Premium
Two‐stage 3D model‐based UAV pose estimation: A comparison of methods for optimization
Author(s) -
Pessanha Santos Nuno,
Lobo Victor,
Bernardino Alexandre
Publication year - 2020
Publication title -
journal of field robotics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.152
H-Index - 96
eISSN - 1556-4967
pISSN - 1556-4959
DOI - 10.1002/rob.21933
Subject(s) - computer science , particle swarm optimization , artificial intelligence , particle filter , pose , classifier (uml) , genetic algorithm , pattern recognition (psychology) , data mining , machine learning , kalman filter
Abstract Particle Filters (PFs) have been successfully used in three‐dimensional (3D) model‐based pose estimation. Typically, these filters depend on the computation of importance weights that use similarity metrics as a proxy to approximate the likelihood function. In this paper, we explore the use of a two‐stage 3D model‐based approach based on a PF for single‐frame pose estimation. First, we use a classifier trained in a synthetic data set for Unmanned Aerial Vehicle (UAV) detection and a pretrained database indexed by bounding boxes properties to obtain an initial rough pose estimate. Second, we employ optimization algorithms to optimize the used similarity metrics and decrease the obtained error. We have tested four different algorithms: (a) Particle Filter Optimization (PFO), (b) Particle Swarm Optimization (PSO), (c) modified PSO, and (d) an approach based on the evolution strategies present in the genetic algorithms named Genetic Algorithm‐based Framework (GAbF). To check the quality of the estimate on each iteration, we have tested several similarity metrics (color, edge, and mask‐based) based on the UAV Computer‐Aided Design (CAD) model. The framework is applied to the outdoor pose estimation of a fixed‐wing UAV for autonomous landing in a Fast Patrol Boat (FPB). We extend our previous approach by adopting a better problem formulation, using Deep Neural Networks (DNNs) for UAV detection, making the comparison between the used similarity metrics, comparing pose optimization schemes, and showing new results. The future work will focus on the inclusion of this scheme in a tracking architecture to increase the accuracy of the result between observations.