JP3589293B2 - Road white line detection method - Google Patents

Description

【００１６】
３．エッジ検出
白線が存在する範囲を、画面の下半分の領域に限定する。以下の処理は、画面の下半分の領域に対してのみ実行する。
３．１ 画素エッジ強度を計算
空間微分（差分）をもとに、位置（ｘ，ｙ）のエッジ強度（Ｉｎｔｅｎｓｉｔｙ）を下記の通り定義し、これを用いてエッジ検出を行う。
【００１７】
エッジ強度＝（Ｉｍ［ｙ］［ｘ＋３］＋Ｉｍ［ｙ］［ｘ＋２］―Ｉｍ［ｙ］［ｘ−２］―Ｉｍ［ｙ］［ｘ−３］）／１０
エッジ強度を表す空間を「エッジ空間」という。
なお、この式は、一次元Ｐｒｅｗｉｔｔ型空間微分（−１ ０ １）の注目点周辺５画素分の平均値をとったものと等価な式となっている。
３．２ エッジ検出
エッジ空間上で、極値を示す画素を選択することにより、エッジを検出する。選択されたエッジは、各々±の符号付き値を持ち、これに基づいて、以後の処理でグループ分けされる（後述）。
【００１８】
ただし、路面ノイズなどの影響を排除するため、極値探索対象範囲を限定できるように工夫している。具体的には、画面下半分のエッジ強度の平均値と、標準偏差を計算し、下記範囲の外を極値探索対象範囲としている。
上限：エッジ強度の平均値＋１．５×標準偏差
下限：エッジ強度の平均値−１．５×標準偏差
エッジ空間上のエッジ強度分布が正規分布に従うとすると、前記範囲には、全画素の約８６．６％が含まれ、結果として、上部の極値探索対象範囲と下部の極値探索対象範囲に含まれる、それぞれ約６．７％の画素から、極値となる画素を抽出することになる。これにより、処理のスピードアップを図れる。
【００１９】
４．白線候補の抽出
前項で抽出されたエッジを下記の手順に従いグループ分けして白線候補（ひと塊の白線の部分）を抽出する。
（１）画像最下段のエッジを白線候補の始点Ｇ０として登録する。
（２）白線候補始点Ｇ０の近傍画素であって、白線候補始点Ｇ０の強度と類似する強度のエッジを新たな白線候補Ｇとして登録する。以下、この処理を繰り返す。
このようにして、白線候補始点Ｇ０及びこれに関連して登録された白線候補Ｇにより、白線候補を構成する。
【００２０】
近傍画素は、最大３段上までのラインから探索する。３ラインを超えたときは、別の白線始点として登録する。
横方向の探索範囲は、（探索ラインまでの距離）×（±３画素）とする。例えば、１ライン上にエッジがなく、２ライン目を探索する場合、±６画素を探索する。式で書くと、（ｘ，ｙ）位置を基準として、２ライン上なら、（ｘ−６，ｙ−２）から（ｘ＋６，ｙ−２）までを探索する。
【００２１】
前記強度の類似判定は、白線候補始点Ｇ０のエッジ強度の±５０％以内かどうかで行う。
５．白線候補のグループ化
前項で抽出された白線候補を、下記の手順に従いグループ化する。
（１）構成画素数が一定以上の白線候補について、左側白線、右側白線の選別をする。なお、左右白線の存在位置が入れ替わる車線変更時でも極力追従できるよう、左右白線の探索領域はオーバーラップさせている。
【００２２】
具体的には、白線候補の構成画素数の下限は３とする。
白線候補始点Ｇ０のｘ座標が１６０＋α以下、かつ、エッジ強度が負であれば、左側白線の右端と判断し、白線候補始点Ｇ０のｘ座標が１６１−α以上、かつ、エッジ強度が正であれば、右側白線の左端と判断する。ここで、「１６０」という座標は、ｘ方向の縮小後の画像サイズが６４０／２＝３２０画素あるという前提で、半分の位置に設定している。
【００２３】
αは、オーバーラップを考慮したもので、ｘ方向の画像サイズの約１０％（３２画素）としている。
