A method and system for point cloud intensity completion based on semantic segmentation

Abstract

The invention discloses a method and system for complementing point cloud intensity based on semantic segmentation. The method includes: synchronously collecting RGB images and point cloud data of the road surface by a camera and a laser radar; using a transformation matrix to perform spatial transformation on the point cloud data, Generate two-dimensional reflection intensity projection map and two-dimensional depth projection map; RGB image and two-dimensional reflection intensity projection map are completed by reflection intensity to obtain single-channel reflection intensity projection map; RGB image and two-dimensional depth projection map are completed by depth A single-channel depth projection map is obtained; the RGB image, single-channel reflection intensity projection map and single-channel depth projection map are processed by coarse-grained completion to obtain a two-dimensional coarse-grained reflection intensity projection map; the RGB image and two-dimensional depth projection map are obtained by Semantic segmentation processing to obtain several regions to be completed; according to the regions to be completed, fine-grained reflection intensity completion is performed on the two-dimensional coarse-grained reflection intensity projection map to obtain a two-dimensional reflection intensity projection completion map.

Description

technical field [0001] The invention belongs to the field of unmanned driving, and in particular relates to a point cloud intensity complement method and system based on semantic segmentation. Background technique [0002] Lidar is the main tool for unmanned driving data collection. Lidar for unmanned vehicles generally has 16 / 32 / 64 / 128 lines of lidar. The cost of lidar increases with the number of lines, but less The lidar of the wire harness collects less point clouds, and the sparse point clouds are difficult to use for high-precision calculations. [0003] In addition, in actual acquisition, the energy of the lidar return beam is affected by distance and propagation medium. Long-distance objects cannot return the beam or the energy of the returned beam is lower than the detection threshold; in addition, due to the influence of microscopic particles in the atmosphere, meteorological conditions such as rain, snow and fog will cause the energy loss of the beam emitted by t...

AI Technical Summary

Problems solved by technology

Long-distance objects cannot return the beam or the energy of the returned beam is lower than the detection threshold; in addition, affected by the microscopic particles in the atmosphere, weather conditions such as rain, snow and fog will cause the energy loss of the beam emitted by the lidar, resulting in the object being unable to return the beam or return the energy of the beam below detection threshold

Both of these conditions will eventually result in the receiver not being able to receive the signal, the received signal being weakened or doped with noise

[0004] The current point cloud completion work mainly has the following limitations: (1) limited to the point cloud completion of local objects, especially the completion of indoor scenes or single objects; (2) limited to the completion of local dependencies, that is, based on phase (3) In the completion of large-scale overall scenes, the focus is on depth completion, while less research has been done on reflection intensity completion

Images