WO2018166083A1 - Application of contrast enhancement and visual saliency optimization method in golf course image - Google Patents

Application of contrast enhancement and visual saliency optimization method in golf course image Download PDF

Info

Publication number
WO2018166083A1
WO2018166083A1 PCT/CN2017/088920 CN2017088920W WO2018166083A1 WO 2018166083 A1 WO2018166083 A1 WO 2018166083A1 CN 2017088920 W CN2017088920 W CN 2017088920W WO 2018166083 A1 WO2018166083 A1 WO 2018166083A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
golf course
map
contrast enhancement
smoothing
Prior art date
Application number
PCT/CN2017/088920
Other languages
French (fr)
Chinese (zh)
Inventor
陈箫枫
潘剑佳
程健
Original Assignee
深圳市嘉和顺信息科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市嘉和顺信息科技有限公司 filed Critical 深圳市嘉和顺信息科技有限公司
Publication of WO2018166083A1 publication Critical patent/WO2018166083A1/en

Links

Images

Classifications

    • G06T5/70—
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/40—Image enhancement or restoration by the use of histogram techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/50—Image enhancement or restoration by the use of more than one image, e.g. averaging, subtraction
    • G06T5/73—
    • G06T5/92—
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10024—Color image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10032—Satellite or aerial image; Remote sensing
    • G06T2207/10041—Panchromatic image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20172—Image enhancement details
    • G06T2207/20192—Edge enhancement; Edge preservation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20212—Image combination
    • G06T2207/20221—Image fusion; Image merging
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30221—Sports video; Sports image
    • G06T2207/30228—Playing field

