Road border detection method based on infrared image

A boundary detection and infrared image technology, applied in the field of image analysis and computer vision, can solve problems such as difficult application, and achieve the effect of real-time processing, reduced resolution, and low time complexity

CN102122344AInactive Publication Date: 2011-07-13NANJING UNIV OF SCI & TECH
2 Cites 26 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
Publication Date
2011-07-13
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a road border detection method based on an infrared image, comprising the following steps: converting an input image into an image with specific scale and size by proper pretreatment; selecting a line segment more than a certain length under each threshold value by a threshold value exhaust algorithm; analyzing the line segment to obtain an accurate gradient; removing a second-order differential operator to obtain a weak line segment; removing a pseudo line segment obtained by the threshold value exhaust algorithm via the second-order differential operator; mutually combining two line segments to jointly extract the border line segment; and finally, obtaining a final road border according to a road border model. With the method, the road border can be accurately and uninterruptedly detected day and night, the method has the advantages of high instantaneity and robustness, and is easy to popularize to application fields of intelligent robot navigation, the active safety of automobiles, video monitoring and the like.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the fields of computer vision and image analysis, in particular to a road boundary detection method based on infrared images. Background technique

[0002] Intelligent vehicle navigation is an important research topic of pattern recognition and artificial intelligence. It has received extensive attention both at home and abroad in the past two decades, and has great theoretical and application value. The detection of natural road boundaries can provide the most basic navigation information for intelligent vehicles. In the past, road border detection methods generally used visible light sensors on two-dimensional visible light images (Fardi B., Wanielik G., Hough transformation based approach for road border detection in infrared images. IEEE Intelligent Vehicles Symposium 2004). However, visible light images are easily affected by uneven lighting and road shadows, and are difficult to apply at night. In recent years, with the...

Examples

Embodiment Construction

[0019] The present invention is based on the road boundary detection method of infrared image, and its steps are:

[0020] The first step: image preprocessing, designate the region of interest in the image, and perform median filter processing after reducing the resolution to improve the consistency of the road area, and reduce the processing area without reducing the detection accuracy, saving processing time.

[0021] Manually specify a rectangular area on the image, so that the rectangular area contains the left and right road boundaries as much as possible, and at the same time excludes the non-road boundaries as much as possible. The image row coordinate Y1 on the upper side of the rectangular area is set according to the farthest distance requirement for road boundary line detection. The image row coordinate Y2 below is set as the row coordinate of the front end on the image, the image column coordinates on the left and right sides are respectively set to X and Width-X (W...