Calibration method of new energy automobile

Abstract

The invention discloses a calibration method for a new energy automobile, and the method comprises the steps: enabling a vehicle-mounted driving camera to collect the images of a front view angle, a rear view angle, a left view angle and a right view angle of a driven-in automobile, carrying out the recognition of the collected images through system software, carrying out the partitioning operation of the images, carrying out the software cutting of the overlapped parts of the partitioned images, and carrying out the recognition of the images. And meanwhile, splicing the four partitioned pictures, identifying ARUCO codes in the partitions, carrying out geometric line connection operation on the retrieved coordinate positions, exiting the calibration mode and resetting the panoramic influence controller. According to the method, the distortion of the fisheye cameras is corrected once according to an actual object, an image seen by a normal person is presented, the overlapped area of the four cameras is divided, four pictures are spliced into a complete image, the calibration precision is further improved, and the calibration time is shortened.

Description

Technical Field

[0001] The present invention relates to the technical field of automobile calibration application, and in particular to a calibration method for a new energy vehicle. Background Art

[0002] In the field of panoramic imaging, multi-camera calibration uses calibration patterns in the common areas of different cameras to match key points, thereby calculating stitching parameters such as position and posture between the multi-cameras, and using these stitching parameters to stitch the photos taken by each camera into a picture or video containing the entire scene. The extraction of calibration pattern key points is the basis of multi-camera panoramic camera calibration.

[0003] Traditional calibration and correction use bar graphs or checkerboards to collect images, and then search one by one based on image pixels, compare the same areas, and perform stitching. This requires a large amount of ECU resources and takes about 10-15 seconds depending on the quality of the image. Therefore, the present invention proposes a calibration method for new energy vehicles. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a calibration method for a new energy vehicle, which can improve the calibration accuracy and the time required for calibration.

[0005] In order to solve the above technical problems, a technical solution adopted by the present invention is: to provide a calibration method for a new energy vehicle, comprising the following steps: Step 1: Image acquisition: The vehicle-mounted driving camera collects images from the front, rear, left and right angles of the vehicle after it enters; Step 2: Screen partitioning: Use system software to identify the captured screen and perform screen partitioning operations; Step 3: Image cropping and splicing: perform software cropping on the overlapping parts of the partitioned images, and splice the four partitioned images at the same time; Step 4: Coordinate connection operation: Identify the ARUCO code inside the partition and perform geometric connection operation on the retrieved coordinate position; Step 5: Exit calibration: Exit calibration mode and reset the panoramic impact controller.

[0006] The present invention is further configured as follows: in step 1, ARUCO codes are arranged in the calibration area in advance, and a number is assigned to each code based on the coordinate system of the entire vehicle, and each number represents a correct coordinate value.

[0007] Through the above technical solution, the entire calibration area can always be quickly numbered around the vehicle position.

[0008] The present invention is further configured as follows: in step 1, the vehicle-mounted driving camera first identifies the ARUCO code of the respective area for preliminary positioning.

[0009] Through the above technical solution, it is convenient to quickly locate the ARUCO codes in the respective areas, thereby improving the operational efficiency for subsequent calibration operations.

[0010] The present invention is further configured as follows: in step one, the following steps are specifically included: first, entering the expansion mode of the system software, secondly, performing security authentication of the data, thirdly, effectively clearing the fault codes that appear, and finally, driving the camera to capture the image.

[0011] Through the above technical solution, when the vehicle enters a certain position, the calibration algorithm system can quickly start and use it, thereby improving efficiency during use and ensuring safety during use.

[0012] The present invention is further configured as follows: in step three, according to the internal shape of the repeated ARUCO code recognized by the two cameras, the image in the area is cropped and spliced, and at the same time, according to the same number recognized by different on-board cameras, the part to be spliced ​​is reduced to reduce the workload of the algorithm, thereby greatly reducing the occupation of the splicing algorithm to EUC and reducing the time consumption.

[0013] Through the above technical solution, multiple repeated areas after partitioning can be quickly cropped and spliced, thereby shortening the calibration time, further improving the efficiency of the algorithm and reducing the occupancy of the ECU.

[0014] The present invention is further configured as follows: in step four, for the areas without repeated numbers identified by different vehicle-mounted cameras, the coordinates corresponding to the numbers are connected, which is equivalent to using straight line connection correction to replace the traditional image edge line fitting, freeing up the occupation of the controller ECU and quickly performing distortion correction of the fisheye camera.

[0015] Through the above technical solution, the vehicle-mounted camera can quickly connect the coordinates of non-repetitive numbers, improve the efficiency of the calibration process, and reduce the occupancy of the controller ECU.

