Efficient Optical flow and Stereo Vision for Velocity Estimation and Obstacle Avoidance on an Autonomous Pocket Drone

TL;DR

This paper introduces Edge-FS, an efficient computer vision algorithm that enables a tiny drone to estimate velocity and depth in real-time using minimal hardware, facilitating autonomous navigation and obstacle avoidance.

Contribution

The paper presents a novel, lightweight algorithm that runs at 20 Hz on a microcontroller, allowing miniature drones to perform autonomous flight using only onboard sensors.

Findings

Runs at 20 Hz on 4 g stereo camera with embedded microcontroller

Enables fully autonomous flight with obstacle avoidance

Uses feature histograms for optical flow and stereo disparity estimation

Abstract

Miniature Micro Aerial Vehicles (MAV) are very suitable for flying in indoor environments, but autonomous navigation is challenging due to their strict hardware limitations. This paper presents a highly efficient computer vision algorithm called Edge-FS for the determination of velocity and depth. It runs at 20 Hz on a 4 g stereo camera with an embedded STM32F4 microprocessor (168 MHz, 192 kB) and uses feature histograms to calculate optical flow and stereo disparity. The stereo-based distance estimates are used to scale the optical flow in order to retrieve the drone's velocity. The velocity and depth measurements are used for fully autonomous flight of a 40 g pocket drone only relying on on-board sensors. The method allows the MAV to control its velocity and avoid obstacles.