Extracting motion velocities from 3D image sequences and coupled spatio-temporal smoothing

2003 ◽  
Author(s):  
Tobias Preusser ◽  
Martin Rumpf
Keyword(s):  
Image Sequences ◽  
3D Image ◽  
Temporal Smoothing ◽  
Spatio Temporal

scholarly journals A Recurrent Deep Network for Estimating the Pose of Real Indoor Images from Synthetic Image Sequences

Sensors ◽  
2020 ◽  
Vol 20 (19) ◽  
pp. 5492
Author(s):  
Debaditya Acharya ◽  
Sesa Singha Roy ◽  
Kourosh Khoshelham ◽  
Stephan Winter
Keyword(s):  
Image Sequences ◽  
Synthetic Image ◽  
3D Image ◽  
Deep Convolutional Neural Networks ◽  
Building Information Model ◽  
Building Information ◽  
Spatio Temporal ◽  
Indoor Spaces ◽  
Inter Frame ◽  
Achievable Accuracy

Recently, deep convolutional neural networks (CNN) have become popular for indoor visual localisation, where the networks learn to regress the camera pose from images directly. However, these approaches perform a 3D image-based reconstruction of the indoor spaces beforehand to determine camera poses, which is a challenge for large indoor spaces. Synthetic images derived from 3D indoor models have been used to eliminate the requirement of 3D reconstruction. A limitation of the approach is the low accuracy that occurs as a result of estimating the pose of each image frame independently. In this article, a visual localisation approach is proposed that exploits the spatio-temporal information from synthetic image sequences to improve localisation accuracy. A deep Bayesian recurrent CNN is fine-tuned using synthetic image sequences obtained from a building information model (BIM) to regress the pose of real image sequences. The results of the experiments indicate that the proposed approach estimates a smoother trajectory with smaller inter-frame error as compared to existing methods. The achievable accuracy with the proposed approach is 1.6 m, which is an improvement of approximately thirty per cent compared to the existing approaches. A Keras implementation can be found in our Github repository.

Sign in / Sign up

Export Citation Format

Share Document