Follow
Valentin Peretroukhin
Valentin Peretroukhin
Computational Research Scientist, Structura Biotechnology
Verified email at structura.bio - Homepage
Title
Cited by
Cited by
Year
Improving foot-mounted inertial navigation through real-time motion classification
B Wagstaff, V Peretroukhin, J Kelly
2017 International Conference on Indoor Positioning and Indoor Navigation …, 2017
712017
A smooth representation of belief over so (3) for deep rotation learning with uncertainty
V Peretroukhin, M Giamou, DM Rosen, WN Greene, N Roy, J Kelly
arXiv preprint arXiv:2006.01031, 2020
692020
Robust data-driven zero-velocity detection for foot-mounted inertial navigation
B Wagstaff, V Peretroukhin, J Kelly
IEEE Sensors Journal 20 (2), 957-967, 2019
602019
Dpc-net: Deep pose correction for visual localization
V Peretroukhin, J Kelly
IEEE Robotics and Automation Letters 3 (3), 2424-2431, 2017
582017
The battle for filter supremacy: A comparative study of the multi-state constraint kalman filter and the sliding window filter
LE Clement, V Peretroukhin, J Lambert, J Kelly
2015 12th Conference on Computer and Robot Vision, 23-30, 2015
552015
Reducing drift in visual odometry by inferring sun direction using a bayesian convolutional neural network
V Peretroukhin, L Clement, J Kelly
2017 IEEE International Conference on Robotics and Automation (ICRA), 2035-2042, 2017
402017
Certifiably globally optimal extrinsic calibration from per-sensor egomotion
M Giamou, Z Ma, V Peretroukhin, J Kelly
IEEE Robotics and Automation Letters 4 (2), 367-374, 2019
312019
PROBE-GK: Predictive robust estimation using generalized kernels
V Peretroukhin, W Vega-Brown, N Roy, J Kelly
2016 IEEE International Conference on Robotics and Automation (ICRA), 817-824, 2016
292016
PROBE: Predictive robust estimation for visual-inertial navigation
V Peretroukhin, L Clement, M Giamou, J Kelly
2015 IEEE/RSJ International Conference on Intelligent Robots and Systems …, 2015
272015
Self-supervised deep pose corrections for robust visual odometry
B Wagstaff, V Peretroukhin, J Kelly
2020 IEEE International Conference on Robotics and Automation (ICRA), 2331-2337, 2020
252020
Convex iteration for distance-geometric inverse kinematics
M Giamou, F Marić, DM Rosen, V Peretroukhin, N Roy, I Petrović, J Kelly
IEEE Robotics and Automation Letters 7 (2), 1952-1959, 2022
242022
Optimizing camera perspective for stereo visual odometry
V Peretroukhin, J Kelly, TD Barfoot
2014 Canadian Conference on Computer and Robot Vision, 1-7, 2014
182014
Deep Probabilistic Regression of Elements of SO (3) using Quaternion Averaging and Uncertainty Injection.
V Peretroukhin, B Wagstaff, J Kelly
CVPR Workshops, 83-86, 2019
152019
Inferring sun direction to improve visual odometry: A deep learning approach
V Peretroukhin, L Clement, J Kelly
The International Journal of Robotics Research 37 (9), 996-1016, 2018
142018
Probabilistic regression of rotations using quaternion averaging and a deep multi-headed network
V Peretroukhin, B Wagstaff, M Giamou, J Kelly
arXiv preprint arXiv:1904.03182, 2019
132019
Improving the accuracy of stereo visual odometry using visual illumination estimation
L Clement, V Peretroukhin, J Kelly
2016 International Symposium on Experimental Robotics, 409-419, 2017
92017
Towards autonomous mobile robots for the exploration of steep terrain
B Stenning, L Bajin, C Robson, V Peretroukhin, GR Osinski, TD Barfoot
Field and Service Robotics: Results of the 9th International Conference, 33-47, 2015
82015
On the coupling of depth and egomotion networks for self-supervised structure from motion
B Wagstaff, V Peretroukhin, J Kelly
IEEE Robotics and Automation Letters 7 (3), 6766-6773, 2022
72022
Toward robust and efficient online adaptation for deep stereo depth estimation
M Knowles, V Peretroukhin, WN Greene, N Roy
2021 IEEE International Conference on Robotics and Automation (ICRA), 12192 …, 2021
52021
Self-supervised structure-from-motion through tightly-coupled depth and egomotion networks
B Wagstaff, V Peretroukhin, J Kelly
arXiv preprint arXiv:2106.04007 7, 2021
22021
The system can't perform the operation now. Try again later.
Articles 1–20