Evaluation of Feature Detectors for KLT based Feature Tracking using the Odroid U3

Australian Robotics and Automation Association
Publication Type:
Conference Proceeding
Issue Date:
Full metadata record
Files in This Item:
Filename Description Size
Thumbnailacra_2014.pdfAccepted Manuscript version2.66 MB
Adobe PDF
Feature tracking is an integral part of most vision-based state estimation frameworks. However, tracking features at a sufficient frame rate is a challenging task for mobile robots such as Micro Aerial Vehicles (MAVs) due to their fast dynamics and limited on-board computing resources. Recent developments in smartphone processors have led to embedded computing platforms that are ideal on-board computers for MAV state estimation. This paper analyses the performance of a Kanade-Lucas-Thomasi (KLT) based feature tracker on a state-of-the-art embedded computing platform suitable for on-board MAV state estimation. It compares the performance of different implementations of the feature tracker using four different low-complexity feature detectors. The experimental results presented herein may serve as guidelines for the selection of a feature detector, image resolution, framerate and feature quantity when developing on-board feature tracking systems based on ARM Cortex-A9 embedded computers.
Please use this identifier to cite or link to this item: