Method and device for determining a headstock orientation angle
A technology of head orientation and angle, which is applied in the field of image processing, and can solve problems such as the inability to accurately determine the angle of the head of the car, the inability to determine the angle of the head of the car, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0079] figure 1 It is a schematic diagram of the process of determining the heading angle of the vehicle head provided by the embodiment of the present invention, and the process includes the following steps:
[0080] S101: Input the obtained first image into a pre-trained vehicle detection model.
[0081] The method for determining the heading angle of the vehicle head provided by the embodiment of the present invention is applied to an electronic device, and the electronic device may be a PC, a tablet computer or the like, or may be an image acquisition device.
[0082] The pre-trained vehicle detection model is stored in the electronic device. If the electronic device is an image acquisition device, the electronic device will directly input the first image after collecting the image of the angle of the vehicle head to be determined, which is the first image. in the vehicle detection model. If the electronic device is a PC, a tablet computer, etc., after the image acquisit...
Embodiment 2
[0099] In order to make the determined target vehicle area more accurate, on the basis of the above embodiments, in the embodiment of the present invention, after each target vehicle area in the first image is determined, each target vehicle area is input into the pre-training Before completing the angular regression model, the method also includes:
[0100] Taking the vertical midline of the first image as an axis, performing mirroring processing on the first image to obtain a mirrored image;
[0101] Input the mirrored image into the pre-trained vehicle detection model, determine each second vehicle area in the mirrored image based on the vehicle detection model, and for any two second vehicle areas, according to The overlapping area of the two second vehicle areas determines the third vehicle area corresponding to the two second vehicle areas; according to the preset area mapping relationship, each third vehicle area in the mirrored image is mapped into the first image, ...
Embodiment 3
[0119] On the basis of the above-mentioned embodiments, in the embodiment of the present invention, before performing image processing on the first image, the method further includes:
[0120] Determine whether the number of target vehicle areas is greater than one, and if yes, perform subsequent steps.
[0121] Before mirroring the first image, the electronic device first recognizes the number of target vehicle areas in the first image, and judges whether the number of target vehicle areas in the first image is greater than one, and if so, mirrors the first image deal with.
[0122] If the number of target vehicle areas is one, performing mirroring processing on the first image includes:
[0123] Perform mirroring processing on the target vehicle area in the first image.
[0124] If the number of the target vehicle area is one, the pixels outside the target vehicle area in the first image have no effect on determining the vehicle area in the mirrored image. In order to redu...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


