Unstructured road detection method based on adaptive edge registration
An unstructured, road detection technology, applied in the direction of image data processing, instruments, calculations, etc., can solve the problem that the shape of the road cannot be accurately modeled, a large number of problems, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0039] An unstructured road detection method based on adaptive edge registration, which is a registration method of Otsu edge and weighted Canny edge. figure 1 The left picture in the figure is the original image of the gravel road collected by the intelligent vehicle, and the right picture is the Canny edge image, which is used as a scale to measure the image segmentation. The specific method is:
[0040] (1) Weighted Canny edge detection
[0041] In the double-threshold detection stage, the gradient magnitude of the identified edge pixels is recorded, and the length, angle, distance and average magnitude strength of the polyline segment are used to jointly characterize the irregular boundary of the unstructured road;
[0042] In the double-threshold detection stage, the connected edge points are uniformly numbered, and after the numbering is completed, the least square method is used to fit the straight line to find the axis of the edge point set with the same number;
[0...
Embodiment 2
[0055] With reference to the detection method of embodiment 1, wherein, Figure 5 The left image is the original image of the dirt road collected by the intelligent vehicle. Figure 5 The right figure of is the road segmentation result of the edge registration method of the present invention; Figure 6 The left picture of is the road segmentation result based on the maximum entropy threshold method, Figure 6 The right figure of the figure is the road segmentation result of the standard Otsu threshold method. Obviously, the latter two methods are affected by the road shadow to segment the road into two parts, while the detection method of the present invention can segment the road very well.
Embodiment 3
[0057] With reference to the detection method of embodiment 1, wherein, Figure 7 The left picture in the figure is the original image of the cement road with light and shadow distribution collected by the intelligent vehicle. Figure 7 The right figure is the road segmentation result diagram of the edge registration method of the present invention; Figure 8 The left picture shows the road segmentation result of the maximum entropy threshold method. Figure 8 The image on the right shows the road segmentation results of the standard Otsu threshold method. The maximum entropy threshold method is greatly affected by shadows, the standard Otsu threshold method is less affected by shadows, and the edge registration method of the present invention is least affected by light and shadow.
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 