How to recover the background image of a sequence

25 outubro 2018, 11:00 • João Paulo Salgado Arriscado Costeira

Given a sequence taken from a static camera, how to compute the background image using the median (explained in class). Check with twocams_books dataset.

imgmed=zeros(480,640,45);

for i=1:45,

    load(['depth1_' int2str(i) '.mat']);

    imagesc(depth_array);

    imgmed(:,:,i)=double(depth_array)/1000;

    pause(.1)

    drawnow;

end

bg=median(imgmed,3);

d=dir('depth1*.mat');

for i=1:length(d),

    load(d(i).name);

    imagesc(abs(double(depth_array)/1000-bg)>.25);

    colormap(gray);

    pause(1);

end

How to recover the background image of a sequence

25 outubro 2018, 08:00 • João Paulo Salgado Arriscado Costeira

Given a sequence taken from a static camera, how to compute the background image using the median (explained in class). Check with twocams_books dataset.

imgmed=zeros(480,640,45);

for i=1:45,

    load(['depth1_' int2str(i) '.mat']);

    imagesc(depth_array);

    imgmed(:,:,i)=double(depth_array)/1000;

    pause(.1)

    drawnow;

end

bg=median(imgmed,3);

d=dir('depth1*.mat');

for i=1:length(d),

    load(d(i).name);

    imagesc(abs(double(depth_array)/1000-bg)>.25);

    colormap(gray);

    pause(1);

end

How to recover the background image of a sequence

22 outubro 2018, 17:00 • João Paulo Salgado Arriscado Costeira

Given a sequence taken from a static camera, how to compute the background image using the median (explained in class). Check with twocams_books dataset.

imgmed=zeros(480,640,45);

for i=1:45,

    load(['depth1_' int2str(i) '.mat']);

    imagesc(depth_array);

    imgmed(:,:,i)=double(depth_array)/1000;

    pause(.1)

    drawnow;

end

bg=median(imgmed,3);

d=dir('depth1*.mat');

for i=1:length(d),

    load(d(i).name);

    imagesc(abs(double(depth_array)/1000-bg)>.25);

    colormap(gray);

    pause(1);

end

III - Image Processing

22 outubro 2018, 15:30 • José Santos-Victor

Gabor filters. Non-linear filters. Median filter. Background estimation (temporal filtering).
Diffusion processes and edge preservation. The heat equation and linear diffusion.
Scale space. Gaussian scale space. Non-linear diffusion and the Perona-Malik filter

III - Image Processing

19 outubro 2018, 15:30 • José Santos-Victor

Filtering and noise reduction, linear filters, separable filters. Gaussian kernel, the notion of scale.
Image derivatives, the gradient operator and noise. Laplacian operator.