scholarly journals Learning-Type Anchors-Driven Pose Estimation for the Autolanding Fixed-Wing UAVs

2021 ◽  
Author(s):  
Dengqing Tang ◽  
Lincheng Shen ◽  
Xiaojiao Xiang ◽  
Han Zhou ◽  
Tianjiang Hu
Keyword(s):  
Real Time ◽  
Pose Estimation ◽  
Stereo Vision ◽  
Vision System ◽  
Estimation Method ◽  
Satellite System ◽  
Training Dataset ◽  
Estimation Accuracy ◽  
The Impact ◽  
Outdoor Experiments

<p>We propose a learning-type anchors-driven real-time pose estimation method for the autolanding fixed-wing unmanned aerial vehicle (UAV). The proposed method enables online tracking of both position and attitude by the ground stereo vision system in the Global Navigation Satellite System denied environments. A pipeline of convolutional neural network (CNN)-based UAV anchors detection and anchors-driven UAV pose estimation are employed. To realize robust and accurate anchors detection, we design and implement a Block-CNN architecture to reduce the impact of the outliers. With the basis of the anchors, monocular and stereo vision-based filters are established to update the UAV position and attitude. To expand the training dataset without extra outdoor experiments, we develop a parallel system containing the outdoor and simulated systems with the same configuration. Simulated and outdoor experiments are performed to demonstrate the remarkable pose estimation accuracy improvement compared with the conventional Perspective-N-Points solution. In addition, the experiments also validate the feasibility of the proposed architecture and algorithm in terms of the accuracy and real-time capability requirements for fixed-wing autolanding UAVs.</p>

scholarly journals Learning-Type Anchors-Driven Pose Estimation for the Autolanding Fixed-Wing UAVs

2021 ◽  
Author(s):  
Dengqing Tang ◽  
Lincheng Shen ◽  
Xiaojiao Xiang ◽  
Han Zhou ◽  
Tianjiang Hu
Keyword(s):  
Real Time ◽  
Pose Estimation ◽  
Stereo Vision ◽  
Vision System ◽  
Estimation Method ◽  
Satellite System ◽  
Training Dataset ◽  
Estimation Accuracy ◽  
The Impact ◽  
Outdoor Experiments

<p>We propose a learning-type anchors-driven real-time pose estimation method for the autolanding fixed-wing unmanned aerial vehicle (UAV). The proposed method enables online tracking of both position and attitude by the ground stereo vision system in the Global Navigation Satellite System denied environments. A pipeline of convolutional neural network (CNN)-based UAV anchors detection and anchors-driven UAV pose estimation are employed. To realize robust and accurate anchors detection, we design and implement a Block-CNN architecture to reduce the impact of the outliers. With the basis of the anchors, monocular and stereo vision-based filters are established to update the UAV position and attitude. To expand the training dataset without extra outdoor experiments, we develop a parallel system containing the outdoor and simulated systems with the same configuration. Simulated and outdoor experiments are performed to demonstrate the remarkable pose estimation accuracy improvement compared with the conventional Perspective-N-Points solution. In addition, the experiments also validate the feasibility of the proposed architecture and algorithm in terms of the accuracy and real-time capability requirements for fixed-wing autolanding UAVs.</p>

scholarly journals A Real-Time Detection Method for BDS Signal in Space Anomalies

Sensors ◽  
2019 ◽  
Vol 19 (6) ◽  
pp. 1437 ◽  
Author(s):  
Chun Cheng ◽  
Yuxin Zhao ◽  
Liang Li ◽  
Lin Zhao
Keyword(s):  
Real Time ◽  
Estimation Method ◽  
Satellite System ◽  
Statistical Characteristics ◽  
Estimation Accuracy ◽  
Navigation Systems ◽  
Long Latency ◽  
Characteristics Analysis ◽  
Satellite Navigation Systems ◽  
Range Error

