CNN-based Visual Ego-Motion Estimation for Fast MAV Maneuvers

01/06/2021
by   Yingfu Xu, et al.
8

In the field of visual ego-motion estimation for Micro Air Vehicles (MAVs), fast maneuvers stay challenging mainly because of the big visual disparity and motion blur. In the pursuit of higher robustness, we study convolutional neural networks (CNNs) that predict the relative pose between subsequent images from a fast-moving monocular camera facing a planar scene. Aided by the Inertial Measurement Unit (IMU), we mainly focus on the translational motion. The networks we study have similar small model sizes (around 1.35MB) and high inference speeds (around 100Hz on a mobile GPU). Images for training and testing have realistic motion blur. Departing from a network framework that iteratively warps the first image to match the second with cascaded network blocks, we study different network architectures and training strategies. Simulated datasets and MAV flight datasets are used for evaluation. The proposed setup shows better accuracy over existing networks and traditional feature-point-based methods during fast maneuvers. Moreover, self-supervised learning outperforms supervised learning. The code developed for this paper will be open-source upon publication at https://github.com/tudelft/.

READ FULL TEXT

page 1

page 3

page 8

page 9

research
10/01/2018

Inertial-aided Motion Deblurring with Deep Networks

We propose an inertial-aided deblurring method that incorporates gyrosco...
research
08/30/2022

CUAHN-VIO: Content-and-Uncertainty-Aware Homography Network for Visual-Inertial Odometry

Learning-based visual ego-motion estimation is promising yet not ready f...
research
06/28/2022

SSL-Lanes: Self-Supervised Learning for Motion Forecasting in Autonomous Driving

Self-supervised learning (SSL) is an emerging technique that has been su...
research
05/22/2018

Fast Motion Deblurring for Feature Detection and Matching Using Inertial Measurements

Many computer vision and image processing applications rely on local fea...
research
02/25/2019

Beyond Photometric Loss for Self-Supervised Ego-Motion Estimation

Accurate relative pose is one of the key components in visual odometry (...
research
01/16/2018

Reblur2Deblur: Deblurring Videos via Self-Supervised Learning

Motion blur is a fundamental problem in computer vision as it impacts im...
research
03/23/2023

Mobile MoCap: Retroreflector Localization On-The-Go

Motion capture (MoCap) through tracking retroreflectors obtains high pre...

Please sign up or login with your details

Forgot password? Click here to reset