Point cloud map construction method, device and equipment

Abstract

The invention discloses a point cloud map construction method, device and equipment, and the method comprises the steps: obtaining the feature point information of a plurality of frames of images, the first speed information of a vehicle, and the positioning information of the vehicle, and the feature point information comprises the feature points of each frame of image and the matching relation of the inter-frame feature points; the first speed information of the vehicle comprises a first linear speed and / or a first angular speed of the vehicle, and the first speed information is measured through a wheel speed sensor; determining first pose information of the vehicle according to the feature point information and the first speed information; determining second pose information of the vehicle according to the first pose information and the positioning information of the vehicle; and performing point cloud reconstruction by using the feature point information of the multi-frame image and the second pose information to obtain a point cloud map. According to the method, the linear speed and / or the angular speed of the vehicle are / is obtained through measurement of the wheel speed sensor, the speed information of the vehicle is measured instead of an IMU, noise introduced by IMU measurement is avoided, meanwhile, erection and arrangement of the IMU are avoided, and the production cost is saved.

Description

technical field [0001] The present application relates to the fields of computer vision and point cloud map construction, in particular to a point cloud map construction method, device and equipment. Background technique [0002] For automatic driving, the acquisition of positioning information is very important. Accurately locating the current position of the vehicle and the objects in the surrounding environment of the vehicle, and simulating the roads and surrounding environment on both sides of the vehicle can improve the accuracy of automatic driving. When building a map of the roads on both sides of the vehicle, the sensors on the vehicle, such as cameras and inertial measurement units (Inertial Measurement Unit, IMU), will collect real-time information around the vehicle, such as vehicle speed information, surrounding moving objects, pedestrians, Trees, grass, etc., and then send the collected information to the server. [0003] The server will build a map of the sur...

AI Technical Summary

Problems solved by technology

[0003] The server will build a map of the surrounding environment of the vehicle based on the measurement data reported by each sensor, but the reported original data is easily affected by the surrounding environment, such as noise interference, buildings, natural objects, etc., resulting in inaccurate positioning results of the vehicle pose, and then in When using this inaccurate vehicle pose for mapping, the matching information is not robust

Images