Signal In Space (SIS) anomalies in satellite navigation systems can degrade satellite-based navigation and positioning performance. The occurrence of SIS anomalies from the BeiDou navigation satellite System (BDS) may be more frequent than for the Global Positioning System (GPS). In order to guarantee the integrity of BDS users, detecting and excluding SIS anomalies is indispensable. The traditional method through the comparison between the final precision ephemeris and the broadcast ephemeris is limited by the issue of long latency of precision ephemeris release. Through the statistical characteristics analysis of Signal In Space User Range Error (SISURE), we propose a real-time Instantaneous SISURE (IURE) estimation method by using the Kalman filtering-based carrier-smoothed-code to detect and exclude BDS SIS anomalies, in which the threshold for BDS IURE anomaly detection are obtained from the integrity requirement. The experimental results based on 1 Hz data from ground observations show that the proposed method has an estimation accuracy of 1.1 m for BDS IURE. The test results show that the proposed method can effectively detect the SIS anomalies caused by either orbit faults or clock faults.

scholarly journals High-Accuracy Real-Time Kinematic Positioning with Multiple Rover Receivers Sharing Common Clock

2021 ◽  
Vol 13 (4) ◽  
pp. 823
Author(s):  
Lin Zhao ◽  
Jiachang Jiang ◽  
Liang Li ◽  
Chun Jia ◽  
Jianhua Cheng
Keyword(s):  
Real Time ◽  
Ambiguity Resolution ◽  
Temporal Stability ◽  
Estimation Method ◽  
Satellite System ◽  
Integer Ambiguity ◽  
Dual Frequency ◽  
Kinematic Positioning ◽  
Real Time Kinematic ◽  
Satellite Visibility

Since the traditional real-time kinematic positioning method is limited by the reduced satellite visibility from the deprived navigational environments, we, therefore, propose an improved RTK method with multiple rover receivers sharing a common clock. The proposed method can enhance observational redundancy by blending the observations from each rover receiver together so that the model strength will be improved. Integer ambiguity resolution of the proposed method is challenged in the presence of several inter-receiver biases (IRB). The IRB including inter-receiver code bias (IRCB) and inter-receiver phase bias (IRPB) is calibrated by the pre-estimation method because of their temporal stability. Multiple BeiDou Navigation Satellite System (BDS) dual-frequency datasets are collected to test the proposed method. The experimental results have shown that the IRCB and IRPB under the common clock mode are sufficiently stable for the ambiguity resolution. Compared with the traditional method, the ambiguity resolution success rate and positioning accuracy of the proposed method can be improved by 19.5% and 46.4% in the restricted satellite visibility environments.

An FPGA-based real-time occlusion robust stereo vision system using semi-global matching

2019 ◽  
Vol 17 (5) ◽  
pp. 1447-1468 ◽  
Author(s):  
Lucas F. S. Cambuim ◽  
Luiz A. Oliveira ◽  
Edna N. S. Barros ◽  
Antonyus P. A. Ferreira
Keyword(s):  
Real Time ◽  
Stereo Vision ◽  
Vision System ◽  
Stereo Vision System ◽  
Global Matching

scholarly journals Impact of ECOM Solar Radiation Pressure Models on Multi-GNSS Ultra-Rapid Orbit Determination

2019 ◽  
Vol 11 (24) ◽  
pp. 3024
Author(s):  
Yang Liu ◽  
Yanxiong Liu ◽  
Ziwen Tian ◽  
Xiaolei Dai ◽  
Yun Qing ◽  
...  
Keyword(s):  
Solar Radiation ◽  
Real Time ◽  
Radiation Pressure ◽  
Orbit Determination ◽  
Precise Orbit Determination ◽  
Solar Radiation Pressure ◽  
Satellite System ◽  
Ambiguity Fixing ◽  
Global Navigation Satellite ◽  
The Impact

The Global Navigation Satellite System (GNSS) ultra-rapid precise orbits are crucial for global and wide-area real-time high-precision applications. The solar radiation pressure (SRP) model is an important factor in precise orbit determination. The real-time orbit determination is generally less accurate than the post-processed one and may amplify the instability and mismodeling of SRP models. Also, the impact of different SRP models on multi-GNSS real-time predicted orbits demands investigations. We analyzed the impact of the ECOM 1 and ECOM 2 models on multi-GNSS ultra-rapid orbit determination in terms of ambiguity resolution performance, real-time predicted orbit overlap precision, and satellite laser ranging (SLR) validation. The multi-GNSS observed orbital arc and predicted orbital arcs of 1, 3, 6, and 24 h are compared. The simulated real-time experiment shows that for GLONASS and Galileo ultra-rapid orbits, compared to ECOM 1, ECOM 2 increased the ambiguity fixing rate to 89.3% and 83.1%, respectively, and improves the predicted orbit accuracy by 9.2% and 27.7%, respectively. For GPS ultra-rapid orbits, ECOM 2 obtains a similar ambiguity fixing rate as ECOM 1 but slightly better orbit overlap precision. For BDS GEO ultra-rapid orbits, ECOM 2 obtains better overlap precision and SLR residuals, while for BDS IGSO and MEO ultra-rapid orbits, ECOM 1 obtains better orbit overlap precision and SLR residuals.

