High-definition(HD)maps are key components that provide rich topologic and semantic information for decision-making in vehicle autonomous driving systems.A complete ground orthophoto is usually used as the base image ...High-definition(HD)maps are key components that provide rich topologic and semantic information for decision-making in vehicle autonomous driving systems.A complete ground orthophoto is usually used as the base image to construct the HD map.The ground orthophoto is obtained through inverse perspective transformation and image mosaicing.During the image mosaicing,multiple consecutive orthophotos are stitched together using pose information and image registration.In this study,wavelet transform is introduced to the image mosaicing process to alleviate the information loss caused by image overlapping.In the orthophoto wavelet transform,high-frequency and low-frequency components are fused using different strategies to form a complete base image with clearer local details.Experimental results show that the accuracy of the orthophotos generated using this method is improved.展开更多
In point cloud registration applications,noise and poor initial conditions lead to many false matches.False matches significantly degrade registration accuracy and speed.A penalty function is adopted in many robust po...In point cloud registration applications,noise and poor initial conditions lead to many false matches.False matches significantly degrade registration accuracy and speed.A penalty function is adopted in many robust point-to-point registration methods to suppress the influence of false matches.However,after applying a penalty function,problems cannot be solved in their analytical forms based on the introduction of nonlinearity.Therefore,most existing methods adopt the descending method.In this paper,a novel iterative-reweighting-based method is proposed to overcome the limitations of existing methods.The proposed method iteratively solves the eigenvectors of a four-dimensional matrix,whereas the calculation of the descending method relies on solving an eight-dimensional matrix.Therefore,the proposed method can achieve increased computational efficiency.The proposed method was validated on simulated noise corruption data,and the results reveal that it obtains higher efficiency and precision than existing methods,particularly under very noisy conditions.Experimental results for the KITTI dataset demonstrate that the proposed method can be used in real-time localization processes with high accuracy and good efficiency.展开更多
基金the National Natural Science Foundation of China(No.U1764264/61873165)the Shanghai Automotive Industry Science and Technology Development Foundation(No.1807)the Guangxi Key Laboratory of Automobile Components and Vehicle Technology Research Project(No.2020GKLACVTKF02)。
文摘High-definition(HD)maps are key components that provide rich topologic and semantic information for decision-making in vehicle autonomous driving systems.A complete ground orthophoto is usually used as the base image to construct the HD map.The ground orthophoto is obtained through inverse perspective transformation and image mosaicing.During the image mosaicing,multiple consecutive orthophotos are stitched together using pose information and image registration.In this study,wavelet transform is introduced to the image mosaicing process to alleviate the information loss caused by image overlapping.In the orthophoto wavelet transform,high-frequency and low-frequency components are fused using different strategies to form a complete base image with clearer local details.Experimental results show that the accuracy of the orthophotos generated using this method is improved.
基金the National Natural Science Foundation of China(No.U1764264)。
文摘In point cloud registration applications,noise and poor initial conditions lead to many false matches.False matches significantly degrade registration accuracy and speed.A penalty function is adopted in many robust point-to-point registration methods to suppress the influence of false matches.However,after applying a penalty function,problems cannot be solved in their analytical forms based on the introduction of nonlinearity.Therefore,most existing methods adopt the descending method.In this paper,a novel iterative-reweighting-based method is proposed to overcome the limitations of existing methods.The proposed method iteratively solves the eigenvectors of a four-dimensional matrix,whereas the calculation of the descending method relies on solving an eight-dimensional matrix.Therefore,the proposed method can achieve increased computational efficiency.The proposed method was validated on simulated noise corruption data,and the results reveal that it obtains higher efficiency and precision than existing methods,particularly under very noisy conditions.Experimental results for the KITTI dataset demonstrate that the proposed method can be used in real-time localization processes with high accuracy and good efficiency.