Home
People
Projects
Publications
Blog
Contact
Home
Projects
Project Page
Machine Learning for Visual Wheelchair Corridor following task.
In this project, we present a novel GP-based visual controller. The HOG features are used as a global representation of the observed image. The Gaussian Processes (GP) algorithm is trained to learn the mapping from the HOG feature vector onto the velocity variables. The GP training is achieved using corridor images collected from different places, these images are labeled using velocity values generated by a geometric-based control law and robust features. A hand-based verification of the features is done to ensure the accuracy of the ground truth labels.Experiments were conducted to explore the capabilities of the developed approach. Results have shown R Squared metric with more than ninety percent on the trained GP model in noisy conditions.
Hafez, AH Abdul, Ammar Tello and Bakr Sarakbi. "Real-time GP-based Wheelchair Corridor Following." 2021 29th Signal Processing and Communications Applications Conference (SIU). IEEE, 2021.
News
Our Papers named "Image based Wheelchair Corridor Following" Has been submitted to RAS Journal
Nov 2021
Our paper titled "Real-time GP-based Wheelchair Corridor Following" has been accepted for publication in the IEEE International conference on Signal Processing and Communication Applications, IEEE SIU 2021
Jan 2021
Our paper titled "Dynamic Time Warping of Deep Features for Place Recognition in Visually Varying Conditions" has been published by the Arabian Journal for Science and Engineering, January 2021. https://doi.org/10.1007/s13369-020-05146-6
Jan 2021