Real-time and Autonomous Detection of Helipad for Landing Quad-Rotors by Visual Servoing

TL;DR

This paper presents a real-time, machine-learning-free method for autonomous helipad detection and landing of quad-rotors using image tracking and a modified IBVS technique tailored for four degrees-of-freedom.

Contribution

It introduces a novel real-time detection and tracking approach combined with a customized visual servoing method for quad-rotor landing.

Findings

Successful real-time helipad detection without machine learning

Effective quad-rotor landing with orientation control

Reduced computational requirements through image tracking

Abstract

In this paper, we first present a method to autonomously detect helipads in real time. Our method does not rely on any machine-learning methods and as such is applicable in real-time on the computational capabilities of an average quad-rotor. After initial detection, we use image tracking methods to reduce the computational resource requirement further. Once the tracking starts our modified IBVS(Image-Based Visual Servoing) method starts publishing velocity to guide the quad-rotor onto the helipad. The modified IBVS scheme is designed for the four degrees-of-freedom of a quad-rotor and can land the quad-rotor in a specific orientation.