scholarly journals Exploiting Attitude Sensing in Vision-Based Navigation for an Airship

2009 ◽  
Vol 2009 ◽  
pp. 1-16 ◽  
Author(s):  
Luiz G. B. Mirisola ◽  
Jorge Dias
Keyword(s):  
Ground Plane ◽  
Translational Motion ◽  
Ground Truth ◽  
Visual Odometry ◽  
Magnetic Sensors ◽  
Controlled Environment ◽  
Translation Model ◽  
Graph Optimization ◽  
Vision Based Navigation ◽  
Previous Image

An Attitude Heading Reference System (AHRS) is used to compensate for rotational motion, facilitating vision-based navigation above smooth terrain by generating virtual images to simulate pure translation movement. The AHRS combines inertial and earth field magnetic sensors to provide absolute orientation measurements, and our recently developed calibration routine determines the rotation between the frames of reference of the AHRS and the monocular camera. In this way, the rotation is compensated, and the remaining translational motion is recovered by directly finding a rigid transformation to register corresponding scene coordinates. With a horizontal ground plane, the pure translation model performs more accurately than image-only approaches, and this is evidenced by recovering the trajectory of our airship UAV and comparing with GPS data. Visual odometry is also fused with the GPS, and ground plane maps are generated from the estimated vehicle poses and used to evaluate the results. Finally, loop closure is detected by looking for a previous image of the same area, and an open source SLAM package based in 3D graph optimization is employed to correct the visual odometry drift. The accuracy of the height estimation is also evaluated against ground truth in a controlled environment.

scholarly journals Real-Time Vehicle Positioning and Mapping Using Graph Optimization

Sensors ◽  
2021 ◽  
Vol 21 (8) ◽  
pp. 2815
Author(s):  
Anweshan Das ◽  
Jos Elfring ◽  
Gijs Dubbelman
Keyword(s):  
Real Time ◽  
Rural Areas ◽  
Low Cost ◽  
Ground Truth ◽  
Visual Odometry ◽  
Graph Optimization ◽  
Urban And Rural Areas ◽  
Vehicle Positioning ◽  
Rate Sensor ◽  
Pose Graph Optimization

In this work, we propose and evaluate a pose-graph optimization-based real-time multi-sensor fusion framework for vehicle positioning using low-cost automotive-grade sensors. Pose-graphs can model multiple absolute and relative vehicle positioning sensor measurements and can be optimized using nonlinear techniques. We model pose-graphs using measurements from a precise stereo camera-based visual odometry system, a robust odometry system using the in-vehicle velocity and yaw-rate sensor, and an automotive-grade GNSS receiver. Our evaluation is based on a dataset with 180 km of vehicle trajectories recorded in highway, urban, and rural areas, accompanied by postprocessed Real-Time Kinematic GNSS as ground truth. We compare the architecture’s performance with (i) vehicle odometry and GNSS fusion and (ii) stereo visual odometry, vehicle odometry, and GNSS fusion; for offline and real-time optimization strategies. The results exhibit a 20.86% reduction in the localization error’s standard deviation and a significant reduction in outliers when compared with automotive-grade GNSS receivers.

Spatiotemporal visual odometry using ground plane in dynamic indoor environment

Optik ◽  
2020 ◽  
Vol 220 ◽  
pp. 165165
Author(s):  
Zaixing He ◽  
Qinfeng Yang ◽  
Xinyue Zhao ◽  
Shuyou Zhang ◽  
Jianrong Tan
Keyword(s):  
Indoor Environment ◽  
Ground Plane ◽  
Visual Odometry

scholarly journals Comparison of Three Off-the-Shelf Visual Odometry Systems

Robotics ◽  
2020 ◽  
Vol 9 (3) ◽  
pp. 56 ◽  
Author(s):  
Alexandre Alapetite ◽  
Zhongyu Wang ◽  
John Paulin Hansen ◽  
Marcin Zajączkowski ◽  
Mikołaj Patalan
Keyword(s):  
Ground Truth ◽  
Visual Odometry ◽  
Measurement Unit ◽  
Positioning System ◽  
Fully Integrated ◽  
Global Positioning ◽  
Comparable Performance ◽  
Robot Position ◽  
Visual Clues ◽  
Better Than