Definitions

  • the present invention relates to the use of a contrast enhancement and visual saliency optimization method in a golf course map.
  • Golf course maps are used to identify distances and locations in golf course ranging and positioning. Existing golf course maps typically use real or manual maps. Real-life maps (including but not limited to satellite and aerial maps) provide an intuitive visual representation of golf course ranging and positioning. However, the fairway, long grass, greens, bunkers and other areas in the real scene of the stadium often have problems of low contrast, inconspicuous image color, and poor visual color image.
  • the object of the present invention is to overcome the deficiencies of the prior art and to provide a contrast enhancement and visual saliency optimization method for use in a golf course, which has the characteristics of a stadium real map with higher contrast and better visual effects.
  • the present invention is achieved by an image contrast enhancement and visual saliency optimization method comprising the following steps:
  • Step 1 Obtain the original real scene map of the golf course, and the original real scene map is a color image, and the original image is decomposed into a color component map;
  • Step 2 Perform image smoothing on the original real scene of the golf course obtained in step one, and improve the details of the real scene image;
  • Step 3 Perform image sharpening on the image smoothed image obtained in step 2, and enhance the real scene image. detail;
  • Step 4 performing image contrast enhancement on the image sharpened image obtained in step 3, and improving contrast and visual saliency of the real image image;
  • Step 5 Combine the contrast-enhanced color component map obtained in step 4 into a color golf field real-life map, and determine whether the desired image visual effect is achieved according to the need, and if the desired image visual effect is achieved, the contrast enhancement is finally obtained.
  • step three a Laplacian image sharpening operator is used for image sharpening processing.
  • step two a Gaussian image smoothing operator is used for image smoothing processing.
  • step four a histogram matching technique is used to perform image contrast enhancement processing.
  • RGB component decomposition is used to decompose the color image into a color component map.
  • An application of an image contrast enhancement and visual saliency optimization method in a golf course map characterized in that the golf course includes greens, bunkers, long grasses, fairways, etc., which have low contrast and vision in existing satellite images. Poor effect, for the golf course satellite real map, the image of the golf course is image sharpening technology, image smoothing technology, image contrast enhancement technology, and the contrast and visual saliency of the image of the golf course map and part of the golf course map are improved. .
  • image sharpening techniques refer to image processing techniques that can attenuate or eliminate low frequency components in an image without affecting high frequency components, including but not limited to Laplacian image sharpening operators, High frequency boost filtering, gradient based sharpening filtering, maximum and minimum sharpening transforms, linear and nonlinear sharpening.
  • image smoothing technology refers to image processing technology that can attenuate or eliminate high frequency components in an image without affecting low frequency components, including but not limited to neighborhood smoothing, plus Weight smoothing, Gaussian smoothing, median smoothing, order statistical smoothing, linear and nonlinear smoothing.
  • image contrast enhancement technology refers to image processing technology that can increase contrast between portions of an image, including but not limited to histogram matching, histogram equalization, and image gray mapping.
  • color component decomposition refers to decomposing color images into color space to describe image color components, including without limitation RGB decomposition, YIQ decomposition, YCbCr decomposition, HSV decomposition, CMY decomposition, HSI decomposition.
  • the invention applies the image visual optimization technology, including image smoothing, image sharpening and contrast enhancement, to the image processing of the golf field satellite real image, so that the image of the real scene of the golf course is clear, the edge is obvious, the fairway, the grass in the course,
  • image visual optimization technology including image smoothing, image sharpening and contrast enhancement
  • FIG. 1 is a flowchart provided by an embodiment of the present invention.
  • an embodiment of the present invention provides an image contrast enhancement and a visual saliency optimization method at a high level.
  • the application of the satellite scene image processing in the golf course, the present invention includes two schemes, as described below.
  • Step 1 Obtain the original real scene map of the golf course, and the original real scene map is a color image, and the original image is decomposed into three RGB three-channel color maps.
  • the original golf scene real scene map is a color image F(i, j)
