視覺移動機器人控制系統(tǒng)設計

購買設計請充值后下載，資源目錄下的文件所見即所得，都可以點開預覽，資料完整，充值下載可得到資源目錄里的所有文件?！咀ⅰ浚篸wg后綴為CAD圖紙，doc,docx為WORD文檔，原稿無水印，可編輯。具體請見文件預覽，有不明白之處，可咨詢QQ:12401814 附錄外文資料 Typically, an image-processing application consists of five steps. First, an image must be acquired. A digitized representation of the image is necessary for further processing. This is denoted with a two-dimensional function I（x， y） that is described with an array. X marks a column and y a row of the array. The domain for x and y depends on the maximal resolution of the image. If the image has size n m, whereby n represents the number of rows and m the number of columns, then itholds for x that 0 x m, and for the y analog, 0 y n. x and y are positive integers or zero. This holds also for the domain of I. I（x，y）is the maximal value for the function value. This then provides the domain, 0 I(x, y) I(x; y). Every possible discrete function value represents a gray value and is called a pixel. Subsequent preprocessing tries to eliminate disturbing effects. Examples are inhomogeneous illumination noise, and movement detection. If image-preprocessing algorithms like the movement detection are applied to an image, it is possible that image pixels of different objects with different properties are merged into regions, because they fulfill the criteria of the preprocessing algorithm. Therefore, a region can be considered as the accumulation of coherent pixels that must not have any similarities. These image regions or the whole image can be decomposed into segments. All contained pixels must be similar in these segments.Pixels will be assigned to objects in the segmentation phase, which is the third step. If objects are isolated from the remainder of the image in the segmentation phase, feature values of these objects must be acquired in the fourth step. The features determined are used in the fifth and last step to perform the classification. This means that the detected objects are allocated to an object class if their measured feature values match to the object description. Examples for features are the object height, object width, compactness, and circularity.A circular region has the compactness of one. The alteration of the regions length effects the alteration of the compactness value. The compactness becomes larger if the regions length rises. An empty region has value zero for the compactness.Color ModelsThe process of vision by a human being is also controlled by colors. This happens subconsciously with signal colors. But a human being searches in some situations directly for specified colors to solve a problem. The color attribute of an object can also be used in computer vision. This knowledge can help to solve a task .For example,a computer-vision application that is developed to detect people can use knowledge about the color of the skin for the detection. This can affect ambiguity in some situations. For example, an image that is taken from a human being who walks beside a carton is difficult to detect, if the carton has a similar color to the color of the skin. But there are more problems. The color attributes of objects can be affected by other objects due to light reflections of these objects. Also colors of different objects that belong to the same class, can vary. For example, a European has a different skin color from an African although both belong to the class “human being”. Color attributes like hue, saturation, intensity, and spectrum can be used to identify objects by its color. Alterations of these parameters can effect different reproductionsof the same object. This is often very difficult to handle in computer-vision applications. Such alterations are as a rule for a human being no or only a small problem for recognition. The selection of an appropriate color space can help in computer vision. Several color spaces exist. Two often-used color spaces are now depicted. These are RGB and YUV color spaces. The RGB color space consists of three color channels. These are the red, green, and blue channels. Every color is representedby its red, green, and blue parts. This coding follows the three-color theory of Gauss. A pixels color part of a channel is often measured within the interval 0; 255. Therefore, a color image consists