（２）下（ｙ座標の大きいもの）から順に、白線候補をグループ化していく。その条件は、（ａ）下にある基準となる白線候補を延ばした直線と、検査対象となっている白線候補の始点との関係が結合範囲にあること、（ｂ）両直線の傾きの差θが所定角度範囲以内であること、である。
【００２４】
前記「結合範囲」とは、図３（ａ）に示すように、検査対象となっている白線候補２の始点Ｇ０から水平方向に引いた線分Ｌと、下にある基準となる白線候補を延ばした直線とが交わる点をＰとすると、長さＧ０Ｐが、±所定数の画素の範囲とする。ただし、ＰがＧ０より右側にあるときは正、ＰがＧ０より左側にあるときは負とする。図３（ａ）では所定数を１０としている。
前記「所定角度範囲」とは、図３（ｂ）に示すように、前記点Ｐが、始点Ｇ０の右にある場合、−５°〜＋２０°とし、図３（ｃ）に示すように、左にある場合は、−２０°〜＋５°とする。
【００２５】
６．三次元座標変換
画面を下記の式を用いて、白線グループの始点Ｇ０を実空間座標に３次元座標変換する。
Ｚ（車両進行方向距離）＝Ｄｉｖｉｄｅｎｄ（η，ｓｉｎψ，ｃｏｓψ）／Ｄｉｖｉｄｅｒ（η，ｓｉｎψ，ｃｏｓψ）
Ｘ（車両横方向距離）＝Ｃｏｎｖ２Ｘ（ξ，Ｚ）
Ｃｏｎｖ２Ｘ（ξ，Ｚ）＝（ξ／Ｆ）［（Ｚ ｃｏｓψ）＋（Ｈ ｓｉｎψ）］
Ｄｉｖｉｄｅｒ（η， ｓｉｎψ，ｃｏｓψ）＝ｓｉｎψ−（η／Ｆ）ｃｏｓψ
Ｄｉｖｉｄｅｎｄ（η，ｓｉｎψ，ｃｏｓψ）＝Ｈ［ｃｏｓψ＋（η／Ｆ）ｓｉｎψ］
Ｈ：カメラの設置高さ（ｍ）
Ｆ：レンズ焦点距離（ｍ）
ψ：カメラ光軸の俯角（ｒａｄ）
ξ，ηは、撮像面中心（原点）からの距離（ｍ）を表す（ｙ軸は上方が正、ｘ軸は右向きが正）。
【００２６】
図４は、３次元座標変換前後の画像を示す図であり、（ａ）はカメラで撮像したエッジ画像を示す図、（ｂ）は３次元座標変換後の画像を示す図である。
７．最も信頼性の高い左右白線の抽出
グループ化された白線候補の中から、左右白線を１本ずつ抽出する。図５は、実空間における複数の白線グループを示す図である。図６は、本項の手順を説明するためのフローチャートである。
【００２７】
（１）３次元座標変換した場合の白線候補始点Ｇ０が、横方向±４ｍ以内、前方３０ｍ以内（図５の太線枠参照）にあるもののうち、３次元座標変換した場合の白線候補の長さＬ１，Ｌ２，‥‥が最大のものを抽出する（ステップＳ６６）。
（２） ３次元座標変換前の画面について、構成画素数が一定数（例えば５とする）以上の白線候補を選択して、ハフ（Ｈｏｕｇｈ）変換パラメータを算出する（ステップＳ６７）。
【００２８】
ここでハフ変換とは、ｘｙ直交座標系で表した直線
ｘｃｏｓθ＋ｙｓｉｎθ＝ｒ
を（ｒ，θ）平面に変換することをいう。極座標の原点は、左側白線候補の場合図７（ａ）に示すように画面の左上とし、右側白線候補の場合図７（ｂ）に示すように画面の右上とする。ハフ変換パラメータをｒ，θとする。点線は前回撮影した画面から抽出した白線、実線は今回撮影した画面から抽出した白線であり、図７では、取得時刻の異なる２つの白線を同時に描いている。
【００２９】
（３） ハフ変換パラメータをもとにして、前回検出した白線候補との類似度を求め、類似度が最も高いものを今回の白線候補として左右別々に抽出する（ステップＳ６２）。
類似度を判断するのに、判定値
１００｜θ０−θ１｜＋｜ｒ０−ｒ１｜
を採用する。ｒ０，θ０は前回の白線候補のハフ変換パラメータであり、ｒ１，θ１は今回の白線候補のハフ変換パラメータである。「１００」は重み係数（一定とする）である。この判定値が小さい方が類似度が高い。
【００３０】
前記判定値が３０を超えた場合は、白線位置を見失ったと判断する（ステップＳ６３のＮＯ）。このときは、ステップＳ６６に飛び、改めて（１）の方式で最適候補を探索し直す。
なお、図６で白線位置を見失ったときには、ステップＳ６６に進まず、ハフ変換パラメータを捨てて、次のサイクルでステップＳ６６からスタートしてもよい。
【００３１】
このようにして抽出された左右白線の、ハフ変換パラメータを更新し（ステップＳ６４）、左右白線を特定する（ステップＳ６５）。
８．道路形状・白線位置推定
以下は、白線位置情報をデータ化する手順である。図８を参照しながら説明する。
（１）左右白線を表す各々の左右白線を円とみなしてその中心及び半径Ｒを計算する。
【００３２】
（２）左右白線位置の推定
左右白線の手前側の２点の座標を直線的に延ばし、カメラ直下の左右白線位置Ｓを推定する。
【００３３】
【発明の効果】
以上のように本発明の道路の白線検出方法によれば、可能な限りシンプルなアルゴリズムと、安価な機器構成で、白線が実際に存在する位置を確実に検出できる。したがって、将来の高度な車両走行制御に最適な道路の白線検出方法とすることができる。
【図面の簡単な説明】
【図１】画像データの定義図である。
【図２】白線検出処理を示す全体フローチャートである。
【図３】白線候補の統合条件を説明するための図であり、（ａ）は、下にある基準となる白線候補と検査対象となっている白線候補との位置関係を示す図、（ｂ）及び（ｃ）は、両直線の角度関係を示す図である。
【図４】３次元座標変換前後の画像を示す図であり、（ａ）はカメラで撮像したエッジ画像を示す図、（ｂ）は３次元座標変換後の画像を示す図である。
【図５】３次元座標変換した場合の白線候補の初期値を抽出する枠を示す図である。
【図６】左右白線を１本ずつ抽出する手順を説明するためのフローチャートである。
【図７】ハフ変換パラメータｒ，θを解説するための図であり、（ａ）は左側白線候補の場合、（ｂ）は右側白線候補の場合を示す。
【図８】白線位置情報をデータ化する手順を示す図である。
【符号の説明】
Ｓ カメラ直下の左右白線位置
Ｒ 左右白線の半径
ｒ，θ ハフ変換パラメータ
Ｌ１，Ｌ２ ３次元座標変換した場合の白線候補の長さ[0001]
TECHNICAL FIELD OF THE INVENTION
The present invention analyzes a forward image captured by a vehicle-mounted camera, and there are various types of road lane boundary lines (white lines, yellow lines, solid lines, broken lines, and the like. White line detection method for recognizing a white line).
[0002]
[Prior art]
In realizing a driving support system for an automobile, road environment recognition using images is expected.
As one of road environment recognition, there is automatic white line recognition of a driving lane, and various methods have been developed.
Oike "Road White Line Recognition by Model-Based Recognition Method" (Technical Report PRMU99-211 (January 2000)) proposes white line recognition using a string model that does not require binarization processing.
[0003]
Ninomiya, Takahashi, Ota "Apply a template in the" High-speed pattern matching method and its application to lane detection "(3rd next-generation runway display / recognition technology workshop material, Koken 3-4-1, November 1999). In this way, a method for performing road structure verification has been proposed.
[0004]
[Problems to be solved by the invention]
The former “model-based ‥‥” does not require binarization and simplifies the hardware. However, since a continuous active contour model is used, it is impossible to distinguish between a solid line and a broken line. There is a problem that the book is defined so as to converge to the left and right white lines, and it is not assumed that the white line is crossed, so that it is impossible to cope with a lane change.
[0005]
The latter, “High-speed pattern matching method ‥‥”, is resistant to fading white lines and bad weather, and has a low computational cost, but requires a large number of road shape templates and requires a huge amount of memory. .
Therefore, the present invention can be realized by an algorithm as simple as possible and an inexpensive device configuration, can reliably detect the position where a white line actually exists, and can detect road white lines that can be applied to advanced vehicle control in the future. The aim is to realize the method.
[0006]
[Means for Solving the Problems]
The road white line detection method of the present invention calculates a luminance spatial differential value of a pixel in an image captured by a vehicle-mounted camera, extracts a white line edge based on a position indicating the extreme value, and detects the detected edge. Are grouped as white line candidates, and the grouped white line candidates are separately grouped on the left and right based on their positional relationship, and Hough is selected from among the left and right grouped white line candidates. Based on the conversion parameters, determine the similarity between the white line candidates between images before and after successive in time, extract a white line group having a high similarity, and separately based on the extracted result, left and right separately. This is a method for detecting one white line (claim 1).
[0007]
According to the method described above, the edge position is detected without using a commonly used binarization method, and the pixel position at which the luminance space differential value (difference between adjacent luminance values) indicates an extreme value is determined. Since it is adopted, the edge can be detected stably without being influenced by the brightness value and the contrast.
Then, by integrating the detected edges having similar luminance values as white line candidates, the portions having different luminances due to the influence of shadows or blurs are not forcibly detected together, but are detected as thin white line candidates. I do.
[0008]
Further, since integration is performed based on the positional relationship (direction and position) of these white line candidates, white lines can be detected even with broken lines or faint white lines without being affected by disturbance.
In particular, unlike the method of detecting a white line by applying it to a template, the detection is performed based on the actual white line position, so that the white line position can be correctly recognized.
Finally, one white line is extracted for each of the left and right sides. The procedure for detecting one white line separately for the left and right is as follows : based on the Hough transformation parameter, the position similarity of the white line group is determined between the images before and after temporally continuous, and one white line group having a large similarity is determined for each one line. Extract. As a result, one continuous white line can be determined. If the similarity is small, it can be determined that the white line has been lost.
In addition, since the Hough transform parameter is adopted, a simple same evaluation formula can be used regardless of how the white line looks, and uniformity of parameter sensitivity can be secured. (For example, if a and b of the primary expression y = ax + b are adopted as parameters , the parameter weights must be changed near a = ∞ and near a = 0. )
When obtaining the extremum, it is preferable to determine the edge extraction range using the average value and the standard deviation of the luminance space differential values (claim 2).
[0009]
As a result, the edge extraction range is not fixed, but is determined dynamically for each image, so that the influence of disturbances (road surface spots, ruts, etc.) mainly present on the road surface can be eliminated as much as possible. In addition, it becomes strong (robust) against a change in brightness.
It is preferable to use a lateral shift direction and a joint angle between the white line candidates as a reference when grouping the white line candidates.
Since the integration is performed using the shape feature (information on the image plane) drawn on the road surface of the white line, it is hardly affected by disturbance of the road surface or the background.
[0010]
In the middle of the range on the image to determine a line in the left right white line candidate, it is preferable to set the overlap region (claim 4).
[0011]
This makes it possible to smoothly shift from the left white line to the right white line or vice versa when changing lanes.
