Unlock instant, AI-driven research and patent intelligence for your innovation.

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.

Active Publication Date: 2013-10-16
南京物联网研究院发展有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The road area detected by this type of method is relatively complete, but it cannot establish an accurate model for complex road surface shapes
The neural network method uses the learning characteristics of the neural network and does not require prior knowledge of the road, but the result of road recognition depends on the samples used in training, requiring a large number of training sets

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Unstructured road detection method based on adaptive edge registration
  • Unstructured road detection method based on adaptive edge registration
  • Unstructured road detection method based on adaptive edge registration

Examples

Experimental program
Comparison scheme
Effect test

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.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an unstructured road detection method based on adaptive edge registration. The method is the registering method of an Otsu edge and a weighted Canny edge. The method comprises the following steps: weighted Canny edge detection, Otsu threshold optimization and weight revaluation of the Canny edge. Compared to the prior art, the unstructured road detection method based on the adaptive edge registration of the invention has the following advantages that: the registration of the Otsu edge and the weighted Canny edge is taken as a core so that precision of road area segmentation and boundary tracking can be increased; unstructured road identification experiments in different scenes show that influences of unfavorable factors, such as a road defect, a shadow, illumination change and the like can be effectively overcome by using the detection method; the method has good practicality and good economic benefits and social benefits can be generated by using the method.

Description

technical field [0001] The invention relates to an unstructured road detection method for autonomous navigation of intelligent vehicles, in particular to an unstructured road detection method based on adaptive edge registration. Background technique [0002] Vision-based unstructured road detection is one of the hotspots in the research of intelligent vehicle autonomous navigation. Compared with the navigation method based on multi-sensor information fusion, the visual navigation method with road detection as the core undoubtedly provides a cheaper solution. Take the Grand Challenge Intelligent Vehicle Off-Road Challenge organized by the U.S. Defense Advanced Research Projects Agency (DARPA) as an example. Most of the vehicles participating in the competition are equipped with expensive non-visual sensor systems, which cost far more than the car itself. Later, the application of this research in the civilian field has buried hidden dangers. Due to the constraints of the de...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T5/00G06T7/00
Inventor 王燕清辛柯俊邹涛李钢吴剑
Owner 南京物联网研究院发展有限公司