Automatic calibration method and system for spatial position of laser radar and camera sensor

An automatic calibration system for spatial positions of a laser radar and a camera sensor, comprising:

• the laser radar, the camera sensor and a spatial position calibration module;
• the spatial position calibration module is configured to:
• adjust a spatial position of the laser radar relative to the camera sensor to obtain a plurality of spatial position relationships of the laser radar and the camera sensor;
• for a spatial position relationship, screen out data conforming to line features from laser radar point cloud data, screen out data conforming to the line features from image data of the camera sensor, project laser radar data conforming to the line features onto a pixel coordinate system of the camera sensor to calculate a gray value of a laser radar point conforming to the line features after projection as a score, and accumulate scores of all laser radar points as a total score;
• traverse all the spatial position relationships to obtain a plurality of total scores;
• and
• select a spatial position relationship of the laser radar and the camera sensor corresponding to a highest total score from the plurality of total scores to serve as a calibrated position relationship of the laser radar and the camera sensor;
• wherein, the step of screening out data conforming to the line features from the laser radar point cloud data specifically comprises:
• acquiring a plurality of beams of laser radar data;
• and
• for laser radar points in each beam, when a distance change of two adjacent laser radar points is larger than a threshold, removing a farther laser radar data point to screen out data conforming to line features;
• wherein, the step of screening out data conforming to the line features from the image data of the camera sensor specifically comprises:
• acquiring image data collected by the camera sensor and converting the image data to a grayscale map;
• detecting the grayscale map with an edge detection algorithm to obtain an edge feature image;
• filtering the edge feature image to leave vertical and horizontal features;
• and
• smoothing the edge feature image using Gaussian filter to obtain the image data conforming to the line features;
• wherein, the step of adjusting the spatial position of the laser radar relative to the camera sensor specifically comprises:
• fixing the camera sensor, and
• adjusting the spatial position of the laser radar according to any one or any combination of the following six degrees of freedom,
• wherein the six degrees of freedom comprise:
• moving along an x axis, moving along a y axis, moving along a z axis, rotating along the x axis, rotating along the y axis and rotating along the z axis, wherein the x axis, the y axis and the z axis are three coordinate axes of a body coordinate system of the camera sensor.

An automatic calibration method for spatial positions of a laser radar and a camera sensor, comprising:

• screening out laser radar data conforming to line features from a laser radar point cloud data;
• and screening data conforming to line features from image data of a camera sensor;
• projecting the laser radar data conforming to line features onto a pixel coordinate system of the camera sensor, calculating gray values of a plurality of laser radar points conforming to line features after projection to accumulate the gray values of all the laser radar points conforming to line features after projection and recording the sum as A;
• and accumulating maximum gray values of all the laser radar points conforming to line features after projection and recording the sum as B;
• and
• judging whether the value of A/B is greater than 0.9, if so, then the spatial position of each of the laser radar and the camera sensor is accurate, otherwise, the spatial position of each of the laser radar and the camera sensor is not accurate;
• adjusting the spatial position of the laser radar relative to the camera sensor to obtain a plurality of spatial position relationships between the laser radar and camera sensor;
• for a spatial position relationship, screening out laser radar data conforming to line features from the laser radar point cloud data;
• screening data conforming to line features from the image data of the camera sensor;
• projecting the laser radar data conforming to line features onto a pixel coordinate system of a camera sensor to calculate each gray value of each laser radar point of a plurality of laser radar points conforming to line features after projection as a score, and accumulating the scores of all the laser radar points as a total score;
• and traversing all the spatial position relationships to obtain a plurality of total scores;
• and
• selecting the spatial position relationship of the laser radar and the camera sensor corresponding to a highest total score from the plurality of total scores, to serve as a calibrated position relationship of the laser radar and the camera sensor.