  • the original image is decomposed into RGB three-channel color map, a total of three, are F R (i, j), F G (i, j), F B (i, j).
  • Step 2 Perform image smoothing on the original real scene of the golf course obtained in the first step, and improve the details of the real image, (F R (i, j), F G (i, j), F B (i, j)) respectively Smoothing the image and improving the image detail.
  • F R (i, j), F G (i, j), F B (i, j) respectively Smoothing the image and improving the image detail.
  • the Gaussian image smoothing operator of the 5*5 template is used for image smoothing.
  • the mathematical expression is
  • the picture shows the original F, as the smoothed image F gau
  • Gaussian smoothing is a kind of linear smoothing filter, which is suitable for eliminating Gaussian noise.
  • the value of each pixel is obtained by weighted averaging of itself and other pixel values in the neighborhood.
  • Gaussian smoothing filtering can reduce the image. Noise, get the visual optimization effect of the details of the real scene.
  • Step 3 Perform image sharpening on the image smoothed image obtained in step 2, and improve the details of the real image.
  • the Laplacian image sharpening operator of the 3*3 template is used for image sharpening, mathematical expression Formula
  • the sharpened image is F l
  • the Laplacian operator is a differential operator, and the image obtained by the convolution operation will sharpen the original image while making the constant region zero.
  • the constant region is restored, and the sharpened image F l is obtained .
  • Step 4 Perform image contrast enhancement on the image sharpened image obtained in the third step, and improve the contrast and visual saliency of the real image image.
  • the histogram matching technique is used for image contrast enhancement.
  • the main display objects are fairways, long grasses, greens, bunkers, trees, and the like.
  • the main gray levels are concentrated in the smaller gray areas.
  • the gray level concentrated in the small gray area is mapped to [0, 255] while maintaining the relative proportion of the gray level, thereby obtaining the effect of image brightness enhancement and contrast enhancement.
  • the H -1 inverse transform function can be obtained, so that the pixel value transform function from the input graph to the desired output histogram can be obtained, and the input graph can be mapped to the desired contrast enhanced output graph. .
  • step 5 the contrast-enhanced RGB three-channel color map obtained in step four is merged into a color golf field real map, and finally a color golf field real map with contrast enhancement and visual saliency optimization is obtained.
  • step one the original real scene map of the golf course is obtained, and the original real scene map is a color image, and the original image is decomposed into an RGB three-channel color map.
  • the image of the original real scene of the golf course obtained in the first step is image smoothed, and the details of the real image are improved.
  • Step 3 Perform image sharpening on the image smoothed image obtained in step 2, and improve the details of the real image.
  • Step 4 Perform image contrast enhancement on the image sharpened image obtained in the third step, and improve the contrast and visual saliency of the real image image.
  • Step 5 Combine the contrast-enhanced RGB three-channel color map obtained in step four into a color golf field real-life map, and determine whether the desired image visual effect is achieved according to the need, and if the desired effect is not obtained, the image is decomposed into RGB three. Channel color map and go to step two. If the effect is achieved, a color golf field real map with contrast enhancement and visual saliency optimization is finally obtained.
  • the Laplacian image sharpening operator of the 3*3 template is used for image sharpening.
  • the Gaussian image smoothing operator of the 5*5 template is used for image smoothing.
  • the histogram matching technique is used for image contrast enhancement.

Abstract

The present invention provides an image contrast enhancement and visual saliency optimization method and the application thereof to a golf course, the method comprising the following steps: obtaining an original realistic image of a golf course, and decomposing the original image into RGB three-channel colour images, i.e. three images in total; after the obtained original realistic image of the golf course is subjected to image smoothing, sharpening, and contrast enhancement, merging same into a realistic colour image of the golf course; and determining, according to requirements, whether the desired visual effect for the image has been achieved, and if the desired visual effect for the image has been achieved, finally obtaining a realistic image with enhanced contrast and optimized visual saliencyd, and if the desired effect is not achieved, decomposing the image into the RGB three-channel colour images, and repeating the above processing process, so that the image of the realistic image of the golf course is clear and the edges are obvious. The visual effects, such as fairways, long grass, greens, sandpits, and trees in the golf course, are significantly improved, and a realistic image, which has a higher contrast and a better visual effect, of the golf course is obtained.

