RANSACs for 3D Rigid Registration:A Comparative Evaluation

Estimating an accurate six-degree-of-freedom(6-Do F)pose from correspondences with outliers remains a critical issue to 3D rigid registration.Random sample consensus(RANSAC)and its variants are popular solutions to this problem.Although there have been a number of RANSAC-fashion estimators,two issues remain unsolved.First,it is unclear which estimator is more appropriate to a particular application.Second,the impacts of different sampling strategies,hypothesis generation methods,hypothesis evaluation metrics,and stop criteria on the overall estimators remain ambiguous.This work fills these gaps by first considering six existing RANSAC-fashion methods and then proposing eight variants for a comprehensive evaluation.The objective is to thoroughly compare estimators in the RANSAC family,and evaluate the effects of each key stage on the eventual 6-Do F pose estimation performance.Experiments have been carried out on four standard datasets with different application scenarios,data modalities,and nuisances.They provide us with input correspondence sets with a variety of inlier ratios,spatial distributions,and scales.Based on the experimental results,we summarize remarkable outcomes and valuable findings,so as to give practical instructions to real-world applications,and highlight current bottlenecks and potential solutions in this research realm.

Straight-Going Priority in Hierarchical Control Framework for Right-Turning Vehicle Merging Based on Cooperative Game

With the development of connected and automated vehicles(CAVs),forming strategies could extend from the typically used first-come-first-served rules.It is necessary to consider passing priorities when crossing intersections to prevent conflicts.In this study,a hierarchical strategy based on a cooperative game was developed to improve safety and efficiency during right-turning merging.A right-turn merging conflict model was established to analyze the right-turning vehicle characteristics of the traffic flow.The proposed three-layered hierarchical strategy includes a decision-making layer,a task layer,and an operation layer.A decision-making-layer cooperative game strategy was used to determine the merging priority of straight-going traffic and right-turning flows.In addition,a task-layer cooperative game strategy was designed for the merging sequence.A modified consensus algorithm was utilized to optimize the speed of vehicles in the virtual platoon of the operation layer.Traffic simulations were performed on the PYTHON-SUMO integrated platform to verify the proposed strategy.The simulation results show that,compared with other methods,the proposed hierarchical strategy has the shortest travel time and loss time and performs better than other methods when the straight-going traffic flow increases during right-turning merging at the intersection.The proposed method shows superiority under a significant traffic flow with a threshold of 900 vehicle/(h·lane).This satisfactory application of right-turning merging might be extended to ramps,lane-changing,and other scenarios in the future.

A method of 3D reconstruction based on panoramic cameras

In this paper,a method of 3D reconstruction from two images acquired by two panoramic cameras is presented.Firstly,the features of the reconstruction object detected in each image are matched through the DP matching method.Secondly,optical correction is carried out on two cameras,and the internal parameters of panoramic cameras can be calculated.Finally,according to the calibration method,the geometric relationship between corresponding points in space and in two panoramic images is deduced.The results indicate that the method of 3D reconstruction based on two panoramic cameras is simple,and the accuracy can reach 98.82%.