Method for extracting water surface passable area by high-robustness unmanned ship based on laser radar

Abstract

The invention relates to the technical field of laser radar sensors and unmanned ship automatic driving, in particular to a method for extracting a water surface passable area by a high-robustness unmanned ship based on a laser radar. According to the method, experimental environment data are acquired by using a laser radar sensor, semantic segmentation is performed on point cloud data through a neural network, continuous multi-frame river bank point cloud data are fused, river bank point cloud is refined through smooth filtering and an image corrosion method, and then feature points are extracted and sequenced to serve as control points. Then, in order to slow down the rapid change of the river bank, the control points are smoothed through unscented Kalman filtering; and fitting the smoothed control points by using a B spline curve, and finally carrying out noise filtering on the extracted water surface region based on particle filtering. The robustness and precision of extracting the water surface passable area are effectively improved.

Description

technical field [0001] The invention relates to the technical field of lidar sensors and unmanned ship automatic driving, and more specifically, to a method for extracting water surface passable areas by a highly robust unmanned ship based on lidar. Background technique [0002] Chinese patent CN108303988A discloses an unmanned ship target recognition and tracking system and its working method. It uses 3D laser radar and vector hydrophone to scan the underwater obstacles on the water surface, and the industrial computer analyzes the position of the obstacles on the water surface. The processor determines the position of the underwater obstacle. According to the obtained obstacle position, the industrial computer adopts the obstacle avoidance algorithm to avoid the obstacle. The purpose of operating in complex waters. This invention is mainly aimed at avoiding obstacles on the water surface and underwater. For the scene of narrow rivers, there will be various shapes of river...

AI Technical Summary

Problems solved by technology

This invention is mainly aimed at avoiding obstacles on the water surface and underwater. For the scene of narrow rivers, there will be various shapes of river banks and the influence of random noise such as water surface ripples. This invention cannot solve these limitations.

Based on laser radar to identify and track underwater targets on the water surface, only fixed obstacles can be identified and analyzed. For small floating objects such as ripples and leaves on the water surface, they will be mistaken for obstacles, which will affect the extraction accuracy; based on laser radar to extract water surface passable areas, Using lidar to collect data on board will cause obvious changes in the collected river bank due to the turbulence of the ship. If the unmanned ship is driving on the water surface, it will be affected by wind, waves, etc., and turbulence will occur, making the radar at a certain moment. The river bank cannot be scanned, causing the river bank point to disappear, which will have a serious impact on the subsequent algorithm for extracting the passable area

Images