Method for calibrating extrinsic parameters of camera devices, vehicle-mounted device, and storage medium
The present application relates to a field of intelligent driving, and provides a method for calibrating extrinsic parameters of camera devices of a panoramic view system, a vehicle-mounted device, and a storage medium. The method uses the camera devices to shoot multiple preset calibration objects to obtain multiple images, the calibration objects include preset embedded information. Based on the embedded information, information is extracted from each of the multiple images to obtain calibration information of each calibration object in each captured image. Based on the calibration information and intrinsic parameters of each camera device, extrinsic parameters of each camera device are determined. The above method can improve an efficiency and an accuracy of an algorithm of calibrating the extrinsic parameters.
1. A method for calibrating extrinsic parameters of a plurality of camera devices of a panoramic view system, comprising:
obtaining a plurality of images by capturing a plurality of calibration objects using the plurality of camera devices, each of the plurality of calibration objects comprising embedded information;
obtaining calibration information of each of the plurality of calibration objects in each of the plurality of images by extracting information from each of the plurality of images based on the embedded information in each of the plurality of calibration objects; and
determining extrinsic parameters of each of the plurality of camera devices based on the calibration information of each of the plurality of calibration objects and intrinsic parameters of each of the plurality of camera devices.
2. The method according to claim 1 , wherein the embedded information comprises one or more of: first information for indicating a boundary position of each of the plurality of calibration objects, second information for indicating a position of a corner point of each of the plurality of calibration objects, and third information for indicating orientation information of each of the plurality of calibration objects, wherein the orientation information comprises an orientation of each of the plurality of calibration objects relative to a vehicle on which the panoramic view system is installed.
3. The method according to claim 2 , wherein the first information comprises one or more of a first predetermined graphic, a first predetermined color, and a first predetermined symbol; the second information comprises one or more of a second predetermined graphic, a second predetermined color, and a second predetermined symbol; the third information comprises one or more of a third predetermined graphic, a third predetermined color, and a third predetermined symbol.
4. The method according to claim 2 , wherein the obtaining calibration information of each of the plurality of calibration objects in each of the plurality of images by extracting information from each of the plurality of images based on the embedded information in each of the plurality of calibration objects comprises:
determining a first image area corresponding to each of the plurality of calibration objects in each of the plurality of images, such that a plurality of first image areas are determined; and
obtaining the calibration information of each of the plurality of calibration objects by performing a feature extraction and a feature recognition on each of the plurality of first image areas based on one or more of the first information, the second information, and the third information in a corresponding one of the plurality of first image areas, wherein the calibration information of each of the plurality of calibration objects further comprises one or more of the boundary position, the position of the corner point, and the orientation information of each of the plurality of calibration objects.
5. The method according to claim 2 , wherein the embedded information further comprises fourth information, and the fourth information comprises coded information obtained by encoding one or more of a size of the calibration object, a serial number of the calibration object, and a distance and/or an orientation of the calibration object relative to a preset reference object.
6. The method according to claim 5 , wherein the fourth information further comprises one or more of a fourth predetermined graphic, a fourth predetermined color, and a fourth predetermined symbol.
7. The method according to claim 6 , wherein the obtaining calibration information of each of the plurality of calibration objects in each of the plurality of images by extracting information from each of the plurality of images based on the embedded information in each of the plurality of calibration objects comprises:
determining a second image area corresponding to each of the plurality of calibration objects in each of the plurality of images, such that a plurality of second image areas are determined; and
obtaining the calibration information of each of the plurality of calibration object by decoding the fourth information in a corresponding one of the plurality of second image areas, wherein the calibration information of each of the plurality of calibration objects further comprises one or more of a size, a serial number of each of the plurality of calibration objects, a distance and/or an orientation of each of the plurality of calibration objects relative to a preset reference object.
8. The method according to claim 2 , wherein the embedded information further comprises fifth information, and the fifth information provides instruction information to a user, and the fifth information comprises one or more of a fifth predetermined graphic, a fifth predetermined color, and a fifth predetermined symbol.
9. A vehicle-mounted device, comprising a storage device and at least one processor, the storage device storing at least one instruction, which when executed by the at least one processor, causing the at least one processor performing a method for calibrating extrinsic parameters of a plurality of camera devices of a panoramic view system, wherein the method comprises:
obtaining a plurality of images by capturing a plurality of calibration objects using the plurality of camera devices, each of the plurality of calibration objects comprising embedded information;
obtaining calibration information of each of the plurality of calibration objects in each of the plurality of images by extracting information from each of the plurality of images based on the embedded information in each of the plurality of calibration objects; and
determining extrinsic parameters of each of the plurality of camera devices based on the calibration information of each of the plurality of calibration objects and intrinsic parameters of each of the plurality of camera devices.
