PMID- 30990417
OWN - NLM
STAT- PubMed-not-MEDLINE
DCOM- 20210212
LR  - 20210212
IS  - 1939-3539 (Electronic)
IS  - 0098-5589 (Linking)
VI  - 42
IP  - 10
DP  - 2020 Oct
TI  - Unsupervised Deep Visual-Inertial Odometry with Online Error Correction for RGB-D 
      Imagery.
PG  - 2478-2493
LID - 10.1109/TPAMI.2019.2909895 [doi]
AB  - While numerous deep approaches to the problem of vision-aided localization have 
      been recently proposed, systems operating in the real world will undoubtedly 
      experience novel sensory states previously unseen even under the most prodigious 
      training regimens. We address the localization problem with online error 
      correction (OEC) modules that are trained to correct a vision-aided localization 
      network's mistakes. We demonstrate the generalizability of the OEC modules and 
      describe our unsupervised deep neural network approach to the fusion of RGB-D 
      imagery with inertial measurements for absolute trajectory estimation. Our 
      network, dubbed the Visual-Inertial-Odometry Learner (VIOLearner), learns to 
      perform visual-inertial odometry (VIO) without inertial measurement unit (IMU) 
      intrinsic parameters or the extrinsic calibration between an IMU and camera. The 
      network learns to integrate IMU measurements and generate hypothesis trajectories 
      which are then corrected online according to the Jacobians of scaled image 
      projection errors with respect to spatial grids of pixel coordinates. We evaluate 
      our network against state-of-the-art (SoA) VIO, visual odometry (VO), and visual 
      simultaneous localization and mapping (VSLAM) approaches on the KITTI Odometry 
      dataset as well as a micro aerial vehicle (MAV) dataset that we collected in the 
      AirSim simulation environment. We demonstrate better than SoA translational 
      localization performance against comparable SoA approaches on our evaluation 
      sequences.
FAU - Shamwell, E Jared
AU  - Shamwell EJ
FAU - Lindgren, Kyle
AU  - Lindgren K
FAU - Leung, Sarah
AU  - Leung S
FAU - Nothwang, William D
AU  - Nothwang WD
LA  - eng
PT  - Journal Article
DEP - 20190415
PL  - United States
TA  - IEEE Trans Pattern Anal Mach Intell
JT  - IEEE transactions on pattern analysis and machine intelligence
JID - 9885960
SB  - IM
EDAT- 2019/04/17 06:00
MHDA- 2019/04/17 06:01
CRDT- 2019/04/17 06:00
PHST- 2019/04/17 06:00 [pubmed]
PHST- 2019/04/17 06:01 [medline]
PHST- 2019/04/17 06:00 [entrez]
AID - 10.1109/TPAMI.2019.2909895 [doi]
PST - ppublish
SO  - IEEE Trans Pattern Anal Mach Intell. 2020 Oct;42(10):2478-2493. doi: 
      10.1109/TPAMI.2019.2909895. Epub 2019 Apr 15.