Positioning is an essential aspect of robot navigation, and visual odometry an important technique for continuous updating the internal information about robot position, especially indoors without GPS (Global Positioning System). Visual odometry is using one or more cameras to find visual clues and estimate robot movements in 3D relatively. Recent progress has been made, especially with fully integrated systems such as the RealSense T265 from Intel, which is the focus of this article. We compare between each other three visual odometry systems (and one wheel odometry, as a known baseline), on a ground robot. We do so in eight scenarios, varying the speed, the number of visual features, and with or without humans walking in the field of view. We continuously measure the position error in translation and rotation thanks to a ground truth positioning system. Our result shows that all odometry systems are challenged, but in different ways. The RealSense T265 and the ZED Mini have comparable performance, better than our baseline ORB-SLAM2 (mono-lens without inertial measurement unit (IMU)) but not excellent. In conclusion, a single odometry system might still not be sufficient, so using multiple instances and sensor fusion approaches are necessary while waiting for additional research and further improved products.

scholarly journals 3D Crowd Counting via Multi-View Fusion with 3D Gaussian Kernels

2020 ◽  
Vol 34 (07) ◽  
pp. 12837-12844
Author(s):  
Qi Zhang ◽  
Antoni B. Chan
Keyword(s):  
Feature Fusion ◽  
Level Density ◽  
Ground Plane ◽  
Ground Truth ◽  
Estimation Methods ◽  
Crowd Counting ◽  
Single View ◽  
Gaussian Kernels ◽  
Density Maps ◽  
Density Map

Crowd counting has been studied for decades and a lot of works have achieved good performance, especially the DNNs-based density map estimation methods. Most existing crowd counting works focus on single-view counting, while few works have studied multi-view counting for large and wide scenes, where multiple cameras are used. Recently, an end-to-end multi-view crowd counting method called multi-view multi-scale (MVMS) has been proposed, which fuses multiple camera views using a CNN to predict a 2D scene-level density map on the ground-plane. Unlike MVMS, we propose to solve the multi-view crowd counting task through 3D feature fusion with 3D scene-level density maps, instead of the 2D ground-plane ones. Compared to 2D fusion, the 3D fusion extracts more information of the people along z-dimension (height), which helps to solve the scale variations across multiple views. The 3D density maps still preserve the 2D density maps property that the sum is the count, while also providing 3D information about the crowd density. We also explore the projection consistency among the 3D prediction and the ground-truth in the 2D views to further enhance the counting performance. The proposed method is tested on 3 multi-view counting datasets and achieves better or comparable counting performance to the state-of-the-art.

scholarly journals Unsupervised Deep Learning-Based RGB-D Visual Odometry

2020 ◽  
Vol 10 (16) ◽  
pp. 5426 ◽  
Author(s):  
Qiang Liu ◽  
Haidong Zhang ◽  
Yiming Xu ◽  
Li Wang
Keyword(s):  
Deep Learning ◽  
Feature Matching ◽  
Ground Truth ◽  
Visual Odometry ◽  
Depth Images ◽  
Network Training ◽  
Stream Structure ◽  
Unsupervised Deep Learning ◽  
Rgb Images ◽  
Learning Frameworks

Recently, deep learning frameworks have been deployed in visual odometry systems and achieved comparable results to traditional feature matching based systems. However, most deep learning-based frameworks inevitably need labeled data as ground truth for training. On the other hand, monocular odometry systems are incapable of restoring absolute scale. External or prior information has to be introduced for scale recovery. To solve these problems, we present a novel deep learning-based RGB-D visual odometry system. Our two main contributions are: (i) during network training and pose estimation, the depth images are fed into the network to form a dual-stream structure with the RGB images, and a dual-stream deep neural network is proposed. (ii) the system adopts an unsupervised end-to-end training method, thus the labor-intensive data labeling task is not required. We have tested our system on the KITTI dataset, and results show that the proposed RGB-D Visual Odometry (VO) system has obvious advantages over other state-of-the-art systems in terms of both translation and rotation errors.

Sign in / Sign up

Export Citation Format

Share Document