; hand pose estimation
Show Figures

Figure 1

MDPI and ACS Style

Al Koutayni, M.R.; Rybalkin, V.; Malik, J.; Elhayek, A.; Weis, C.; Reis, G.; Wehn, N.; Stricker, D. Real-Time Energy Efficient Hand Pose Estimation: A Case Study. Sensors 2020, 20, 2828.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop