Lane line identification method based on double-camera image fusion

Lane line identification method based on double-camera image fusion

  • CN 104,899,858 A
  • Filed: 02/15/2015
  • Published: 09/09/2015
  • Est. Priority Date: 02/15/2015
  • Status: Active Application
First Claim
Patent Images

1. , based on the Lane detection system of twin camera image co-registration, it is characterized in that comprising following step:

  • Step 1;

    install monocular-camera below the side mirror of left and right vehicle wheel, the camera lens of video camera rushes ahead below;

    Step 2-1;

    left video camera is demarcated, require that the scope of the visual field transaxial width of the general view after inverse perspective mapping is 150cm--250cm, the scope of longitudinal axis width is 500cm--1000cm;

    The scope of described visual field transaxial width refers to that outside vehicle left side front and back wheel, line is with the field range on a left side;

    The scope of described visual field longitudinal axis width refers to the field range of vehicle front;

    Step 2-2;

    right video camera is demarcated, require that the scope of the visual field transaxial width of the general view after inverse perspective mapping is 150cm--250cm, the scope of longitudinal axis width is 500cm--1000cm;

    The scope of described visual field transaxial width refers to that outside vehicle right side front and back wheel, line is with the field range on the right side;

    The scope of described visual field longitudinal axis width refers to the field range of vehicle front;

    Step 2-1 is consistent with the field range in step 2-2;

    The order of step 2-1 and step 2-2 can be exchanged;

    Step 3-1;

    obtain vehicle left side pavement image L_image from left video camera, first gray processing process is carried out to image L_image and obtain gray level image L_gray, then self-adaption binaryzation process is carried out to image L_gray and obtain binary image L_binary, again inverse perspective mapping is carried out to image L_binary and obtain general view as L_bird-view, finally the conversion of Hough straight line is carried out to image L_bird-view, all straight lines in detected image L_bird-view, and the width L_width of the rule calculated line of linear correlation and the angle L_rho of level and straight line is presented according to the distance of general view picture, when satisfied 30 °



    L_rho≤

    150 °

    , then think during 12cm≤

    L_width≤

    30cm that this straight line is candidate'"'"'s straight line of vehicle left side lane line,Step 3-2;

    obtain vehicle right side pavement image R_image from right video camera, first gray processing process is carried out to image R_image and obtain grey image R _ gray, then self-adaption binaryzation process is carried out to image R_gray and obtain binary image R_binary, again inverse perspective mapping is carried out to image R_binary and obtain general view as R_bird-view, finally the conversion of Hough straight line is carried out to image R_bird-view, all straight lines in detected image R_bird-view, and the width R_width of the rule calculated line of linear correlation and the angle R_rho of level and straight line is presented according to the distance of general view picture, when satisfied 30 °



    R_rho≤

    150 °

    , then think during 12cm≤

    R_width≤

    30cm that this straight line is candidate'"'"'s straight line of vehicle right side lane line,The order of 3-1 and step 3-2 can be exchanged;

    Step 3-3;

    the result of step 3-1 and step 3-2 is merged;

    The principle parallel according to left and right vehicle wheel lane line, the angle L_rho of known left-hand lane line is equal with the angle R_rho of right-hand lane line, the existence of permissible error, when meeting | and then think it may is left and right lane line during L_rho-R_rho|≤

    5 °

    , judge further;

    According to the principle that track is wide, the distance of left and right lane line is fixing or in some scopes, the lane width scope of urban road, at 300cm--375cm, when the spacing of left and right candidate lane line meets lane width, then thinks left and right lane line.

View all claims
    ×
    ×

    Thank you for your feedback

    ×
    ×