Description

一种对比度增强和视觉显著度优化方法在高尔夫球场图中的应用Application of contrast enhancement and visual saliency optimization method in golf course map 技术领域Technical field
本发明涉及一种对比度增强和视觉显著度优化方法在高尔夫球场图中的应用。The present invention relates to the use of a contrast enhancement and visual saliency optimization method in a golf course map.
背景技术Background technique
高尔夫球场测距和定位中需要利用高尔夫球场图来标识距离和定位，现有高尔夫球场图一般使用实景图或人工示意图。实景图(包括但不限于卫星图和航拍图)为高尔夫球场测距和定位提供了直观形象的画面表达。但是球场实景图中的球道、长草、果岭、沙坑等区域，常出现对比度不高、图像颜色不显著、图像色彩视觉效果较差的问题。Golf course maps are used to identify distances and locations in golf course ranging and positioning. Existing golf course maps typically use real or manual maps. Real-life maps (including but not limited to satellite and aerial maps) provide an intuitive visual representation of golf course ranging and positioning. However, the fairway, long grass, greens, bunkers and other areas in the real scene of the stadium often have problems of low contrast, inconspicuous image color, and poor visual color image.
发明内容Summary of the invention
本发明的目的在于克服现有技术之缺陷，提供了一种对比度增强和视觉显著度优化方法在高尔夫球场中的应用，其具有更高对比度和更优视觉效果的球场实景图的特性。SUMMARY OF THE INVENTION The object of the present invention is to overcome the deficiencies of the prior art and to provide a contrast enhancement and visual saliency optimization method for use in a golf course, which has the characteristics of a stadium real map with higher contrast and better visual effects.
本发明是这样实现的：一种图像对比度增强和视觉显著度优化方法，其包括以下步骤：The present invention is achieved by an image contrast enhancement and visual saliency optimization method comprising the following steps:
步骤一、获取高尔夫球场原始实景图，原始实景图为彩色图像，将原始图分解为彩色分量图；Step 1: Obtain the original real scene map of the golf course, and the original real scene map is a color image, and the original image is decomposed into a color component map;
步骤二、对步骤一得到的高尔夫球场原始实景图做图像平滑，提升实景图图像细节；Step 2: Perform image smoothing on the original real scene of the golf course obtained in step one, and improve the details of the real scene image;
步骤三、对步骤二得到的图像平滑后的图像做图像锐化，提升实景图图像 细节；Step 3: Perform image sharpening on the image smoothed image obtained in step 2, and enhance the real scene image. detail;
步骤四、对步骤三得到的图像锐化后的图像做图像对比度增强，提高实景图图像的对比度和视觉显著度；Step 4: performing image contrast enhancement on the image sharpened image obtained in step 3, and improving contrast and visual saliency of the real image image;
步骤五、将步骤四得到的对比度增强的彩色分量图合并为一张彩色高尔夫球场实景图，根据需要判断是否达到了期望的图像视觉效果，若达到了期望的图像视觉效果，则最终获得对比度增强和视觉显著度优化的彩色高尔夫球场实景图；若没有得到期望的效果，则将图分解为彩色分量图，共三张一并转入步骤二。Step 5: Combine the contrast-enhanced color component map obtained in step 4 into a color golf field real-life map, and determine whether the desired image visual effect is achieved according to the need, and if the desired image visual effect is achieved, the contrast enhancement is finally obtained. A visual map of a color golf course optimized with visual saliency; if the desired effect is not obtained, the map is decomposed into a color component map, and a total of three sheets are transferred to step two.
进一步地，步骤三中采用拉普拉斯图像锐化算子做图像锐化处理。Further, in step three, a Laplacian image sharpening operator is used for image sharpening processing.
进一步地，步骤二中采用高斯图像平滑算子做图像平滑处理。Further, in step two, a Gaussian image smoothing operator is used for image smoothing processing.
进一步地，步骤四中采用直方图匹配技术做图像对比度增强处理。Further, in step four, a histogram matching technique is used to perform image contrast enhancement processing.
进一步地，步骤一中采用RGB分量分解将彩色图像分解为彩色分量图。Further, in step 1, RGB component decomposition is used to decompose the color image into a color component map.
一种图像对比度增强和视觉显著度优化方法在高尔夫球场图中的应用，其特征在于，包括高尔夫球场中果岭、沙坑、长草、球道等在现有卫星图中存在对比度不高和视觉效果差问题，针对高尔夫球场卫星实景图，对高尔夫球场图以图像锐化技术，图像平滑技术，图像对比度增强技术做图像处理，提高高尔夫球场图及球场图的一部分的图像的对比度和视觉显著度。An application of an image contrast enhancement and visual saliency optimization method in a golf course map, characterized in that the golf course includes greens, bunkers, long grasses, fairways, etc., which have low contrast and vision in existing satellite images. Poor effect, for the golf course satellite real map, the image of the golf course is image sharpening technology, image smoothing technology, image contrast enhancement technology, and the contrast and visual saliency of the image of the golf course map and part of the golf course map are improved. .
进一步地，包括图像锐化技术，图像锐化技术是指能减弱或消除图像中的低频率分量但不影响高频率分量的图像处理技术，包括而不限于拉普拉斯图像锐化算子、高频提升滤波、基于梯度的锐化滤波、最大和最小锐化变换、线性和非线性锐化。Further, including image sharpening techniques, image sharpening techniques refer to image processing techniques that can attenuate or eliminate low frequency components in an image without affecting high frequency components, including but not limited to Laplacian image sharpening operators, High frequency boost filtering, gradient based sharpening filtering, maximum and minimum sharpening transforms, linear and nonlinear sharpening.
进一步地，包括图像平滑技术，图像平滑技术是指能减弱或消除图像中的高频率分量但不影响低频率分量的图像处理技术，包括而不限于邻域平滑、加 权平滑、高斯平滑、中值平滑、序统计平滑、线性和非线性平滑。Further, including image smoothing technology, image smoothing technology refers to image processing technology that can attenuate or eliminate high frequency components in an image without affecting low frequency components, including but not limited to neighborhood smoothing, plus Weight smoothing, Gaussian smoothing, median smoothing, order statistical smoothing, linear and nonlinear smoothing.
