Identification method, identification device, computer readable storage medium and vehicle
An identification method and lane line identification technology are applied in the fields of identification, identification devices, computer-readable storage media and vehicles, and can solve problems such as hidden dangers of automatic driving and the inability to accurately identify lane lines by edge detection methods.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0068] like Figure 16 As shown, this embodiment provides a method for identifying lane lines:
[0069] Step S102, performing camera calibration on the original picture including the lane line and the background, and obtaining the calibration result;
[0070] Step S104, extracting the region of interest from the calibration result and performing perspective transformation to obtain a perspective picture;
[0071] Step S106, based on the lane line recognition support vector machine model, establish a classification plane of the perspective picture, so as to classify each pixel in the perspective picture according to the classification plane, and obtain a classification result;
[0072] In step S108, the classification result is represented by a binary image to draw the lane line recognition result;
[0073] In step S110, the lane line recognition result is subjected to inverse perspective transformation and inverse camera calibration, so as to identify lane lines.
[0074] T...
Embodiment 2
[0082] like Figure 17 As shown, this embodiment provides a lane line recognition method. In addition to the technical features of the above-mentioned embodiment 1, this embodiment further includes the following technical features.
[0083] Extract the region of interest from the calibration results and perform perspective transformation to obtain perspective pictures, including:
[0084] Step S202, extracting the region of interest from the calibration result to obtain multiple pixel points;
[0085] Step S204, obtaining the color channel vector of each pixel;
[0086] Step S206, mapping the color channel vectors into the color space to perform perspective transformation to obtain a perspective picture.
[0087] In this embodiment, the region of interest is extracted from the camera calibration results to obtain multiple pixels, and then obtain the color channel vectors of multiple pixels, map the color channel vectors to the color space for perspective transformation, and ...
Embodiment 3
[0089] like Figure 18 As shown, this embodiment provides a lane line recognition method. In addition to the technical features of any of the above embodiments, this embodiment further includes the following technical features.
[0090] The classification results are represented by a binary image to draw the lane line recognition results, including:
[0091] Step S302, performing histogram statistics on the binary image obtained based on the classification result to calculate the expected starting position of the lane line;
[0092] Step S304, using the sliding window technique, starting from the expected starting position of the lane line, drawing the recognition result of the lane line.
[0093] In this embodiment, histogram statistics are performed on the classification results of pixels obtained by using the classification plane to calculate the expected starting position of the lane line and improve the accuracy of lane line recognition. Further, by using the sliding wind...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


