From: Ashar on 15 Apr 2010 20:14 Hi everyone, i m currently working on object tracking for undergraduate final project. i'm using regionprops to get bounding box for every object on my image. but... i just want to track single object, how to eliminate other object that i dont need ? this is my code : for i=1:1:193 %(number of image) file_name=strcat('beta_',int2str(i),'.jpg'); im1=imread(file_name); image=adaptivethreshold(im1,10,0.08,0); %additional adaptive threshold SE = strel('square', 5); biner_dilate=imdilate(image,SE); %pixel dilatation biner_filter= bwareaopen(biner_dilate,150); SE = strel('square', 20); biner_dilate_2=imdilate(biner_filter,SE); %pixel dilatation region=regionprops(biner_dilate_2); %regionprops koordinat_x=region(1,1).BoundingBox(1,1); koordinat_y=region(1,1).BoundingBox(1,2); width_x=region(1,1).BoundingBox(1,3); width_y=region(1,1).BoundingBox(1,4); center_x=region(1,1).Centroid(1,1); center_y=region(1,1).Centroid(1,2); figure(1) frame_count=strcat('frame ke :',int2str(i)); subplot(2,2,1); imshow(im1); title(frame_count); subplot(2,2,2); imshow(image); title('adaptive threshold'); subplot(2,2,3); imshow(biner_dilate_2); title('test dilate 2'); subplot(2,2,4); imshow(biner_filter); title('filter'); subplot(2,2,1),rectangle('Position',[koordinat_x,koordinat_y,width_x,width_y], 'Edge', 'g', 'LineWidth',2); hold on subplot(2,2,1),plot(center_x,center_y,'g+'); hold off end
From: ImageAnalyst on 15 Apr 2010 22:45 How is it supposed to know which one of the dozens of blobs there is the one that you want to keep? You have to tell it, by giving it instructions that identify the blob you're interested in. It could be thresholding on area, perimeter, intensity, etc. But whatever characteristics your blob has that makes it unique from all other blobs is what you have to program in there.
From: Ashar on 16 Apr 2010 02:34 ImageAnalyst <imageanalyst(a)mailinator.com> wrote in message <603e5ec5-4f8c-4961-8d36-5af57040df51(a)20g2000vbr.googlegroups.com>... > How is it supposed to know which one of the dozens of blobs there is > the one that you want to keep? You have to tell it, by giving it > instructions that identify the blob you're interested in. It could be > thresholding on area, perimeter, intensity, etc. But whatever > characteristics your blob has that makes it unique from all other > blobs is what you have to program in there. hmm... okey... you right. thank you very much imageanalyst. :D you open my mind, hehe...
|
Pages: 1 Prev: Search of data within vector Next: How to delete string from a list of cells |