CN102779349A - Foggy day detecting method based on image color spatial feature - Google Patents

Abstract

The invention provides a foggy day detecting method based on an image color spatial feature. The method comprises the following steps of first step, obtaining a background picture through a video image or a single image; step 2, performing color space conversion for the background picture, and extracting the color space feature: firstly performing color space conversion for the background picture, converting from an RGB (red-green-blue) color space into an HSV (hue, saturation, value) color space, and extracting the features of various components of the HSV according to the information included image; and step 3, dividing the weather information included image into a non-foggy day, a little foggy day and a dense foggy day according to the identification conditions: at first, if the identification condition 1 is met, the weather is the dense foggy day, otherwise the identification is continued; secondly, if the identification condition 2 is met, the weather is the non-foggy day, otherwise, the identification is continued; and finally, if the identification condition 3 is met, the weather is the little foggy day, otherwise, the weather is the dense foggy day. The method provided by the invention is suitable for being used for monitoring the foggy day in expressways, particularly pre-warning the emergency of agglomerate fog in partial road segments, thus, the safe road driving can be ensured.

Description

A kind of foggy day detection method based on the color of image space characteristics

Technical field

The present invention relates to digital video image and handle and traffic weather detection range, is a kind of foggy day detection method based on color of image HSV characteristic.

Background technology

Visibility is the road with one of key element of weather conditions system.At traffic high speed networking; The major issue that the grasp of a road visibility is related to the road user safety of life and property; Reporting for work of the pernicious traffic hazard that causes owing to low visibility is of common occurrence; Under the low visibility situation, human reaction velocity descends, and is especially all the more so in the high-speed travel process., fast, weather conditions information just can provide warning in advance accurately, thus super expressway is carried out the rational and effective management in help high-speed transit road management department and road users are chosen safe road use route and driving speed.

Mainly accomplish for the observation of dense fog at present by the artificial visually examine; The special monitoring station of installing mainly is through advanced optical devices are installed, through receiving and measure the intensity of scattered beam; Accurately measure the air visibility on the present highway, judged whether that dense fog takes place.Because the length of the expense of apparatus expensive and super expressway is bigger, intensive layout research station on highway is caught the group's mist that haunts everywhere, obviously too expensive.

For detection technique based on traditional greasy weather visibility of image; Need carry out on-site proving to video camera, wherein not only need know the various parameters in inside of video camera, and need know position angle of installation etc.; And needing corresponding corresponding scene, computing complicacy and cost are also than higher.

Foggy day detection method becomes an importance of institute's primary study of high-speed transit control relevant departments in recent years, is putting before this, researchs and proposes a kind of simple, convenient, detection method fast.

Summary of the invention

The present invention is a kind of foggy day detection method based on the color of image space characteristics; At first obtain background picture through video image or single image; Then background picture is carried out color space conversion (from RGB to HSV); And then HSV carried out feature extraction, and utilize the characteristic of extracting that weather is carried out qualitative detection, it is divided into non-greasy weather gas, little greasy weather gas, foggy weather.

The present invention adopts following technical scheme:

A kind of foggy day detection method based on color of image HSV characteristic, implement according to following steps:

A kind of foggy day detection method based on the color of image space characteristics is characterized in that, implements according to following steps:

Step 1: initialization, read in road traffic image or video,

Step 2:, then read in picture and be background picture I if read in piece image in the step 1 ₁If what read in the step 1 is video, then handle as follows, obtain background picture I ₁:

The N frame picture that from video camera, reads in, N=30 ~ 40, statistics comes across the number of times of the same color gray-scale value on the same pixel of 30 ~ 40 frame pictures, and with the highest color gray-scale value of occurrence number picture I as a setting ₁The color gray-scale value of respective pixel point, mathematic(al) representation is:

$P(i,j,n)=\left\{\begin{array}{cc}P(i,j,n)+1& I_k(i,j,m)=n\\ P(i,j,n)& I_k(i,j,m)\≠n\end{array}\right.k=\mathrm{1,2},...,N$