[0016] The present invention is further configured as follows: in step four, the following steps are specifically included: first, the ARUCO code inside each partition is recognized by the camera, then the numbered coordinates assigned to the ARUCO code are retrieved, then several lines are connected to the retrieved coordinates, and rapid calculations are performed through internal algorithms, and finally, the distortion in the image is corrected after the calculation, and the calibrated result is input.

[0017] The above technical solution facilitates fast machine geometry connection calculations using the numbered coordinates assigned by the ARUCO code, thereby improving the accuracy and time required for calibration.

[0018] The present invention is further configured as follows: in step five, the following steps are specifically included: first, the fault code appearing in the corrected image is cleared, then the calibrated mode is exited, and finally the panoramic image controller is reset.

[0019] Through the above technical solution, the current calibration operation is ended, thereby facilitating repeated calibration operations in subsequent vehicles.

[0020] The present invention is further configured as follows: in step 4, it also includes abnormal processing during calibration: If the calibration query result is 0x00, it indicates that the calibration is successful; If the calibration query result is 0x01, wait for the calibration result; If the calibration query result is 0x03, adjust the sensor position to ensure installation accuracy and recalibrate; If the calibration query result is 0x04, it indicates that the calibration has stopped abnormally and the vehicle needs to be checked; If the calibration query result is 0x05, it is in the initial state and can continue calibration.

[0021] Through the above technical solution, when calibrating the coordinates, the meaning of the calibration can be quickly known through the calibration query data, which is convenient for the staff to carry out the next step of operation.

[0022] The beneficial effects of the present invention are as follows: 1. A calibration method for new energy vehicles proposed in the present invention corrects the distortion of the fisheye camera itself by referring to the actual object, thus presenting the image seen by the normal human eye; 2. A calibration method for a new energy vehicle proposed in the present invention divides the overlapping area of ​​four cameras and splices the four pictures into a complete image. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a flow chart of a calibration method for a new energy vehicle of the present invention; Figure 2 It is a schematic diagram of calibration in a calibration method for a new energy vehicle of the present invention. DETAILED DESCRIPTION

[0024] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings so that the advantages and features of the present invention can be more easily understood by those skilled in the art, thereby making a clearer and more definite definition of the protection scope of the present invention.

[0025] like Figure 1 and Figure 2 As shown, a calibration method for a new energy vehicle comprises the following steps: Step 1: Image acquisition: The on-board driving camera acquires images from four perspectives of the front, rear, left and right of the vehicle after it enters. In step 1, the ARUCO code is arranged in the calibration area in advance, and each code is assigned a number based on the coordinate system of the entire vehicle, and each number represents a correct coordinate value, so that the entire calibration area can always be quickly numbered around the vehicle position. In step 1, the on-board driving camera first identifies the ARUCO code of each area for preliminary positioning, which is convenient for quickly locating the ARUCO code of each area, thereby improving the operating efficiency for subsequent calibration operations. In step 1, the following steps are specifically included: first, entering the expansion mode of the system software, secondly, performing data security authentication, and then effectively clearing the fault codes that appear. Finally, the camera is driven to acquire images, so that when the vehicle enters a certain position, the calibration algorithm system can quickly start and use it, thereby improving efficiency in use and ensuring safety in use.

[0026] Step 2: Screen partitioning: Use system software to identify the captured screen and perform screen partitioning operations.

[0027] Step 3: Image cropping and splicing: The overlapping parts of the partitioned images are cropped by software, and the four partitioned images are spliced. In step 3, the images in the area are cropped and spliced ​​according to the internal shapes of the repeated ARUCO codes recognized by the two cameras. At the same time, according to the same numbers recognized by different on-board cameras, the parts that need to be spliced ​​are reduced to reduce the workload of the algorithm, thereby greatly reducing the occupancy of the splicing algorithm on the EUC and reducing the time consumption. It can quickly crop and splice multiple repeated areas after partitioning, thereby shortening the calibration time, further improving the efficiency of the algorithm and reducing the occupancy of the ECU.