[0012]
BEST MODE FOR CARRYING OUT THE INVENTION
Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
1. Definition of image data (see Fig. 1)
The coordinate system of the image captured by the on-vehicle camera is set to the origin (0, 0) at the upper left, the x axis to the right, and the y axis to the lower. The image size is 640 pixels in the horizontal (x direction) and 480 pixels in the vertical (y direction).
[0013]
The pixel value is represented by 8 bits, 256 levels from 0 to 255. 0 is black and 255 is white. The pixel value at the position (x, y) is described as Im [y] [x].
FIG. 2 is an overall flowchart showing the white line detection processing. This process is performed every time one image is captured. Images are captured at 30 sheets per second (step S1). Hereinafter, each step will be described separately.
2. Preprocessing 2.1 Sampling is performed every other pixel in both the reduced x direction and the y direction. As a result, the processing amount is reduced, and the processing time can be shortened.
[0014]
2.2 Smoothing Smoothing is performed by convolving the pixel values with the following operators over the entire image.
[0015]
(Equation 1)

[0016]
3. The range where the edge detection white line exists is limited to the lower half area of the screen. The following processing is executed only for the lower half area of the screen.
3.1 Calculation of Pixel Edge Intensity Based on spatial differentiation (difference), edge intensity (Intensity) at position (x, y) is defined as follows, and edge detection is performed using this.
[0017]
Edge strength = (Im [y] [x + 3] + Im [y] [x + 2] -Im [y] [x-2] -Im [y] [x-3]) / 10
The space representing the edge strength is called “edge space”.
Note that this equation is equivalent to the one-dimensional Prewitt-type spatial derivative (-1 0 1) obtained by averaging five pixels around the target point.
3.2 Edge Detection An edge is detected by selecting a pixel showing an extreme value in the edge space. The selected edges each have a signed value of ±, and based on this, are grouped in the subsequent processing (described later).
[0018]
However, in order to eliminate the influence of road surface noise and the like, the invention is devised so as to limit the extremum search target range. Specifically, the average value and the standard deviation of the edge strength in the lower half of the screen are calculated, and the outside of the following range is set as the extreme value search target range.
Upper limit: average value of edge intensity + 1.5 × standard deviation Lower limit: average value of edge intensity−1.5 × standard deviation Assuming that the edge intensity distribution in the edge space follows a normal distribution, the above range includes approximately 86.6% are included, and as a result, an extreme value pixel is extracted from about 6.7% of the pixels included in the upper extreme value search target range and the lower extreme value search target range, respectively. Become. As a result, the processing speed can be increased.
[0019]
4. Extraction of White Line Candidates Edges extracted in the preceding paragraph are grouped according to the following procedure to extract white line candidates (a portion of a white line as a whole).
(1) The lowermost edge of the image is registered as the starting point G0 of the white line candidate.
(2) An edge which is a pixel near the white line candidate start point G0 and has an intensity similar to that of the white line candidate start point G0 is registered as a new white line candidate G. Hereinafter, this process is repeated.
In this way, a white line candidate is constituted by the white line candidate start point G0 and the white line candidate G registered in relation thereto.
[0020]
Neighboring pixels are searched from a line up to three steps at the maximum. If the number exceeds three lines, it is registered as another white line start point.
The search range in the horizontal direction is (distance to search line) × (± 3 pixels). For example, when there is no edge on one line and the second line is searched, ± 6 pixels are searched. In terms of the expression, if two lines are on the basis of the (x, y) position, a search is made from (x-6, y-2) to (x + 6, y-2).
[0021]
The intensity similarity determination is performed based on whether or not the edge intensity of the white line candidate start point G0 is within ± 50%.
5. Grouping of white line candidates The white line candidates extracted in the preceding section are grouped according to the following procedure.
(1) For a white line candidate having a certain number of constituent pixels or more, a left white line and a right white line are selected. Note that the search areas for the left and right white lines are overlapped so that the left and right white lines can be followed as much as possible when changing lanes where the positions of the left and right white lines are interchanged.