Background(i,j)＝Max(P(i,j,n))n＝0,1,2,...,255

In the formula, (n) (i j) locates the number of times that color gray level n occurs to the remarked pixel point to P, and initial value is 0, I for i, j _k(i, j, m) pixel in the expression k two field picture (i, j) locating gray level is m, m=0; 1,2 ..., 255, Background (i; J) be background picture in that ((P (i, j, n)) is P (i to Max for i, color gray-scale value j); J, represented color gray-scale value when the number of times that n) occurs is maximum carries out traversing operation to every bit in the image, obtains background picture I ₁,

Step 3: to background picture I ₁Carry out color space conversion, from the RGB color space conversion to the hsv color space:

For each pixel form and aspect component H (i j) is obtained by following formula:

$H(i,j)=\left\{\begin{array}{cc}\mathrm{\θ}& B(i,j)\≤G(i,j)\\ 360-\mathrm{\θ}& B(i,j)>G(i,j)\end{array}\right.$

Here

$\mathrm{\θ}=\arccos \{\frac{\frac{1}{2}\left\{\right[R(i,j)-G(i,j)]+[R(i,j)-B(i,j)\left]\right\}}{{\{{[R(i,j)-G(i,j)]}^2+[R(i,j)-G(i,.j)\left]\right[G(i,j)-B(i,j)\left]\right\}}^{1/2}},$

Wherein, pixel (i, the red component intensity of j) locating be R (i, j), effective value is between 0 to 255; Pixel (i, the green component intensity of j) locating be G (i, j), effective value between 0 to 255, pixel (i; J) the blue component intensity of locating is that (i, j), effective value is between 0 to 255 for B

Saturation degree component S (i, j) as follows:

$S(i,j)=1-\frac{3}{[R(i,j)+G(i,j)+B(i,j)]}\left[\min (R(i,j),G(i,j),B(i,j))\right]$

Wherein, pixel (i, the red component intensity of j) locating be R (i, j), effective value is between 0 to 255; Pixel (i, the green component intensity of j) locating be G (i, j), effective value between 0 to 255, pixel (i; J) the blue component intensity of locating is that (i, j), effective value is between 0 to 255 for B

Tone component V (i, j) as follows:

$V(i,j)=\frac{1}{3}[R(i,j)+G(i,j)+B(i,j)],$

Wherein, pixel (i, the red component intensity of j) locating be R (i, j), effective value is between 0 to 255; Pixel (i, the green component intensity of j) locating be G (i, j), effective value between 0 to 255, pixel (i; J) the blue component intensity of locating is that (i, j), effective value is between 0 to 255 for B

Each pixel of Target Photo is carried out conversion as above, obtain background picture I ₁The hsv color space,

Step 4: to background picture I ₁The color space of HSV carries out feature extraction, and is specific as follows:

4.1) form and aspect component H characteristic AveH: statistics background picture I ₁In the summation SumH of each pixel H component value, the H component value is not that 0 pixel adds up to M ₁, then H divides measure feature AveH=SumH/M ₁

4.2) saturation degree component S characteristic AveS: statistics background picture I ₁In the summation SumS of each pixel S component value, the S component value is not that 0 pixel adds up to M ₂, then S divides measure feature AveS=SumS/M ₂

4.3) tone component V characteristic AveV: statistics background picture I ₁In the summation SumV of each pixel V component value, the V component value is not that 0 pixel adds up to M ₃, then V divides measure feature AveV=SumV/M ₃

Step 5: according to resulting background picture I in the step 4 ₁The characteristic of HSV according to decision condition 1, marks off the foggy weather with specific characteristic, and decision condition 1 is expressed as follows:

AveH＜125&&AveS＜0.200&&AveV＜0.4800

Satisfy above-mentioned condition simultaneously, then weather is dense fog, otherwise carries out next step,

Step 6: to being judged to be in the step 5 under the situation not, according to decision condition 2, mark off non-greasy weather weather, decision condition 2 expression formulas are following:

(if AveS＞0.1050&&AveH＜200)

Perhaps (Aves＞0.200&&AveH＞120),

Perhaps 0.0700＜AveS＜0.1050&&120＜AveH＜200,

Satisfying above-mentioned any one condition, then is the non-greasy weather, and the person does not carry out next step,

Step 7: to being judged to be in the step 6 under the situation not, according to decision condition 3, mark off little greasy weather gas, decision condition 3 is expressed as follows:

AveS＜0.0700&&AveH＜100&&AveV＜0.500,

Satisfy above-mentioned condition simultaneously, then weather is little mist, otherwise is dense fog.

