untitled.asv

统计模式识别工具包(统计模式识别工具包

i=1
X=newdata{1};
model=pca(X,1);
Z = linproj(X,model); % lower dim. proj.
XR = pcarec(X,model); % reconstr. data
figure; hold on; axis equal; % visualization
h1 = ppatterns(X,'kx');
h2 = ppatterns(XR,'bo');
[dummy,mn] = min(Z);
[dummy,mx] = max(Z);
h3 = plot([XR(1,mn) XR(1,mx)],[XR(2,mn) XR(2,mx)],'r');
legend([h1 h2 h3],'Input vectors','Reconstructed','PCA subspace');
hold on;
plot(newdata{i,1}(:,1),newdata{i,1}(:,2),'r-');
        hold on;
        %绘出背景模型
        x1=[320,0];
        y1=[135,110];
        plot(x1,y1);
        hold on;
        x2=[0,150];
        y2=[240,0];
        plot(x2,y2);
        hold on;
        x3=[80,280];
        y3=[240,0];
        plot(x3,y3);
        hold on;
        x4=[150,320];
        y4=[240,75];
        plot(x4,y4);
        hold on;
        x4=[150,320];
        y4=[240,75];
        plot(x4,y4);
        hold on;
        x5=[0,320];
        y5=[240,240];
        plot(x5,y5);
        hold on;
        x6=[320,320];
        y6=[0,240];
        plot(x6,y6);
        hold on;
        %画出各个lane    
        x7=[38,202];
        y7=[240,0];
        plot(x7,y7,'b-.');
        hold on;
        x8=[57,235];
        y8=[240,0];
        plot(x8,y8,'b-.');
        hold on;
        x9=[100,308];
        y9=[240,0];
        plot(x9,y9,'b-.');
        hold on;
        x10=[116,320];
        y10=[240,22];
        plot(x10,y10,'b-.');
        hold on;