[0022]
Specifically, the lower limit of the number of pixels constituting the white line candidate is three.
If the x coordinate of the white line candidate start point G0 is 160 + α or less and the edge strength is negative, it is determined that the x coordinate of the white line candidate start point G0 is 161-α or more and the edge strength is positive. For example, it is determined to be the left end of the right white line. Here, the coordinate “160” is set to a half position on the assumption that the image size after reduction in the x direction is 640/2 = 320 pixels.
[0023]
α is about 10% (32 pixels) of the image size in the x direction in consideration of the overlap.
(2) White line candidates are grouped in order from the bottom (larger y coordinate). The conditions are as follows: (a) the relationship between the straight line obtained by extending the lower reference white line candidate and the starting point of the white line candidate to be inspected is within the coupling range; (b) the difference between the slopes of the two lines θ is within a predetermined angle range.
[0024]
As shown in FIG. 3A, the “joining range” refers to a line segment L drawn in the horizontal direction from the start point G0 of the white line candidate 2 to be inspected and a white line candidate below as a reference. Assuming that a point at which the extended straight line intersects is P, the length G0P is within a range of ± a predetermined number of pixels. However, when P is on the right side of G0, it is positive, and when P is on the left side of G0, it is negative. In FIG. 3A, the predetermined number is set to 10.
The “predetermined angle range” is, as shown in FIG. 3B, when the point P is on the right of the starting point G0, −5 ° to + 20 °, and as shown in FIG. When it is on the left, it is -20 ° to + 5 °.
[0025]
6. The starting point G0 of the white line group is three-dimensionally transformed into real space coordinates on the three-dimensional coordinate transformation screen using the following equation.
Z (distance in the vehicle traveling direction) = Dividend (η, sinψ, cosｃｏ) / Divider (η, sinψ, cosψ)
X (vehicle lateral distance) = Conv2X (ξ, Z)
Conv2X (ξ, Z) = (ξ / F) [(Z cosψ) + (H sinψ)]
Divider (η, sinψ, cosψ) = sinψ- (η / F) cosψ
Divendend (η, sinψ, cosψ) = H [cosψ + (η / F) sinψ]
H: Camera installation height (m)
F: Lens focal length (m)
ψ: Depression angle (rad) of the camera optical axis
ξ and η represent the distance (m) from the center (origin) of the imaging plane (the y-axis is positive upward and the x-axis is positive rightward).
[0026]
4A and 4B are diagrams showing images before and after the three-dimensional coordinate conversion. FIG. 4A is a diagram showing an edge image captured by a camera, and FIG. 4B is a diagram showing an image after the three-dimensional coordinate conversion.
7. Extraction of the most reliable left and right white lines From the white line candidates in the group, left and right white lines are extracted one by one. FIG. 5 is a diagram showing a plurality of white line groups in the real space. FIG. 6 is a flowchart for explaining the procedure in this section.
[0027]
(1) The length of the white line candidate when the three-dimensional coordinate conversion is performed, when the starting point G0 of the white line candidate when the three-dimensional coordinate conversion is performed is within ± 4 m in the horizontal direction and within 30 m in front (see the thick line frame in FIG. 5). L1, L2,... Are extracted with the largest value (step S66).
(2) On the screen before the three-dimensional coordinate conversion, a white line candidate having a certain number of pixels (for example, 5) or more is selected, and a Hough conversion parameter is calculated (step S67).
[0028]
Here, the Hough transform means a straight line xcosθ + ysinθ = r expressed in an xy orthogonal coordinate system.
To the (r, θ) plane. The origin of the polar coordinates is the upper left of the screen as shown in FIG. 7A for a left white line candidate, and the upper right of the screen as shown in FIG. 7B for a right white line candidate. The Hough transform parameters are r and θ. The dotted line is a white line extracted from the screen shot last time, and the solid line is a white line extracted from the screen shot this time. In FIG. 7, two white lines having different acquisition times are simultaneously drawn.