of three gray images. The RGB color space is not very stable with regard to alterations in the illumination, because the representation of a color with the RGB color space contains no separation between the illumination and the color parts. If a computer-vision application, which performs image analysis on color images, is to be robust against alterations in illumination, the YUV color space could be a better choice, because the color parts and the illumination are represented separately. The color representation happens only with two channels, U and V. Y channel measures the brightness. The conversion between the RGB and the YUV color space happens with a linear transformation: (1-1)This yields the following equations: Y=0.299R+0.587G+0.114B (1-2)U=-0.147R-0.289G+0.436B (1-3)V=0.615R-0.514G-0.101B (1-4)To show the robustness of the YUV color space with regard to the illumination, the constant c will be added to the RGB color parts. Positive c effects a brighter color impression and negative c a darker color impression. The constant c affects only the brightness Y and not the color parts U and V in the YUV color space if a transformation into the YUV color space is performed: Y=Y+C (1-5) U=U+C (1-6) V=V+C (1-7)The sum of the weights in Equations (1.3) and (1.4) is zero. Therefore, the value of the constant c in the color parts is mutually cancelled. The addition of the constant c is only represented in Equation (1.2). This shows that the alteration of the brightness effects an incorrect change in the color parts of the RGB color space, whereas only the Y part is affected in the YUV color space. Examinations of different color spaces have shown that the robustness can be further improved if the color parts are normalized and the weights are varied. One of these color spaces, where this was applied, is the (YUV)color space, which is very similar to the YUV color space. The transformation from the RGB color space into the (YUV)color space is: (1.8)The explanations show that the YUV color space should be preferred for object detection by the use of the color attribute if the computer-vision application has to deal with changes in the illumination.中文翻譯通常,一個是圖像處理申請有5個步驟。首先,一個圖像是必須得到的。如果要進行更深入的圖像分析，這就需要一個數(shù)字化表示法 了。這是一個二維函數(shù)表示,I（x，y），它用一個數(shù)列描述。x標記的一個橫坐標和y表示縱坐標的數(shù)組。該域名x和y取決于圖像最大分辨率。如果圖像的大小為nm,由此n代表行數(shù)，m代表的列數(shù),那么它適用于,并適用于，x和y正整數(shù)或零。I（x, y）是這個鄰域里的最大的函數(shù)值，0 I（x，y） I(x, y)max。每一種可能的離散函數(shù)值代表一個灰色的價值，這被稱為是一個像素。后續(xù)的預處理則是用來消除干擾效果的。例如均勻照明,去噪和運動檢測。如果視覺算法比如同運動檢測算法那樣應用到一個圖像里面,很可能是不同物體的像素和不同的屬性并入到一個圖像區(qū)域,因為它們滿足了標準的預處理算法。因此,這個區(qū)域可被視為是一連貫的像素累積的，并且這些像素之間肯定沒有任何相似之處。這些圖像區(qū)域或整個圖像可以被分解成片段。在這些片段里面，所有包含的像素必須是相似的。在這個階段，這些像素將被分屬給物體，這就是是第三步。在分解片段的過程中，如果目標物體特征值與圖片的剩余部分相隔離,這些物體特征值必須獲得第四步。這個特點確定了在第五步和最后一步進行分類。這意味著如果被測物體的測量特征值與物體的描述相符合，被檢測物體將會定位到一個對象等級,例如特征值為物體的高度、寬度、體積。顏色模型人類的視覺過程也是由顏色控制的。這一切發(fā)生的時候,潛意識里只是單種顏色。但人類在某些情況下只是搜索一些特定的顏色,直接去解決某個問題。色彩屬性的對象也可以應用在計算機視覺。這些知識能幫助你解決一些事情。例如,一個計算機視覺程序研制了一種膚色檢測算法。但在某些情況下會受到一些影響。例如,一幅取自走在紙箱旁邊的人的圖像，如果紙箱也有類似皮膚的顏色，這就會很難察覺。但是還有更多的問題。物體顏色的屬性可能會受到其他物體反射光的影響，雖然不同的物體顏色等級是一樣的屬于同一類,但這是可以改變的。例如,歐洲人的膚色和非洲人的不同，但他們都屬于“人”這個屬性。顏色屬性例如色調(diào),飽和,光譜強度,可以利用這些顏色屬性來識別物體。這些參數(shù)的變化會影響相同對象的不同復制品。這在計算機視覺處理應用程序里通常是很難的。這樣的改變在人類世界里或許很正常，或者在識別的時候只是個很小的問題。在計算機視覺里選擇適當?shù)纳士臻g是會很有幫助的，幾種顏色空間共同存在?，F(xiàn)在經(jīng)常使用的是兩種色彩空間，是RGB和YUV色彩空間。這個RGB顏色空間包括三種顏色通道，它們是紅、綠、藍三種顏色通道。每種顏色都是由紅、綠、藍三部分按不同數(shù)值分配所呈現(xiàn)出來的。這些數(shù)值遵循高斯三色理論。一個顏色通道的像素通常是在0到255之間。因此,彩色圖像灰度圖像包含三個。但當亮度發(fā)生變化的時候，這個RGB顏色空間在不是很穩(wěn)定的范圍里變化,因為顏色的呈現(xiàn)和RGB顏色空間在亮度和色彩上沒有脫節(jié)。如果一個用于圖像分析計算機視覺程序，在亮度改變的情況下不能正常的運行，YUV可能是一個更好的選擇,因為顏色和亮度是分離表現(xiàn)出來的。顏色表示只發(fā)生在兩個渠道上，U和V.Y方面只負責亮度的調(diào)節(jié)。RGB模式和YUV模式之間的轉換存在一個線性關系。= (1-1)上式可變換為： Y=0.299R+0.587G+0.114B (1-2)U=-0.147R-0.289G=0.436B (1-3)V=0.615R-0.514GG-0.101B (1-4)為了展示當亮度變化時，YUV顏色空間的穩(wěn)定性，我們將常數(shù)c添加到RGB顏色部分。正的常數(shù)c影響亮色的呈現(xiàn)，而負的常數(shù)影響暗色的呈現(xiàn)。在顏色空間里，常數(shù)c只影響亮度Y而不對U、V部分造成影響。在YUV顏色模型空間中，如果轉變用下式來表示：Y=Y+C (1-5)U=U+C (1-6)V=V+C (1-7)式(2.3)和(2.4)的和為零。因此,實際上常數(shù)c在顏色模型空間里的部分是被取消了。常數(shù)c的添加只是在式（2.2）中發(fā)揮了作用。這表明在RGB顏色空間里,亮度的變化對圖像造成了錯誤的影響，在顏色空間里，只有Y分量被影響了。審核不同顏色的空間模型可以發(fā)現(xiàn)：如果顏色的部分被標準化，值多樣化，那么圖像的穩(wěn)定性會被大大的提高。在色彩模型空間里,有一種模型會被用到，它就是YUV色彩空間,它非常類似于采用基于YUV彩色空間。從RGB顏色空間轉換到YUV顏色空間需用到下式： (1-8)這個解釋表明,在利用顏色屬性進行目標檢測的時候，如果計算機程序無法解決亮度的問題，應首選YUV顏色模型空間。