DronePose: The identification, segmentation, and orientation detection of drones via neural networks

TL;DR

DronePose employs a neural network with decision trees to identify, segment, and determine the orientation of drones in flight, enhancing air-space monitoring capabilities with detailed drone characterization.

Contribution

The paper introduces a novel CNN-based system that combines decision trees and ensemble methods for comprehensive drone identification, segmentation, and orientation detection.

Findings

Accurately classifies drone types in real-time

Effectively segments drone body parts in images

Generates high-fidelity training data for system training

Abstract

The growing ubiquity of drones has raised concerns over the ability of traditional air-space monitoring technologies to accurately characterise such vehicles. Here, we present a CNN using a decision tree and ensemble structure to fully characterise drones in flight. Our system determines the drone type, orientation (in terms of pitch, roll, and yaw), and performs segmentation to classify different body parts (engines, body, and camera). We also provide a computer model for the rapid generation of large quantities of accurately labelled photo-realistic training data and demonstrate that this data is of sufficient fidelity to allow the system to accurately characterise real drones in flight. Our network will provide a valuable tool in the image processing chain where it may build upon existing drone detection technologies to provide complete drone characterisation over wide areas.