Compared with prior art, the invention has the advantages that:

1, the present invention utilizes the color of image spatial information, to weather condition in the road traffic, can mark off non-greasy weather gas, little greasy weather gas and foggy weather more exactly, the greasy weather is reported to the police and road carries out safety management realizing;

2, the hsv color spatial information that self comprised according to image of the present invention; Utilize the characteristic of its each component under different weather to come the qualitative different weather situation that marks off; Algorithm is simpler, and parameter adjustment is convenient, and travelling speed is very fast; Avoided video camera is carried out complicated on-site proving link, realized the detection of pin-point accuracy.

3, compare with the expensive cost of traditional visibility detector, cost of the present invention is lower, makes the present invention can in actual field is used, realize large-area covering, real realize to road conditions detect in real time, management and early warning, guarantee traffic safety

Description of drawings:

Fig. 1 is the particular flow sheet that total system detects.

Embodiment:

In concrete embodiment, will combine accompanying drawing, know and intactly describe detailed process based on the foggy day detection method of color of image HSV characteristic.

Concrete steps are following:

A kind of foggy day detection method based on the color of image space characteristics, implement according to following steps:

Step 1: initialization, read in road traffic image or video,

Step 2:, then read in picture and be background picture I if read in piece image in the step 1 ₁If what read in the step 1 is video, then handle as follows, obtain background picture I ₁:

The N frame picture that from video camera, reads in, N=30 ~ 40, statistics comes across the number of times of the same color gray-scale value on the same pixel of 30 ~ 40 frame pictures, and with the highest color gray-scale value of occurrence number picture I as a setting ₁The color gray-scale value of respective pixel point, mathematic(al) representation is:

$P(i,j,n)=\left\{\begin{array}{cc}P(i,j,n)+1& I_k(i,j,m)=n\\ P(i,j,n)& I_k(i,j,m)\≠n\end{array}\right.k=\mathrm{1,2},...,N$

Background(i,j)＝Max(P(i,j,n))n＝0,1,2,...,255

In the formula, (n) (i j) locates the number of times that color gray level n occurs to the remarked pixel point to P, and initial value is 0, I for i, j _k(i, j, m) pixel in the expression k two field picture (i, j) locating gray level is m, m=0; 1,2 ..., 255, Background (i; J) be background picture in that ((P (i, j, n)) is P (i to Max for i, color gray-scale value j); J, represented color gray-scale value when the number of times that n) occurs is maximum carries out traversing operation to every bit in the image, obtains background picture I ₁,

Step 3: to background picture I ₁Carry out color space conversion, from the RGB color space conversion to the hsv color space:

For each pixel form and aspect component H (i j) is obtained by following formula:

$H(i,j)=\left\{\begin{array}{cc}\mathrm{\θ}& B(i,j)\≤G(i,j)\\ 360-\mathrm{\θ}& B(i,j)>G(i,j)\end{array}\right.$

Here

$\mathrm{\θ}=\arccos \{\frac{\frac{1}{2}\left\{\right[R(i,j)-G(i,j)]+[R(i,j)-B(i,j)\left]\right\}}{{\{{[R(i,j)-G(i,j)]}^2+[R(i,j)-G(i,.j)\left]\right[G(i,j)-B(i,j)\left]\right\}}^{1/2}},$

Wherein, pixel (i, the red component intensity of j) locating be R (i, j), effective value is between 0 to 255; Pixel (i, the green component intensity of j) locating be G (i, j), effective value between 0 to 255, pixel (i; J) the blue component intensity of locating is that (i, j), effective value is between 0 to 255 for B

Saturation degree component S (i, j) as follows:

$S(i,j)=1-\frac{3}{[R(i,j)+G(i,j)+B(i,j)]}\left[\min (R(i,j),G(i,j),B(i,j))\right]$

