Fast Object Detection with a Machine Learning Edge Device

TL;DR

This study demonstrates that using Google's Edge TPU significantly reduces inference time and power consumption for object detection on embedded systems, enabling real-time autonomous robot applications.

Contribution

It provides a comparative analysis of CPU, GPU, and TPU performance for object detection, highlighting the Edge TPU's superior speed and efficiency for embedded machine learning.

Findings

Edge TPU reduces inference time by 87.5% compared to CPU

TPU inference time is 25% faster than GPU

Monocular versus stereo vision had no significant impact on performance

Abstract

This machine learning study investigates a lowcost edge device integrated with an embedded system having computer vision and resulting in an improved performance in inferencing time and precision of object detection and classification. A primary aim of this study focused on reducing inferencing time and low-power consumption and to enable an embedded device of a competition-ready autonomous humanoid robot and to support real-time object recognition, scene understanding, visual navigation, motion planning, and autonomous navigation of the robot. This study compares processors for inferencing time performance between a central processing unit (CPU), a graphical processing unit (GPU), and a tensor processing unit (TPU). CPUs, GPUs, and TPUs are all processors that can be used for machine learning tasks. Related to the aim of supporting an autonomous humanoid robot, there was an additional effort to observe whether or not there was a significant difference in using a camera having monocular vision versus stereo vision capability. TPU inference time results for this study reflect a 25% reduction in time over the GPU, and a whopping 87.5% reduction in inference time compared to the CPU. Much information in this paper is contributed to the final selection of Google's Coral brand, Edge TPU device. The Arduino Nano 33 BLE Sense Tiny ML Kit was also considered for comparison but due to initial incompatibilities and in the interest of time to complete this study, a decision was made to review the kit in a future experiment.