[0029]
(3) Based on the Hough transform parameters, the similarity to the previously detected white line candidate is obtained, and the one with the highest similarity is separately extracted as the current white line candidate (step S62).
To determine the similarity, the determination value 100 | θ0−θ1 | + | r0−r1 |
Is adopted. r0 and θ0 are Hough transformation parameters of the previous white line candidate, and r1 and θ1 are Hough transformation parameters of the current white line candidate. “100” is a weight coefficient (constant). The smaller this determination value is, the higher the similarity is.
[0030]
If the determination value exceeds 30, it is determined that the position of the white line has been lost (NO in step S63). In this case, the process jumps to step S66, and the optimum candidate is searched again by the method (1).
When the position of the white line is lost in FIG. 6, the process may not proceed to step S66, but may discard the Hough transform parameter and start from step S66 in the next cycle.
[0031]
The Hough transform parameters of the left and right white lines thus extracted are updated (step S64), and the left and right white lines are specified (step S65).
8. Road Shape / White Line Position Estimation The following is a procedure for converting white line position information into data. This will be described with reference to FIG.
(1) The center and radius R are calculated by regarding each of the left and right white lines representing the left and right white lines as a circle.
[0032]
(2) Estimation of left and right white line positions The coordinates of two points on the near side of the left and right white lines are linearly extended, and the left and right white line positions S immediately below the camera are estimated.
[0033]
【The invention's effect】
As described above, according to the road white line detection method of the present invention, the position where the white line actually exists can be reliably detected with the simplest possible algorithm and inexpensive device configuration. Therefore, it is possible to provide a road white line detection method optimal for future advanced vehicle traveling control.
[Brief description of the drawings]
FIG. 1 is a definition diagram of image data.
FIG. 2 is an overall flowchart illustrating a white line detection process.
FIGS. 3A and 3B are diagrams for explaining integration conditions of white line candidates, and FIG. 3A is a diagram illustrating a positional relationship between a white line candidate serving as a reference below and a white line candidate to be inspected; And (c) are diagrams showing the angular relationship between the two straight lines.
4A and 4B are diagrams showing images before and after three-dimensional coordinate conversion, where FIG. 4A is a diagram showing an edge image captured by a camera, and FIG. 4B is a diagram showing an image after three-dimensional coordinate conversion.
FIG. 5 is a diagram illustrating a frame for extracting an initial value of a white line candidate when three-dimensional coordinate conversion is performed.
FIG. 6 is a flowchart illustrating a procedure for extracting left and right white lines one by one.
FIGS. 7A and 7B are diagrams for explaining Hough transform parameters r and θ, wherein FIG. 7A shows a case of a left white line candidate, and FIG. 7B shows a case of a right white line candidate.
FIG. 8 is a diagram showing a procedure for converting white line position information into data.
[Explanation of symbols]
S Right and left white line position R immediately below the camera Radius of right and left white line r, θ Hough transformation parameters L1 and L2 Length of white line candidate after three-dimensional coordinate transformation

Claims (4)

Calculate the luminance space differential value of the pixel in the image taken by the on-board camera,
Extract the edge of the white line based on the position showing the extreme value,
Those with similar luminance values of the detected edges are grouped as white line candidates,
The grouped white line candidates are grouped separately on the left and right based on their positional relationship,
From the white line candidates grouped into the left group and the right group, the similarity between the white line candidates between the images before and after temporally consecutive is calculated based on the Hough transform parameter, and the white line group having a high similarity is calculated. Extract
A white line detection method for roads, wherein one white line is detected separately for left and right based on the extracted result . 2. The road white line detection method according to claim 1, wherein when the extremum is obtained, an edge extraction range is determined using an average value and a standard deviation of the luminance space differential values. The road white line detection method according to claim 1, wherein a lateral shift direction and a joint angle between the white line candidates are used as a reference when grouping the white lines. 2. The road white line detection method according to claim 1, wherein an overlap area is set at the center of a range on the image for obtaining lines as left and right white line candidates.

Images