Cross-modal vehicle detection method based on multilayer local sampling and three-dimensional view cone point cloud
The invention discloses a cross-modal vehicle detection method based on multilayer local sampling and a three-dimensional view cone point cloud. The method comprises the following steps: step 1, obtaining point cloud data; 2, determining a first sampling point from the point cloud data through down-...
Saved in:
Main Authors | , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
09.12.2022
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The invention discloses a cross-modal vehicle detection method based on multilayer local sampling and a three-dimensional view cone point cloud. The method comprises the following steps: step 1, obtaining point cloud data; 2, determining a first sampling point from the point cloud data through down-sampling, and recording the first sampling point as a candidate point; 3, taking the candidate point as a center, determining K nearest neighbor points by adopting a KNN algorithm with abstract feature constraint, recording a set formed by each candidate point and the corresponding K nearest neighbor points as a local region, performing feature extraction on each local region by adopting PointNet to generate a feature vector, and performing feature extraction on the feature vector to obtain a feature vector; each local area corresponds to one candidate point and one feature vector; 4, judging whether the number of the sampling points is not reduced any more, if not, executing the step 5, and if yes, executing the s |
---|---|
Bibliography: | Application Number: CN202211033470 |