进一步地，包括图像对比度增强技术，图像对比度增强技术是指能增加图像中各部分间反差的图像处理技术，包括而不限于直方图匹配，直方图均衡化，图像灰度映射。Further, including image contrast enhancement technology, image contrast enhancement technology refers to image processing technology that can increase contrast between portions of an image, including but not limited to histogram matching, histogram equalization, and image gray mapping.
进一步地，包括图像彩色分量分解，彩色分量分解是指将彩色图像分解到彩色空间描述图像色彩分量，包括而不限于RGB分解，YIQ分解，YCbCr分解，HSV分解，CMY分解，HSI分解。Further, including image color component decomposition, color component decomposition refers to decomposing color images into color space to describe image color components, including without limitation RGB decomposition, YIQ decomposition, YCbCr decomposition, HSV decomposition, CMY decomposition, HSI decomposition.
本发明将图像视觉优化技术，包括图像平滑、图像锐化、对比度增强应用于高尔夫球场卫星实景图的图像处理中，使高尔夫球场实景图的图像清晰，边缘明显，球场中的球道、长草、果岭、沙坑、树木等视觉效果显著度提高，获得了更高对比度和更优视觉效果的球场实景图。The invention applies the image visual optimization technology, including image smoothing, image sharpening and contrast enhancement, to the image processing of the golf field satellite real image, so that the image of the real scene of the golf course is clear, the edge is obvious, the fairway, the grass in the course, The visual effects of greens, bunkers, and trees are significantly improved, and a realistic view of the stadium with higher contrast and better visual effects is obtained.
附图说明DRAWINGS
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below. Obviously, the drawings in the following description are only It is a certain embodiment of the present invention, and other drawings can be obtained from those skilled in the art without any inventive labor.
图1为本发明实施例提供的流程图。FIG. 1 is a flowchart provided by an embodiment of the present invention.
具体实施方式detailed description
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。The technical solutions in the embodiments of the present invention are clearly and completely described in the following with reference to the accompanying drawings in the embodiments of the present invention. It is obvious that the described embodiments are only a part of the embodiments of the present invention, but not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts are within the scope of the present invention.
如图1，本发明实施例提供一种图像对比度增强和视觉显著度优化方法在高 尔夫球场卫星实景图图像处理中的应用，本发明包括两个方案，具体请参见如下叙述。As shown in FIG. 1 , an embodiment of the present invention provides an image contrast enhancement and a visual saliency optimization method at a high level. The application of the satellite scene image processing in the golf course, the present invention includes two schemes, as described below.
方案一:Option One:
一种图像对比度增强和视觉显著度优化方法在高尔夫球场实景图图像处理中的应用，具体步骤如下：An application of image contrast enhancement and visual saliency optimization method in golf course real image processing, the specific steps are as follows:
步骤一，获取高尔夫球场原始实景图，原始实景图为彩色图像，将原始图分解为RGB三通道色彩图，共三张，具体地，原始高尔夫球场实景图为彩色图像F(i,j)，将原图分解为RGB三通道色彩图，共三张,分别为FR(i,j)，FG(i,j)，FB(i,j)。Step 1: Obtain the original real scene map of the golf course, and the original real scene map is a color image, and the original image is decomposed into three RGB three-channel color maps. Specifically, the original golf scene real scene map is a color image F(i, j), the original image is decomposed into RGB three-channel color map, a total of three, are F R (i, j), F G (i, j), F B (i, j).
步骤二，对步骤一得到的高尔夫球场原始实景图做图像平滑，提升实景图图像细节，(FR(i,j)，FG(i,j)，FB(i,j))分别进行图像平滑，提升图像细节，作为优选，采用5*5模板的高斯图像平滑算子做图像平滑，数学表达式为Step 2: Perform image smoothing on the original real scene of the golf course obtained in the first step, and improve the details of the real image, (F R (i, j), F G (i, j), F B (i, j)) respectively Smoothing the image and improving the image detail. As a preference, the Gaussian image smoothing operator of the 5*5 template is used for image smoothing. The mathematical expression is
Figure PCTCN2017088920-appb-000001
Figure PCTCN2017088920-appb-000001
原始图为F，平滑后的图像为Fgau The picture shows the original F, as the smoothed image F gau
Figure PCTCN2017088920-appb-000002
Figure PCTCN2017088920-appb-000002
Figure PCTCN2017088920-appb-000003
表示卷积运算
Figure PCTCN2017088920-appb-000003
Convolution operation
高斯平滑滤波是一种线性平滑滤波，适用于消除高斯噪声,每一个像素点的值，都由其本身和邻域内的其他像素值经过加权平均后得到.通过高斯平滑滤波，可以降低图像中的噪声，得到实景图的细节视觉优化效果。Gaussian smoothing is a kind of linear smoothing filter, which is suitable for eliminating Gaussian noise. The value of each pixel is obtained by weighted averaging of itself and other pixel values in the neighborhood. Gaussian smoothing filtering can reduce the image. Noise, get the visual optimization effect of the details of the real scene.
步骤三，对步骤二得到的图像平滑后的图像做图像锐化，提升实景图图像细节。作为优选，采用3*3模板的拉普拉斯图像锐化算子做图像锐化，数学表达 式为Step 3: Perform image sharpening on the image smoothed image obtained in step 2, and improve the details of the real image. Preferably, the Laplacian image sharpening operator of the 3*3 template is used for image sharpening, mathematical expression Formula
Figure PCTCN2017088920-appb-000004
Figure PCTCN2017088920-appb-000004
锐化后的图像为Fl The sharpened image is F l
Figure PCTCN2017088920-appb-000005
Figure PCTCN2017088920-appb-000005
