Point set registration has been a topic of significant research interest in the field of mobile intelligent unmanned systems.In this paper,we present a novel approach for a three-dimensional scan-to-map point set regi...Point set registration has been a topic of significant research interest in the field of mobile intelligent unmanned systems.In this paper,we present a novel approach for a three-dimensional scan-to-map point set registration.Using Gaussian process(GP)regression,we propose a new type of map representation,based on a regionalized GP map reconstruction algorithm.We combine the predictions and the test locations derived from the GP as the predictive points.In our approach,the correspondence relationships between predictive point pairs are set up naturally,and a rigid transformation is calculated iteratively.The proposed method is implemented and tested on three standard point set datasets.Experimental results show that our method achieves stable performance with regard to accuracy and efficiency,on a par with two standard methods,the iterative closest point algorithm and the normal distribution transform.Our mapping method also provides a compact point-cloud-like map and exhibits low memory consumption.展开更多
A key step of constructing active appearance model is requiring a set of appropriate training shapes with well-defined correspondences.In this paper,we introduce a novel point correspondence method(FB-CPD),which can i...A key step of constructing active appearance model is requiring a set of appropriate training shapes with well-defined correspondences.In this paper,we introduce a novel point correspondence method(FB-CPD),which can improve the accuracy of coherent point drift(CPD) by using the information of image feature.The objective function of the proposed method is defined by both of geometric spatial information and image feature information,and the origin Gaussian mixture model in CPD is modified according to the image feature of points.FB-CPD is tested on the 3D prostate and liver point sets through the simulation experiments.The registration error can be reduced efficiently by FB-CPD.Moreover,the active appearance model constructed by FB-CPD can obtain fine segmentation in 3D CT prostate image.Compared with the original CPD,the overlap ratio of voxels was improved from 88.7% to 90.2% by FB-CPD.展开更多
基金Project supported by the National Natural Science Foundation of China(Nos.61673341,61703366,and 11705026)。
文摘Point set registration has been a topic of significant research interest in the field of mobile intelligent unmanned systems.In this paper,we present a novel approach for a three-dimensional scan-to-map point set registration.Using Gaussian process(GP)regression,we propose a new type of map representation,based on a regionalized GP map reconstruction algorithm.We combine the predictions and the test locations derived from the GP as the predictive points.In our approach,the correspondence relationships between predictive point pairs are set up naturally,and a rigid transformation is calculated iteratively.The proposed method is implemented and tested on three standard point set datasets.Experimental results show that our method achieves stable performance with regard to accuracy and efficiency,on a par with two standard methods,the iterative closest point algorithm and the normal distribution transform.Our mapping method also provides a compact point-cloud-like map and exhibits low memory consumption.
基金National Basic Research Program of China(973 Program)grant number:2010CB732505+1 种基金National Natural Science Foundation of Chinagrant number:30900380
文摘A key step of constructing active appearance model is requiring a set of appropriate training shapes with well-defined correspondences.In this paper,we introduce a novel point correspondence method(FB-CPD),which can improve the accuracy of coherent point drift(CPD) by using the information of image feature.The objective function of the proposed method is defined by both of geometric spatial information and image feature information,and the origin Gaussian mixture model in CPD is modified according to the image feature of points.FB-CPD is tested on the 3D prostate and liver point sets through the simulation experiments.The registration error can be reduced efficiently by FB-CPD.Moreover,the active appearance model constructed by FB-CPD can obtain fine segmentation in 3D CT prostate image.Compared with the original CPD,the overlap ratio of voxels was improved from 88.7% to 90.2% by FB-CPD.
