Saturation waveform and non-saturation waveform classification method and system and electronic device for full waveform lidar
By extracting five waveform features from a full-waveform lidar and using the K-means clustering method, the ranging error problem of full-waveform lidar under saturated waveforms was solved. This enabled effective classification of "flat peak" or "quasi-flat peak" saturated waveforms and non-saturated waveforms, thereby improving ranging accuracy.
CN118568575BActive Publication Date: 2026-06-05JILIN UNIVERSITY
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- JILIN UNIVERSITY
- Filing Date
- 2024-03-12
- Publication Date
- 2026-06-05
Smart Images
Figure CN118568575B_ABST
Abstract
The application belongs to the technical field of laser radars, and specifically discloses a saturated waveform and non-saturated waveform classification method and system of a full-waveform laser radar and an electronic device. Five waveform features are constructed, K-means clustering is used on the basis of five feature values of each waveform data to cluster the waveforms, and a label is given to the classification result according to the feature value size, so that the saturated waveforms and non-saturated waveforms are finally obtained, the saturated waveform data is eliminated, and the full-waveform airborne laser radar ranging accuracy is improved.
Need to check novelty before this filing date? Find Prior Art