Figure PCTCN2017088920-appb-000006
表示卷积运算
Figure PCTCN2017088920-appb-000006
Convolution operation
拉普拉斯算子是微分操作符，卷积运算得到的图像将使原图锐化，同时使常量区域为零。通过从平滑图中减去拉普拉斯算子处理过的结果，还原常量区域，得到锐化后的图像Fl。The Laplacian operator is a differential operator, and the image obtained by the convolution operation will sharpen the original image while making the constant region zero. By subtracting the result processed by the Laplacian from the smoothed graph, the constant region is restored, and the sharpened image F l is obtained .
步骤四，对步骤三得到的图像锐化后的图像做图像对比度增强，提高实景图图像的对比度和视觉显著度。Step 4: Perform image contrast enhancement on the image sharpened image obtained in the third step, and improve the contrast and visual saliency of the real image image.
作为优选，采用直方图匹配技术做图像对比度增强。Preferably, the histogram matching technique is used for image contrast enhancement.
高尔夫球场的实景图中，主要显示物为球道、长草、果岭、沙坑、树木等。对于分解为RGB三色彩通道的分量图像，在它们的灰度级区间[0，255]的实景图的分量直方图中，主要灰度级集中在灰度较小区域。通过直方图匹配，将集中在灰度较小区域的灰度等级映射到[0，255]，同时保持灰度等级的相对比例，从而得到图像亮度提高和对比度增强的效果。In the real scene of the golf course, the main display objects are fairways, long grasses, greens, bunkers, trees, and the like. For component images decomposed into RGB three color channels, in the component histogram of the real scene of their gray level interval [0, 255], the main gray levels are concentrated in the smaller gray areas. By histogram matching, the gray level concentrated in the small gray area is mapped to [0, 255] while maintaining the relative proportion of the gray level, thereby obtaining the effect of image brightness enhancement and contrast enhancement.
令r和z分别表示输入和输出图像的灰度级，输入灰度级的概率密度函数为pr(r),输出灰度级的概率密度函数为pz(z)。对输入图的直方图进行灰度均衡化：Let r and z represent the gray level of the input image and an output, the input gray level of the probability density function P r (r), the output gray level of the probability density function p z (z). Grayscale equalization of the histogram of the input graph:
Figure PCTCN2017088920-appb-000007
Figure PCTCN2017088920-appb-000007
对于期望得到的输出图灰度直方图： For the desired output map gray histogram:
Figure PCTCN2017088920-appb-000008
Figure PCTCN2017088920-appb-000008
于是有，Then there,
z＝H-1(s)＝H-1[T(r)] z = H -1 (s) = H -1 [T (r)]
通过给定期望的输出图直方图，可以得到H-1反变换函数，从而可以得到从输入图到期望的输出直方图的像素值变换函数，并将输入图映射到期望的对比度增强的输出图。By giving the desired output graph histogram, the H -1 inverse transform function can be obtained, so that the pixel value transform function from the input graph to the desired output histogram can be obtained, and the input graph can be mapped to the desired contrast enhanced output graph. .
步骤五，将步骤四得到的对比度增强的RGB三通道色彩图合并为彩色高尔夫球场实景图，最终获得对比度增强和视觉显著度优化的彩色高尔夫球场实景图。In step 5, the contrast-enhanced RGB three-channel color map obtained in step four is merged into a color golf field real map, and finally a color golf field real map with contrast enhancement and visual saliency optimization is obtained.
方案二:Option II:
一种多次迭代的图像对比度增强和视觉显著度优化方法在高尔夫球场实景图图像处理中的应用，步骤如下：An application of image iteration enhancement and visual saliency optimization method for multiple iterations in golf field image processing, the steps are as follows:
步骤一，获取高尔夫球场原始实景图，原始实景图为彩色图像，将原始图分解为RGB三通道色彩图。In step one, the original real scene map of the golf course is obtained, and the original real scene map is a color image, and the original image is decomposed into an RGB three-channel color map.
步骤二，对步骤一得到的高尔夫球场原始实景图做图像平滑，提升实景图图像细节。In the second step, the image of the original real scene of the golf course obtained in the first step is image smoothed, and the details of the real image are improved.
步骤三，对步骤二得到的图像平滑后的图像做图像锐化，提升实景图图像细节。Step 3: Perform image sharpening on the image smoothed image obtained in step 2, and improve the details of the real image.
步骤四，对步骤三得到的图像锐化后的图像做图像对比度增强，提高实景图图像的对比度和视觉显著度。Step 4: Perform image contrast enhancement on the image sharpened image obtained in the third step, and improve the contrast and visual saliency of the real image image.
步骤五，将步骤四得到的对比度增强的RGB三通道色彩图合并为彩色高尔夫球场实景图，根据需要判断是否达到了期望的图像视觉效果，若没有得到期望的效果，则将图分解为RGB三通道色彩图并转入步骤二。若达到效果，则最终获得对比度增强和视觉显著度优化的彩色高尔夫球场实景图。 Step 5: Combine the contrast-enhanced RGB three-channel color map obtained in step four into a color golf field real-life map, and determine whether the desired image visual effect is achieved according to the need, and if the desired effect is not obtained, the image is decomposed into RGB three. Channel color map and go to step two. If the effect is achieved, a color golf field real map with contrast enhancement and visual saliency optimization is finally obtained.
作为优选，采用3*3模板的拉普拉斯图像锐化算子做图像锐化。Preferably, the Laplacian image sharpening operator of the 3*3 template is used for image sharpening.
作为优选，采用5*5模板的高斯图像平滑算子做图像平滑。Preferably, the Gaussian image smoothing operator of the 5*5 template is used for image smoothing.
作为优选，采用直方图匹配技术做图像对比度增强。Preferably, the histogram matching technique is used for image contrast enhancement.
以上所述仅为本发明的较佳实施例而已，并不用以限制本发明，凡在本发明的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本发明的保护范围之内。 The above is only the preferred embodiment of the present invention, and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., which are included in the spirit and scope of the present invention, should be included in the present invention. Within the scope of protection.