Wherein, pixel (i, the red component intensity of j) locating be R (i, j), effective value is between 0 to 255; Pixel (i, the green component intensity of j) locating be G (i, j), effective value between 0 to 255, pixel (i; J) the blue component intensity of locating is that (i, j), effective value is between 0 to 255 for B

Tone component V (i, j) as follows:

$V(i,j)=\frac{1}{3}[R(i,j)+G(i,j)+B(i,j)],$

Wherein, pixel (i, the red component intensity of j) locating be R (i, j), effective value is between 0 to 255; Pixel (i, the green component intensity of j) locating be G (i, j), effective value between 0 to 255, pixel (i; J) the blue component intensity of locating is that (i, j), effective value is between 0 to 255 for B

Each pixel of Target Photo is carried out conversion as above, obtain background picture I ₁The hsv color space,

Step 4: to background picture I ₁The color space of HSV carries out feature extraction, and is specific as follows:

4.1) form and aspect component H characteristic AveH: statistics background picture I ₁In the summation SumH of each pixel H component value, the H component value is not that 0 pixel adds up to M ₁, then H divides measure feature AveH=SumH/M ₁

4.2) saturation degree component S characteristic AveS: statistics background picture I ₁In the summation SumS of each pixel S component value, the S component value is not that 0 pixel adds up to M ₂, then S divides measure feature AveS=SumS/M ₂

4.3) tone component V characteristic AveV: statistics background picture I ₁In the summation SumV of each pixel V component value, the V component value is not that 0 pixel adds up to M ₃, then V divides measure feature AveV=SumV/M ₃

Step 5: according to resulting background picture I in the step 4 ₁The characteristic of HSV according to decision condition 1, marks off the foggy weather with specific characteristic, and decision condition 1 is expressed as follows:

AveH＜125&&AveS＜0.200&&AveV＜0.4800

Satisfy above-mentioned condition simultaneously, then weather is dense fog, otherwise carries out next step,

Step 6: to being judged to be in the step 5 under the situation not, according to decision condition 2, mark off non-greasy weather weather, decision condition 2 expression formulas are following:

(if AveS＞0.1050&&AveH＜200)

Perhaps (Aves＞0.200&&AveH＞120),

Perhaps 0.0700＜AveS＜0.1050&&120＜AveH＜200,

Satisfying above-mentioned any one condition, then is the non-greasy weather, and the person does not carry out next step,

Step 7: to being judged to be in the step 6 under the situation not, according to decision condition 3, mark off little greasy weather gas, decision condition 3 is expressed as follows:

AveS＜0.0700&&AveH＜100&&AveV＜0.500,

Satisfy above-mentioned condition simultaneously, then weather is little mist, otherwise is dense fog.

Claims (1)

1. the foggy day detection method based on the color of image space characteristics is characterized in that, implements according to following steps:

Step 1: initialization, read in road traffic image or video,

Step 2:, then read in picture and be background picture I if read in piece image in the step 1 ₁If what read in the step 1 is video, then handle as follows, obtain background picture I ₁:

From video camera, read in N frame picture, N=30 ~ 40, statistics comes across the number of times of the same color gray-scale value on the same pixel of 30 ~ 40 frame pictures, and with the highest color gray-scale value of occurrence number picture I as a setting ₁The color gray-scale value of respective pixel point, mathematic(al) representation is:

$P(i,j,n)=\left\{\begin{array}{cc}P(i,j,n)+1& I_k(i,j,m)=n\\ P(i,j,n)& I_k(i,j,m)\≠n\end{array}\right.k=\mathrm{1,2},...,N$

Background(i,j)＝Max(P(i,j,n))n＝0,1,2,...,255

In the formula, (n) (i j) locates the number of times that color gray level n occurs to the remarked pixel point to P, and initial value is 0, I for i, j _k(i, j, m) pixel in the expression k two field picture (i, j) locating gray level is m, m=0; 1,2 ..., 255, Background (i; J) be background picture in that ((P (i, j, n)) is P (i to Max for i, color gray-scale value j); J, represented color gray-scale value when the number of times that n) occurs is maximum carries out traversing operation to every bit in the image, obtains background picture I ₁,

