An FPGA-Based Embedded System for Terrain Recognition Using Inertial Measurement Units
Lotfi Madaoui, Malika Kedir-Talha, Oussama Kerdjidj · 2024
Terrains Recognition (TR) using Inertial Measurement Units has received special attention in recent years due to the widespread availability of wearable devices. In this research, we suggested a hardware implementation of a Terrains Recognition system on a Xilinx FPGA platform. The solution employs a lone IMU sensor positioned on the shank and employs an MLP neural network classifier for the categorization of five terrains (Walking, Stair Descent/Ascent, Ramp Descent/Ascent). The hardware architecture of the suggested system underwent optimization through the utilization of parallelism optimization methods such as Unroll, Pipeline and Memory partition. This approach led to a significant improvement in performance, with faster processing speeds.