scholarly journals Voxel-Based Scene Representation for Camera Pose Estimation of a Single RGB Image

2020 ◽  
Vol 10 (24) ◽  
pp. 8866
Author(s):  
Sangyoon Lee ◽  
Hyunki Hong ◽  
Changkyoung Eem
Keyword(s):  
Pose Estimation ◽  
Estimation Method ◽  
Ground Truth ◽  
Training Dataset ◽  
Interest Points ◽  
Camera Pose Estimation ◽  
Polygonal Region ◽  
Camera Pose ◽  
End To End ◽  
Image Pairs

Deep learning has been utilized in end-to-end camera pose estimation. To improve the performance, we introduce a camera pose estimation method based on a 2D-3D matching scheme with two convolutional neural networks (CNNs). The scene is divided into voxels, whose size and number are computed according to the scene volume and the number of 3D points. We extract inlier points from the 3D point set in a voxel using random sample consensus (RANSAC)-based plane fitting to obtain a set of interest points consisting of a major plane. These points are subsequently reprojected onto the image using the ground truth camera pose, following which a polygonal region is identified in each voxel using the convex hull. We designed a training dataset for 2D–3D matching, consisting of inlier 3D points, correspondence across image pairs, and the voxel regions in the image. We trained the hierarchical learning structure with two CNNs on the dataset architecture to detect the voxel regions and obtain the location/description of the interest points. Following successful 2D–3D matching, the camera pose was estimated using n-point pose solver in RANSAC. The experiment results show that our method can estimate the camera pose more precisely than previous end-to-end estimators.

scholarly journals Statistical post-processing of ensemble forecasts of the height of new snow

2019 ◽  
Vol 26 (3) ◽  
pp. 339-357 ◽  
Author(s):  
Jari-Pekka Nousu ◽  
Matthieu Lafaysse ◽  
Matthieu Vernay ◽  
Joseph Bellier ◽  
Guillaume Evin ◽  
...  
Keyword(s):  
Real Time ◽  
Spatial Scales ◽  
Weather Prediction ◽  
Evaluation Criteria ◽  
Training Dataset ◽  
Post Processing ◽  
Probabilistic Forecasting ◽  
Ensemble Forecasts ◽  
Heterogeneous Model ◽  
The Impact

Abstract. Forecasting the height of new snow (HN) is crucial for avalanche hazard forecasting, road viability, ski resort management and tourism attractiveness. Météo-France operates the PEARP-S2M probabilistic forecasting system, including 35 members of the PEARP Numerical Weather Prediction system, where the SAFRAN downscaling tool refines the elevation resolution and the Crocus snowpack model represents the main physical processes in the snowpack. It provides better HN forecasts than direct NWP diagnostics but exhibits significant biases and underdispersion. We applied a statistical post-processing to these ensemble forecasts, based on non-homogeneous regression with a censored shifted Gamma distribution. Observations come from manual measurements of 24 h HN in the French Alps and Pyrenees. The calibration is tested at the station scale and the massif scale (i.e. aggregating different stations over areas of 1000 km2). Compared to the raw forecasts, similar improvements are obtained for both spatial scales. Therefore, the post-processing can be applied at any point of the massifs. Two training datasets are tested: (1) a 22-year homogeneous reforecast for which the NWP model resolution and physical options are identical to the operational system but without the same initial perturbations; (2) 3-year real-time forecasts with a heterogeneous model configuration but the same perturbation methods. The impact of the training dataset depends on lead time and on the evaluation criteria. The long-term reforecast improves the reliability of severe snowfall but leads to overdispersion due to the discrepancy in real-time perturbations. Thus, the development of reliable automatic forecasting products of HN needs long reforecasts as homogeneous as possible with the operational systems.

Sign in / Sign up

Export Citation Format

Share Document