10. The vehicle-mounted device according to claim 9 , wherein the embedded information comprises one or more of: first information for indicating a boundary position of each of the plurality of calibration objects, second information for indicating a position of a corner point of each of the plurality of calibration objects, and third information for indicating orientation information of each of the plurality of calibration objects, wherein the orientation information comprises an orientation of each of the plurality of calibration objects relative to a vehicle on which the panoramic view system is installed.
11. The vehicle-mounted device according to claim 10 , wherein the first information comprises one or more of a first predetermined graphic, a first predetermined color, and a first predetermined symbol; the second information comprises one or more of a second predetermined graphic, a second predetermined color, and a second predetermined symbol; the third information comprises one or more of a third predetermined graphic, a third predetermined color, and a third predetermined symbol.
12. The vehicle-mounted device according to claim 10 , wherein the obtaining calibration information of each of the plurality of calibration objects in each of the plurality of images by extracting information from each of the plurality of images based on the embedded information in each of the plurality of calibration objects comprises:
determining a first image area corresponding to each of the plurality of calibration objects in each of the plurality of images, such that a plurality of first image areas are determined; and
obtaining the calibration information of each of the plurality of calibration objects by performing a feature extraction and a feature recognition on each of the plurality of first image areas based on one or more of the first information, the second information, and the third information in a corresponding one of the plurality of first image areas, wherein the calibration information of each of the plurality of calibration objects further comprises one or more of the boundary position, the position of the corner point, and the orientation information of each of the plurality of calibration objects.
13. The vehicle-mounted device according to claim 10 , wherein the embedded information further comprises fourth information, and the fourth information comprises coded information obtained by encoding one or more of a size of the calibration object, a serial number of the calibration object, and a distance and/or an orientation of the calibration object relative to a preset reference object.
14. The vehicle-mounted device according to claim 13 , wherein the fourth information further comprises one or more of a fourth predetermined graphic, a fourth predetermined color, and a fourth predetermined symbol.
15. The vehicle-mounted device according to claim 14 , wherein the obtaining calibration information of each of the plurality of calibration objects in each of the plurality of images by extracting information from each of the plurality of images based on the embedded information in each of the plurality of calibration objects comprises:
determining a second image area corresponding to each of the plurality of calibration objects in each of the plurality of images, such that a plurality of second image areas are determined; and
obtaining the calibration information of each of the plurality of calibration object by decoding the fourth information in a corresponding one of the plurality of second image areas, wherein the calibration information of each of the plurality of calibration objects further comprises one or more of a size, a serial number of each of the plurality of calibration objects, a distance and/or an orientation of each of the plurality of calibration objects relative to a preset reference object.
16. The vehicle-mounted device according to claim 10 , wherein the embedded information further comprises fifth information, and the fifth information provides instruction information to a user, and the fifth information comprises one or more of a fifth predetermined graphic, a fifth predetermined color, and a fifth predetermined symbol.
17. A non-transitory computer-readable storage medium having a computer program stored thereon, which when executed by a processor, a method for calibrating extrinsic parameters of a plurality of camera devices of a panoramic view system is implemented, wherein the method comprises:
obtaining a plurality of images by capturing a plurality of calibration objects using the plurality of camera devices, each of the plurality of calibration objects comprising embedded information;
obtaining calibration information of each of the plurality of calibration objects in each of the plurality of images by extracting information from each of the plurality of images based on the embedded information in each of the plurality of calibration objects; and
determining extrinsic parameters of each of the plurality of camera devices based on the calibration information of each of the plurality of calibration objects and intrinsic parameters of each of the plurality of camera devices.
18. The non-transitory computer-readable storage medium according to claim 17 , wherein the embedded information comprises one or more of: first information for indicating a boundary position of each of the plurality of calibration objects, second information for indicating a position of a corner point of each of the plurality of calibration objects, and third information for indicating orientation information of each of the plurality of calibration objects, wherein the orientation information comprises an orientation of each of the plurality of calibration objects relative to a vehicle on which the panoramic view system is installed.
19. The non-transitory computer-readable storage medium according to claim 18 , wherein the first information comprises one or more of a first predetermined graphic, a first predetermined color, and a first predetermined symbol; the second information comprises one or more of a second predetermined graphic, a second predetermined color, and a second predetermined symbol; the third information comprises one or more of a third predetermined graphic, a third predetermined color, and a third predetermined symbol.
20. The non-transitory computer-readable storage medium according to claim 18 , wherein the obtaining calibration information of each of the plurality of calibration objects in each of the plurality of images by extracting information from each of the plurality of images based on the embedded information in each of the plurality of calibration objects comprises:
determining a first image area corresponding to each of the plurality of calibration objects in each of the plurality of images, such that a plurality of first image areas are determined; and
obtaining the calibration information of each of the plurality of calibration objects by performing a feature extraction and a feature recognition on each of the plurality of first image areas based on one or more of the first information, the second information, and the third information in a corresponding one of the plurality of first image areas, wherein the calibration information of each of the plurality of calibration objects further comprises one or more of the boundary position, the position of the corner point, and the orientation information of each of the plurality of calibration objects.