An Optimization-Based Multi-Sensor Fusion Approach Towards Global Drift-Free Motion Estimation

Wang, Ke; Cao, Chenzhong; Ma, Sai; Ren, Fan

doi:10.1109/jsen.2021.3064446

Cited by 22 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The visual and LiDAR sensor information are loosely coupled by covariance intersection in [17] for the robust inter-frame transformation estimation. Besides, a multisensor joint optimization approach has been proposed in [18] and the dual-layer optimization design ensures both local and global estimation consistency. At the same time, the RTK/IMU measurements are employed to verify the LiDAR scan matching accuracy to prevent degenerated estimation in [19].…”

Section: Hybrid Scan Matchingmentioning

confidence: 99%

Uncertainty-Aware Adaptive Semidirect LiDAR Scan Matching for Ground Vehicle Positioning

Chen

Frémont

2023

IEEE Sensors J.

View full text Add to dashboard Cite

Iterative Closest Point (ICP) algorithms are widely used in the literature for the estimation of relative transformations using 3D LiDAR point clouds. This class of algorithms proves to be efficient when the 3D data share sufficient overlapping parts and a good initial guess is provided. However, large relative motions and mutual occlusion of objects in real-road scenarios hinder traditional optimization-based ICP from achieving optimal estimation. This paper explores both direct and feature-based 3D LiDAR scan matching using the ICP framework in different contexts, such as parking, residential, urban, and highway scenarios. In order to guarantee the scan matching performances in scenarios with scarce geometric information and fast ego-vehicle motion, we propose an adaptive semi-direct scan matching method together with an alignment uncertainty quantification. The proposed semi-direct scan matching is tested on both the public KITTI and self-recorded LS2N datasets, which accomplishes the robust 6 Degrees of Freedom (DoF) pose estimation and consistent scene reconstruction. We demonstrate that the proposed approach outperforms the state-of-the-art and achieves the leading results with 68.3 % average relative fitness and 5.71 cm average RMSE, respectively.

show abstract

Section: Hybrid Scan Matchingmentioning

confidence: 99%

Uncertainty-Aware Adaptive Semidirect LiDAR Scan Matching for Ground Vehicle Positioning

Chen

Frémont

2023

IEEE Sensors J.

View full text Add to dashboard Cite

show abstract

“…To solve the problem of the poor positioning of the sensors and the surrounding objects, multiple sensors were used to capture the finer details and clearer geometric shapes in order to better reconstruct the high-texture 3D point cloud map in real-time. K. Wang et al [196] proposed a two-layer optimization strategy. In the local estimation layer, the relative pose is obtained through LIDAR odometry and visual inertial odometry, and GPS information is introduced in the global optimization layer to correct the cumulative drift, so that accurate absolute positioning can be achieved without global drift.…”

Section: (B) Other Fusion Optionsmentioning

confidence: 99%

SLAM Overview: From Single Sensor to Heterogeneous Fusion

et al. 2022

View full text Add to dashboard Cite

After decades of development, LIDAR and visual SLAM technology has relatively matured and been widely used in the military and civil fields. SLAM technology enables the mobile robot to have the abilities of autonomous positioning and mapping, which allows the robot to move in indoor and outdoor scenes where GPS signals are scarce. However, SLAM technology relying only on a single sensor has its limitations. For example, LIDAR SLAM is not suitable for scenes with highly dynamic or sparse features, and visual SLAM has poor robustness in low-texture or dark scenes. However, through the fusion of the two technologies, they have great potential to learn from each other. Therefore, this paper predicts that SLAM technology combining LIDAR and visual sensors, as well as various other sensors, will be the mainstream direction in the future. This paper reviews the development history of SLAM technology, deeply analyzes the hardware information of LIDAR and cameras, and presents some classical open source algorithms and datasets. According to the algorithm adopted by the fusion sensor, the traditional multi-sensor fusion methods based on uncertainty, features, and novel deep learning are introduced in detail. The excellent performance of the multi-sensor fusion method in complex scenes is summarized, and the future development of multi-sensor fusion method is prospected.

show abstract

“…Lu W et al extended the Camshaft algorithm by adding a fast panoramic video multitarget state prediction algorithm with adaptive kernel bandwidth and state estimation, which reduces the mean-shift [21]. Saha P et al used the Camshaft tracker to detect hand motion trajectories from video images, combining Markov model sequence classification methods to improve the success rate of target detection [22].…”

Section: Panoramic Video Multitarget Real-time Trackingmentioning

confidence: 99%

Real-Time Multitarget Tracking for Panoramic Video Based on Dual Neural Networks for Multisensor Information Fusion

Lin

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

A multitarget real-time tracking system for panoramic video with multisensor information fusion dual neural networks is studied and implemented by combining dual neural networks, fused geometric features, and deep learning-based target real-time tracking algorithms. The motion model of multisensor information fusion is analyzed, the dual neural network perturbation model is introduced, and the state variables of the system are determined. Combined with the data structure model of multisensor information fusion, a least-squares-based optimization function is constructed. In this optimization function, the image sensor is constructed as an observationally constrained residual term based on the pixel plane, the inertial measurement unit is constructed as an observationally constrained residual term based on the motion model, and the motion relationship between sensors is constructed as a motion-constrained residual term to derive a mathematical model for real-time multitarget tracking of panoramic video. The simulation experimental results show that the integrated position estimation accuracy of the multisensor information fusion dual neural network-based panoramic video multitarget real-time tracking fusion algorithm is 10.5% higher than that of the optimal distributed panoramic video multitarget fusion algorithm without feedback. The results of the simulation experiments show that the integrated position estimation accuracy of the multitarget real-time tracking fusion algorithm for panoramic video improves by 10.96%, and the integrated speed estimation accuracy improves by 6.32% compared with the optimal distributed multitarget fusion algorithm without feedback. The proposed panoramic video multitarget real-time tracking algorithm based on the dual neural network can effectively improve the target tracking accuracy of the model on degraded frames (motion blur, target occlusion, out-of-focus, etc.), and the stability of the algorithm for target location and category detection is effectively improved by multiframe feature fusion. The research in this paper provides better technical support and research theory for panoramic video multitarget real-time tracking.

show abstract

An Optimization-Based Multi-Sensor Fusion Approach Towards Global Drift-Free Motion Estimation

Cited by 22 publications

References 21 publications

Uncertainty-Aware Adaptive Semidirect LiDAR Scan Matching for Ground Vehicle Positioning

Uncertainty-Aware Adaptive Semidirect LiDAR Scan Matching for Ground Vehicle Positioning

SLAM Overview: From Single Sensor to Heterogeneous Fusion

Real-Time Multitarget Tracking for Panoramic Video Based on Dual Neural Networks for Multisensor Information Fusion

Contact Info

Product

Resources

About