Step 3: to background picture I ₁Carry out color space conversion, from the RGB color space conversion to the hsv color space:

For each pixel form and aspect component H (i j) is obtained by following formula:

$H(i,j)=\left\{\begin{array}{cc}\mathrm{\θ}& B(i,j)\≤G(i,j)\\ 360-\mathrm{\θ}& B(i,j)>G(i,j)\end{array}\right.$

Here

$\mathrm{\θ}=\arccos \{\frac{\frac{1}{2}\left\{\right[R(i,j)-G(i,j)]+[R(i,j)-B(i,j)\left]\right\}}{{\{{[R(i,j)-G(i,j)]}^2+[R(i,j)-G(i,.j)\left]\right[G(i,j)-B(i,j)\left]\right\}}^{1/2}},$

Wherein, pixel (i, the red component intensity of j) locating be R (i, j), effective value is between 0 to 255; Pixel (i, the green component intensity of j) locating be G (i, j), effective value between 0 to 255, pixel (i; J) the blue component intensity of locating is that (i, j), effective value is between 0 to 255 for B

Saturation degree component S (i, j) as follows:

$S(i,j)=1-\frac{3}{[R(i,j)+G(i,j)+B(i,j)]}\left[\min (R(i,j),G(i,j),B(i,j))\right]$

Wherein, pixel (i, the red component intensity of j) locating be R (i, j), effective value is between 0 to 255; Pixel (i, the green component intensity of j) locating be G (i, j), effective value between 0 to 255, pixel (i; J) the blue component intensity of locating is that (i, j), effective value is between 0 to 255 for B

Tone component V (i, j) as follows:

$V(i,j)=\frac{1}{3}[R(i,j)+G(i,j)+B(i,j)],$

Wherein, pixel (i, the red component intensity of j) locating be R (i, j), effective value is between 0 to 255; Pixel (i, the green component intensity of j) locating be G (i, j), effective value between 0 to 255, pixel (i; J) the blue component intensity of locating is that (i, j), effective value is between 0 to 255 for B

Each pixel of Target Photo is carried out conversion as above, obtain background picture I ₁The hsv color space,

Step 4: to background picture I ₁The color space of HSV carries out feature extraction, and is specific as follows:

4.1) form and aspect component H characteristic AveH: statistics background picture I ₁In the summation SumH of each pixel H component value, the H component value is not that 0 pixel adds up to M ₁, then H divides measure feature AveH=SumH/M ₁

4.2) saturation degree component S characteristic AveS: statistics background picture I ₁In the summation SumS of each pixel S component value, the S component value is not that 0 pixel adds up to M ₂, then S divides measure feature AveS=SumS/M ₂

4.3) tone component V characteristic AveV: statistics background picture I ₁In the summation SumV of each pixel V component value, the V component value is not that 0 pixel adds up to M ₃, then V divides measure feature AveV=SumV/M ₃

Step 5: according to resulting background picture I in the step 4 ₁The characteristic of HSV according to decision condition 1, marks off the foggy weather with specific characteristic, and decision condition 1 is expressed as follows:

AveH＜125&&AveS＜0.200&&AveV＜0.4800

Satisfy above-mentioned condition simultaneously, then weather is dense fog, otherwise carries out next step,

Step 6: to being judged to be in the step 5 under the situation not, according to decision condition 2, mark off non-greasy weather weather, decision condition 2 expression formulas are following:

(if AveS＞0.1050&&AveH＜200),

Perhaps (Aves＞0.200&&AveH＞120),

Perhaps 0.0700＜AveS＜0.1050&&120＜AveH＜200,

Satisfying above-mentioned any one condition, then is the non-greasy weather, and the person does not carry out next step,

Step 7: to being judged to be in the step 6 under the situation not, according to decision condition 3, mark off little greasy weather gas, decision condition 3 is expressed as follows:

AveS＜0.0700&&AveH＜100&&AveV＜0.500,

Satisfy above-mentioned condition simultaneously, then weather is little mist, otherwise is dense fog.

Images