Claims (10)

  1. 一种图像对比度增强和视觉显著度优化方法，其特征在于，包括以下步骤：An image contrast enhancement and visual saliency optimization method, comprising the steps of:
    步骤一、获取高尔夫球场原始实景图，原始实景图为彩色图像，将原始图分解为彩色分量图；Step 1: Obtain the original real scene map of the golf course, and the original real scene map is a color image, and the original image is decomposed into a color component map;
    步骤二、对步骤一得到的高尔夫球场原始实景图做图像平滑，提升实景图图像细节；Step 2: Perform image smoothing on the original real scene of the golf course obtained in step one, and improve the details of the real scene image;
    步骤三、对步骤二得到的图像平滑后的图像做图像锐化，提升实景图图像细节；Step 3: Perform image sharpening on the image smoothed image obtained in step 2, and improve the details of the real image image;
    步骤四、对步骤三得到的图像锐化后的图像做图像对比度增强，提高实景图图像的对比度和视觉显著度；Step 4: performing image contrast enhancement on the image sharpened image obtained in step 3, and improving contrast and visual saliency of the real image image;
    步骤五、将步骤四得到的对比度增强的彩色分量图合并为一张彩色高尔夫球场实景图，根据需要判断是否达到了期望的图像视觉效果，若达到了期望的图像视觉效果，则最终获得对比度增强和视觉显著度优化的彩色高尔夫球场实景图；若没有得到期望的效果，则将图分解为彩色分量图，共三张一并转入步骤二。Step 5: Combine the contrast-enhanced color component map obtained in step 4 into a color golf field real-life map, and determine whether the desired image visual effect is achieved according to the need, and if the desired image visual effect is achieved, the contrast enhancement is finally obtained. A visual map of a color golf course optimized with visual saliency; if the desired effect is not obtained, the map is decomposed into a color component map, and a total of three sheets are transferred to step two.
  2. 如权利要求1所述的一种高尔夫球场实景图的对比度增强和视觉显著度优化方法，其特征在于：步骤三中采用拉普拉斯图像锐化算子做图像锐化处理。The contrast enhancement and visual saliency optimization method for a golf course real scene according to claim 1, wherein the Laplacian image sharpening operator is used in the third step to perform image sharpening processing.
  3. 如权利要求1所述的一种高尔夫球场实景图的对比度增强和视觉显著度优化方法，其特征在于：步骤二中采用高斯图像平滑算子做图像平滑处理。The contrast enhancement and visual saliency optimization method of a golf course real scene according to claim 1, wherein the Gaussian image smoothing operator is used in the second step to perform image smoothing processing.
  4. 如权利要求1所述的一种高尔夫球场实景图的对比度增强和视觉显著度优化方法，其特征在于：步骤四中采用直方图匹配技术做图像对比度增强处理。The contrast enhancement and visual saliency optimization method for a golf course real scene according to claim 1, wherein the image contrast enhancement processing is performed by using a histogram matching technique in the fourth step.
  5. 如权利要求1所述的一种高尔夫球场实景图的对比度增强和视觉显著度优化方法，其特征在于：步骤一中采用RGB分量分解将彩色图像分解为彩色 分量图。A contrast enhancement and visual saliency optimization method for a golf course real scene according to claim 1, wherein in step 1, RGB component decomposition is used to decompose the color image into color. Component map.
  6. 一种如权利要求1所述的图像对比度增强和视觉显著度优化方法在高尔夫球场图中的应用，其特征在于，包括高尔夫球场中果岭、沙坑、长草、球道等在现有卫星图中存在对比度不高和视觉效果差问题，针对高尔夫球场卫星实景图，对高尔夫球场图以图像锐化技术，图像平滑技术，图像对比度增强技术做图像处理，提高高尔夫球场图及球场图的一部分的图像的对比度和视觉显著度。An image contrast enhancement and visual saliency optimization method according to claim 1 for use in a golf course map, comprising: a golf course, a green, a bunker, a long grass, a fairway, etc. in an existing satellite image There is a problem of low contrast and poor visual effects. For the golf course satellite real map, the image of the golf course is image sharpening, image smoothing, image contrast enhancement technology is used to improve the golf course map and part of the golf course map. The contrast and visual saliency of the image.
  7. 一种如权利要求6所述的图像对比度增强和视觉显著度优化方法在高尔夫球场图中的应用，其特征在于，包括图像锐化技术，图像锐化技术是指能减弱或消除图像中的低频率分量但不影响高频率分量的图像处理技术，包括而不限于拉普拉斯图像锐化算子、高频提升滤波、基于梯度的锐化滤波、最大和最小锐化变换、线性和非线性锐化。An image contrast enhancement and visual saliency optimization method according to claim 6 for use in a golf course map, characterized in that it includes an image sharpening technique, which means that the image sharpening technique can be reduced or eliminated. Image processing techniques that do not affect frequency components, including but not limited to Laplacian image sharpening operators, high-frequency lifting filters, gradient-based sharpening filtering, maximum and minimum sharpening transforms, linear and nonlinear Sharpen.
  8. 一种如权利要求6所述的图像对比度增强和视觉显著度优化方法在高尔夫球场图中的应用，其特征在于，包括图像平滑技术，图像平滑技术是指能减弱或消除图像中的高频率分量但不影响低频率分量的图像处理技术，包括而不限于邻域平滑、加权平滑、高斯平滑、中值平滑、序统计平滑、线性和非线性平滑。An image contrast enhancement and visual saliency optimization method according to claim 6 for use in a golf course map, characterized in that it comprises an image smoothing technique, which is capable of reducing or eliminating high frequency components in an image. Image processing techniques that do not affect low frequency components include, but are not limited to, neighborhood smoothing, weighted smoothing, Gaussian smoothing, median smoothing, sequential statistical smoothing, linear and nonlinear smoothing.
  9. 一种如权利要求6所述的图像对比度增强和视觉显著度优化方法在高尔夫球场图中的应用，其特征在于，包括图像对比度增强技术，图像对比度增强技术是指能增加图像中各部分间反差的图像处理技术，包括而不限于直方图匹配，直方图均衡化，图像灰度映射。The invention relates to an image contrast enhancement and visual saliency optimization method according to claim 6, which is characterized in that it comprises an image contrast enhancement technology, and the image contrast enhancement technology refers to an increase in contrast between parts in an image. Image processing techniques include, without limitation, histogram matching, histogram equalization, and image grayscale mapping.
  10. 一种如权利要求6所述的图像对比度增强和视觉显著度优化方法在高尔夫球场图中的应用，其特征在于，包括图像彩色分量分解，彩色分量分解是 指将彩色图像分解到彩色空间描述图像色彩分量，包括而不限于RGB分解，YIQ分解，YCbCr分解，HSV分解，CMY分解，HSI分解。 An image contrast enhancement and visual saliency optimization method according to claim 6 for use in a golf course map, characterized in that it comprises image color component decomposition, and color component decomposition is Refers to decomposing color images into color space to describe image color components, including but not limited to RGB decomposition, YIQ decomposition, YCbCr decomposition, HSV decomposition, CMY decomposition, HSI decomposition.
PCT/CN2017/088920 2017-03-13 2017-06-19 Application of contrast enhancement and visual saliency optimization method in golf course image WO2018166083A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710147632.4 2017-03-13
CN201710147632.4A CN106971380A (en) 2017-03-13 2017-03-13 A kind of contrast enhancing and application of the visual saliency optimization method in golf course figure

