Guided Feature Selection for Deep Visual Odometry

11/25/2018
by   Fei Xue, et al.
0

We present a novel end-to-end visual odometry architecture with guided feature selection based on deep convolutional recurrent neural networks. Different from current monocular visual odometry methods, our approach is established on the intuition that features contribute discriminately to different motion patterns. Specifically, we propose a dual-branch recurrent network to learn the rotation and translation separately by leveraging current Convolutional Neural Network (CNN) for feature representation and Recurrent Neural Network (RNN) for image sequence reasoning. To enhance the ability of feature selection, we further introduce an effective context-aware guidance mechanism to force each branch to distill related information for specific motion pattern explicitly. Experiments demonstrate that on the prevalent KITTI and ICL_NUIM benchmarks, our method outperforms current state-of-the-art model- and learning-based methods for both decoupled and joint camera pose recovery.

READ FULL TEXT
research
05/20/2021

DeepAVO: Efficient Pose Refining with Feature Distilling for Deep Visual Odometry

The technology for Visual Odometry (VO) that estimates the position and ...
research
09/25/2017

DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks

This paper studies monocular visual odometry (VO) problem. Most of exist...
research
11/29/2018

Visual SLAM with Network Uncertainty Informed Feature Selection

In order to facilitate long-term localization using a visual simultaneou...
research
10/13/2020

Map-Based Temporally Consistent Geolocalization through Learning Motion Trajectories

In this paper, we propose a novel trajectory learning method that exploi...
research
03/03/2019

Understanding Feature Selection and Feature Memorization in Recurrent Neural Networks

In this paper, we propose a test, called Flagged-1-Bit (F1B) test, to st...
research
04/17/2019

DistanceNet: Estimating Traveled Distance from Monocular Images using a Recurrent Convolutional Neural Network

Classical monocular vSLAM/VO methods suffer from the scale ambiguity pro...
research
06/19/2019

PoseConvGRU: A Monocular Approach for Visual Ego-motion Estimation by Learning

While many visual ego-motion algorithm variants have been proposed in th...

Please sign up or login with your details

Forgot password? Click here to reset