[0028] Step 4: Coordinate connection operation: Identify the ARUCO code inside the partition and perform geometric connection operation on the retrieved coordinate position. In step 4, connect the coordinates corresponding to the number for the areas with non-repeated numbers identified by different on-board cameras, which is equivalent to using straight line connection correction to replace the traditional image edge line fitting, freeing up the occupation of the controller ECU, and quickly performing distortion correction of the fisheye camera, so that the on-board camera can quickly connect the coordinates without repetitive numbers, improve the efficiency of the calibration process, and reduce the occupation of the controller ECU. In step 4, the following steps are specifically included: first, the ARUCO code inside each partition is recognized by the camera, and then the assigned The numbered coordinates of the ARUCO code are retrieved, and then the retrieved coordinates are connected several times, and the internal algorithm is used for rapid calculation. Finally, the distortion in the image is corrected after the calculation, and the calibrated result is input, so as to facilitate the rapid machine geometry connection calculation through the numbered coordinates assigned by the ARUCO code, thereby improving the accuracy and time required for calibration. In step five, the following steps are specifically included: first, the fault code appearing in the corrected image is cleared, then the calibrated mode is exited, and finally the panoramic image controller is reset to end the calibration operation, so as to facilitate repeated calibration operations in subsequent vehicles. In step four, abnormal handling during calibration is also included: If the calibration query result is 0x00, it indicates that the calibration is successful; If the calibration query result is 0x01, wait for the calibration result; If the calibration query result is 0x03, adjust the sensor position to ensure installation accuracy and recalibrate; If the calibration query result is 0x04, it indicates that the calibration has stopped abnormally and the vehicle needs to be checked; If the calibration query result is 0x05, it is in the initial state and can continue calibration; It is convenient to calibrate the coordinates so that the meaning of the calibration can be quickly understood through the calibration query data, which is convenient for the staff to carry out the next step of operation.

[0029] Step 5: Exit calibration: Exit calibration mode and reset the panoramic impact controller.

[0030] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A calibration method for a new energy vehicle, characterized in that: The following steps are involved: Step 1: Image acquisition: The vehicle-mounted driving camera collects images from the front, rear, left and right angles of the vehicle after it enters; Step 2: Screen partitioning: Use system software to identify the captured screen and perform screen partitioning operations; Step 3: Image cropping and splicing: perform software cropping on the overlapping parts of the partitioned images, and splice the four partitioned images at the same time; Step 4: Coordinate connection operation: Identify the ARUCO code inside the partition and perform geometric connection operation on the retrieved coordinate position; Step 5: Exit calibration: Exit calibration mode and reset the panoramic impact controller.

2. A calibration method for a new energy vehicle according to claim 1, characterized in that: In step 1, ARUCO codes are arranged in the calibration area in advance, and each code is assigned a number based on the coordinate system of the entire vehicle, and each number represents a correct coordinate value.

3. A calibration method for a new energy vehicle according to claim 2, characterized in that: In step 1, the vehicle-mounted driving camera first identifies the ARUCO code of the respective area for preliminary positioning.

4. A calibration method for a new energy vehicle according to claim 1, characterized in that: In step one, the following steps are specifically included: first, entering the expansion mode of the system software, secondly, performing data security authentication, thirdly, effectively clearing the fault codes that appear, and finally, driving the camera to capture the image.

5. The calibration method of a new energy vehicle according to claim 1, characterized in that: In step three, the images in the area are cropped and spliced ​​according to the internal shapes of the repeated ARUCO codes recognized by the two cameras. At the same time, according to the same numbers recognized by different on-board cameras, the parts that need to be spliced ​​are reduced to reduce the workload of the algorithm, thereby greatly reducing the stitching algorithm's occupancy of EUC and reducing time consumption.

6. A calibration method for a new energy vehicle according to claim 1, characterized in that: In step 4, for the areas without repeated numbers identified by different vehicle-mounted cameras, the coordinates corresponding to the numbers are connected, which is equivalent to using straight line connection correction instead of traditional image edge line fitting, freeing up the controller ECU and quickly performing distortion correction of the fisheye camera.

7. A calibration method for a new energy vehicle according to claim 1, characterized in that: In step four, the following steps are specifically included: first, the ARUCO code inside each partition is recognized by the camera, then the numbered coordinates assigned to the ARUCO code are retrieved, then several lines are connected to the retrieved coordinates, and rapid calculations are performed through internal algorithms, and finally, the distortion in the image is corrected after the calculation, and the calibrated result is input.

8. The calibration method of a new energy vehicle according to claim 1, characterized in that: In step five, the following steps are specifically included: first, the fault code appearing in the corrected image is cleared, then the calibrated mode is exited, and finally the panoramic image controller is reset.

9. A calibration method for a new energy vehicle according to claim 7, characterized in that: In step 4, exception handling during calibration is also included: If the calibration query result is 0x00, it indicates that the calibration is successful; If the calibration query result is 0x01, wait for the calibration result; If the calibration query result is 0x03, adjust the sensor position to ensure installation accuracy and recalibrate; If the calibration query result is 0x04, it indicates that the calibration has stopped abnormally and the vehicle needs to be checked; If the calibration query result is 0x05, it is in the initial state and can continue calibration.

Images