Method for unmanned ship to pass through bridge autonomously

Abstract

The invention discloses a method for an unmanned ship to pass through a bridge autonomously. The method comprises the steps that a microwave radar detects whether an obstacle is in front of the unmanned ship; a main camera in the front of the unmanned ship is used to collect image data, and a horizontal plane saliency target map is acquired from collected images through a saliency test algorithm;a SIFT operator is used to extract the eigenvectors of a saliency region; the eigenvectors are clustered, and a bridge region histogram is established through a word bag method; the histogram is usedto judge whether the obstacle is a bridge region through an SVM model; a three-dimensional laser radar is used to establish a point cloud model to generate a passing path; and finally, the unmanned ship uses combined inertial navigation and a shipboard power system to pass the bridge according to the preset path. According to the invention, the problems that the microwave radar cannot determine whether the bridge region is in front of the unmanned ship and a monocular camera cannot acquire the distance information of the bridge region are solved.

Description

technical field [0001] The invention relates to the technical field of unmanned boat identification, and more specifically, relates to a method for an unmanned boat to autonomously pass a bridge. Background technique [0002] With the promotion of the application of unmanned ships in inland waterways, it is impossible to judge whether the inland bridge area is passable based on traditional lidar and microwave navigation radar. Shipborne microwave navigation radar does not have the ability to recognize three-dimensional space, and cannot distinguish whether the area around the unmanned ship is a bridge area or a non-bridge area. Lidar can judge the bridge area through 3D point cloud data, but the detection distance of lidar is limited. The invention provides a bridge area detection algorithm to judge whether the obstacle area in the river is a passable area, cooperate with the laser radar in the passable area, detect the surrounding environment of the unmanned ship, and reali...

AI Technical Summary

Problems solved by technology

[0002] With the application and promotion of unmanned ships in inland rivers, it is impossible to judge whether the inland bridge area can pass based on traditional laser radar and microwave navigation radar.

Shipborne microwave navigation radar does not have the ability to recognize three-dimensional space, and cannot distinguish whether the area around the unmanned ship is a bridge area or a non-bridge area. Lidar can judge bridge areas through 3D point cloud data, but the detection distance of lidar is limited.

Images