Publications (1)

Publication Number Publication Date
WO2018166083A1 true WO2018166083A1 (en) 2018-09-20

Family

ID=59329486

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/088920 WO2018166083A1 (en) 2017-03-13 2017-06-19 Application of contrast enhancement and visual saliency optimization method in golf course image

Country Status (2)

Country Link
CN (1) CN106971380A (en)
WO (1) WO2018166083A1 (en)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108024103A (en) * 2017-12-01 2018-05-11 重庆贝奥新视野医疗设备有限公司 Image sharpening method and device
CN108259873B (en) * 2018-02-01 2020-03-17 电子科技大学 Gradient domain video contrast enhancement method
CN108564072A (en) * 2018-05-25 2018-09-21 平安科技（深圳）有限公司 Iris image Enhancement Method, device, equipment and medium based on multi task process
CN109359654B (en) * 2018-09-18 2021-02-12 北京工商大学 Image segmentation method and system based on frequency tuning global saliency and deep learning
CN109788197A (en) * 2019-01-10 2019-05-21 李�杰 Intelligent face recognition method and storage medium
CN110266268B (en) * 2019-06-26 2020-11-10 武汉理工大学 Photovoltaic module fault detection method based on image fusion recognition

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6757442B1 (en) * 2000-11-22 2004-06-29 Ge Medical Systems Global Technology Company, Llc Image enhancement method with simultaneous noise reduction, non-uniformity equalization, and contrast enhancement
CN1793913A (en) * 2005-12-28 2006-06-28 浙江工业大学 Biological water monitoring device based on machine vision
CN101196979A (en) * 2006-12-22 2008-06-11 四川川大智胜软件股份有限公司 Method for recognizing vehicle type by digital picture processing technology
CN101350109A (en) * 2008-09-05 2009-01-21 交通部公路科学研究所 Method for locating and controlling multilane free flow video vehicle
CN103778611A (en) * 2014-01-26 2014-05-07 天津大学 Switch weighting vector median filter method utilizing edge detection
CN104320622A (en) * 2014-10-30 2015-01-28 上海电力学院 Embedded video enhancement system for open source server software

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102262778A (en) * 2011-08-24 2011-11-30 重庆大学 Method for enhancing image based on improved fractional order differential mask
CN104182947B (en) * 2014-09-10 2017-04-26 安科智慧城市技术（中国）有限公司 Low-illumination image enhancement method and system

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6757442B1 (en) * 2000-11-22 2004-06-29 Ge Medical Systems Global Technology Company, Llc Image enhancement method with simultaneous noise reduction, non-uniformity equalization, and contrast enhancement
CN1793913A (en) * 2005-12-28 2006-06-28 浙江工业大学 Biological water monitoring device based on machine vision
CN101196979A (en) * 2006-12-22 2008-06-11 四川川大智胜软件股份有限公司 Method for recognizing vehicle type by digital picture processing technology
CN101350109A (en) * 2008-09-05 2009-01-21 交通部公路科学研究所 Method for locating and controlling multilane free flow video vehicle
CN103778611A (en) * 2014-01-26 2014-05-07 天津大学 Switch weighting vector median filter method utilizing edge detection
CN104320622A (en) * 2014-10-30 2015-01-28 上海电力学院 Embedded video enhancement system for open source server software

Also Published As

Publication number Publication date
CN106971380A (en) 2017-07-21

Similar Documents

Publication Publication Date Title
WO2018166083A1 (en) Application of contrast enhancement and visual saliency optimization method in golf course image
Ren et al. Joint enhancement and denoising method via sequential decomposition
CN104156921B (en) Self-adaptive low-illuminance or non-uniform-brightness image enhancement method
Zhou et al. Retinex-based laplacian pyramid method for image defogging
Ancuti et al. Effective single image dehazing by fusion
Vishwakarma et al. Color image enhancement techniques: a critical review
CN103942758A (en) Dark channel prior image dehazing method based on multiscale fusion
Park et al. Contrast enhancement for low-light image enhancement: A survey
CN110796626B (en) Image sharpening method and device
Wang et al. Variational single nighttime image haze removal with a gray haze-line prior
Kim et al. Single image haze removal using hazy particle maps
CN108648160B (en) Underwater sea cucumber image defogging enhancement method and system
CN111968065A (en) Self-adaptive enhancement method for image with uneven brightness
Tang et al. A local flatness based variational approach to retinex
Gu et al. A novel Retinex image enhancement approach via brightness channel prior and change of detail prior
Wen et al. Autonomous robot navigation using Retinex algorithm for multiscale image adaptability in low-light environment
Zhang et al. Underwater image enhancement via multi-scale fusion and adaptive color-gamma correction in low-light conditions
CN113344810A (en) Image enhancement method based on dynamic data distribution
CN110706180B (en) Method, system, equipment and medium for improving visual quality of extremely dark image
CN110415185B (en) Improved Wallis shadow automatic compensation method and device
Goel et al. An efficient approach to restore naturalness of non-uniform illumination images
CN111127350A (en) Image enhancement method
Lian et al. Learning intensity and detail mapping parameters for dehazing
Negru et al. Exponential image enhancement in daytime fog conditions
CN109886901B (en) Night image enhancement method based on multi-channel decomposition

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17900987

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 17900987

Country of ref document: EP

Kind code of ref document: A1