US 12,020,456 B2
External parameter calibration method, device and system for image acquisition apparatus
Zhiyong Tang, Shanghai (CN); Jiang Peng, Shanghai (CN); and Tao Zhang, Shanghai (CN)
Assigned to Black Sesame Technologies Inc., San Jose, CA (US)
Filed by Black Sesame Technologies Inc., San Jose, CA (US)
Filed on Jan. 26, 2022, as Appl. No. 17/585,213.
Claims priority of application No. 202110179411.1 (CN), filed on Feb. 7, 2021.
Prior Publication US 2022/0254064 A1, Aug. 11, 2022
Int. Cl. G06K 9/00 (2022.01); A61B 5/18 (2006.01); B60W 40/04 (2006.01); B60W 50/06 (2006.01); G06T 7/80 (2017.01)
CPC G06T 7/80 (2017.01) [B60W 40/04 (2013.01); B60W 50/06 (2013.01); B60W 2420/403 (2013.01); B60W 2552/53 (2020.02); G06T 2207/30256 (2013.01)] 10 Claims
OG exemplary drawing
 
1. An external parameter calibration method for an image acquisition apparatus having a camera, comprising:
step a, acquiring images from the image acquisition apparatus, wherein the images comprise reference objects captured by the image acquisition apparatus during a traveling of a vehicle;
step b, dividing the reference objects in the acquired images into a plurality of sections along a road direction the vehicle is travelling, and fitting the reference objects in each of the sections into straight lines;
step c, determining a pitch angle and a yaw angle of the image acquisition apparatus based on vanishing points of straight lines in each of the sections;
step d, filtering sequences of the determined pitch angle and yaw angle along the road direction;
step e, obtaining straight portions in the road from the filtered sequences of the pitch angle and the yaw angle;
step f, storing data of the pitch angle and yaw angle corresponding to the straight portions into a data stack; and
step h, determining a quasi-static calibration external parameter from the pitch angle and the yaw angle in the data stack when a vehicle state data of the vehicle indicates that the vehicle state satisfies a preset requirement;
wherein the vehicle state data is acquired from vehicle-related components for determining a vehicle running environment;
wherein the vehicle state data comprises one or any combination of a speed, a steering wheel angle, and a yaw rate of the vehicle; and
wherein after obtaining the straight portion of the road from the filtered sequence of the pitch angle and the yaw angle, the method further comprises performing steps b to e on the straight portion if an output of the straight portion is not satisfied.