Data processing method and apparatus
Example data processing methods and apparatus are provided. One example method includes obtaining an image captured by an in-vehicle camera. A to-be-detected target in the image is determined. A feature region corresponding to the to-be-detected target in the image is further determined based on a location of the to-be-detected target in the image. A first parking state is determined based on the image and wheel speedometer information. A first homography matrix corresponding to the first parking state is determined from a prestored homography matrix set, where different parking states correspond to different homography matrices. Image information of the feature region is processed based on the first homography matrix to obtain a detection result.
1. A data processing method, the data processing method comprising:
obtaining an image captured by an in-vehicle camera;
determining a to-be-detected target in the image;
determining a feature region corresponding to the to-be-detected target in the image based on a location of the to-be-detected target in the image;
determining a first parking state based on the image and wheel speedometer information;
determining a first homography matrix corresponding to the first parking state from a prestored homography matrix set, wherein different parking states correspond to different homography matrices in the prestored homography matrix set; and
processing image information of the feature region based on the first homography matrix to obtain a detection result.
2. The data processing method according to claim 1 , wherein the data processing method further comprises:
determining a first transmit/receive state parameter corresponding to the first parking state from a prestored set of transmit/receive state parameters of a plurality of ultrasonic radars, wherein the first transmit/receive state parameter is any one of single-transmit multi-receive, single-transmit single-receive, or multi-transmit multi-receive.
3. The data processing method according to claim 1 , wherein
the first parking state is a parking space searching state or a vehicle parking state.
4. The data processing method according to claim 3 , wherein;
when the first parking state is the parking space searching state, the first homography matrix is a far-end homography matrix, and the feature region corresponding to the to-be-detected target in the image is a first feature region; or
when the first parking state is the vehicle parking state, the first homography matrix is a near-end homography matrix, and the feature region corresponding to the to-be-detected target in the image is a second feature region, wherein
a distance from a to-be-detected target in the first feature region to a vehicle body is greater than a distance from a to-be-detected target in the second feature region to the vehicle body.
5. The data processing method according to claim 4 , wherein:
when the first parking state is the parking space searching state, the first transmit/receive state parameter is single-transmit single-receive; or
when the first parking state is the vehicle parking state, the first transmit/receive state parameter is single-transmit multi-receive or multi-transmit multi-receive.
6. The data processing method according to claim 1 , wherein the data processing method further comprises:
adjusting a size of the feature region based on different parking environments.
7. The data processing method according to claim 6 , wherein
each parking environment comprises at least one of a weather condition during parking, a ground condition during parking, or an ambient environment of a vehicle during parking.
8. The data processing method according to claim 1 , wherein the to-be-detected target comprises at least one of a parking space or an obstacle.
9. A data processing method, the data processing method comprising:
generating an image;
obtaining detection information based on the image;
sending the detection information;
receiving a first parking state information of a first parking state;
determining a first homography matrix corresponding to the first parking state from a prestored homography matrix set, wherein different parking states correspond to different homography matrices in the prestored homography matrix set; and
processing image information of the image based on the first homography matrix to obtain a detection result.
10. The data processing method according to claim 9 , wherein
the first parking state is a parking space searching state or a vehicle parking state.
11. The data processing method according to claim 10 , the data processing method further comprising:
determining a to-be-detected target according to the image;
determining a feature region corresponding to the to-be-detected target in the image based on a location of the to-be-detected target in the image.
12. The data processing method according to claim 11 , wherein:
when the first parking state is the parking space searching state, the first homography matrix is a far-end homography matrix, and the feature region corresponding to the to-be-detected target in the image is a first feature region; or
when the first parking state is the vehicle parking state, the first homography matrix is a near-end homography matrix, and the feature region corresponding to the to-be-detected target in the image is a second feature region, wherein
a distance from a particular to-be-detected target in the first feature region to a vehicle body is greater than a distance from a particular to-be-detected target in the second feature region to the vehicle body.
13. The data processing method according to claim 11 ,
adjusting a size of the feature region based on different parking environments.
14. The data processing method according to claim 11 , wherein the data processing method further comprises:
adjusting a size of the feature region based on different parking environments.
15. An apparatus, the apparatus comprising:
at least one processor; and
one or more memories coupled to the at least one processor and storing program instructions for execution by the at least one processor to:
obtain an image captured by an in-vehicle camera;
determine a to-be-detected target in the image;
determine a feature region corresponding to the to-be-detected target in the image based on a location of the to-be-detected target in the image;
determine a first parking state based on the image and wheel speedometer information;
determine a first homography matrix corresponding to the first parking state from a prestored homography matrix set, wherein different parking states correspond to different homography matrices in the prestored homography matrix set; and
process image information of the feature region based on the first homography matrix, to obtain a detection result.
16. The apparatus according to claim 15 , wherein the one or more memories stores the program instructions for execution by the at least one processor to:
determine a first transmit/receive state parameter corresponding to the first parking state from a prestored set of transmit/receive state parameters of a plurality of ultrasonic radars, wherein the first transmit/receive state parameter is any one of single-transmit multi-receive, single-transmit single-receive, or multi-transmit multi-receive.
17. The apparatus according to claim 15 , wherein
the first parking state is a parking space searching state or a vehicle parking state.
18. The apparatus according to claim 17 , wherein:
when the first parking state is the parking space searching state, the first homography matrix is a far-end homography matrix, and the feature region corresponding to the to-be-detected target in the image is a first feature region; or
when the first parking state is the vehicle parking state, the first homography matrix is a near-end homography matrix, and the feature region corresponding to the to-be-detected target in the image is a second feature region, wherein
a distance from a to-be-detected target in the first feature region to a vehicle body is greater than a distance from a to-be-detected target in the second feature region to the vehicle body.
19. The apparatus according to claim 18 , wherein
when the first parking state is the parking space searching state, the first transmit/receive state parameter is single-transmit single-receive; or
when the first parking state is the vehicle parking state, the first transmit/receive state parameter is single-transmit multi-receive or multi-transmit multi-receive.
20. The apparatus according to claim 15 , wherein the one or more memories stores the program instructions for execution by the at least one processor to:
adjust a size of the feature region based on different parking environments.
21. The apparatus according to claim 20 , wherein
each parking environment comprises at least one of a weather condition during parking, a ground condition during parking, or an ambient environment of a vehicle during parking.