A loop that can repetitively extract features?

1 view (last 30 days)
Hi guys,
i would like to seek help! i'm trying to do a extract HOG feature from a list of UCF sport videos and save the size of hoefeature into a folder. how can i do it?
clc; clear; close;
% video data
vidObj=VideoReader('Kicking-Side-004.avi');
video=read(vidObj);
img=zeros(size(video,1),size(video,2),size(video,4));
for j=1:size(video,4)
img(:,:,j)=im2single(rgb2gray(video(:,:,:,j)));
end
% spatio temporal orientation filter
SOE = SpatialTemporalEnergy(img,'G3',3,0);
% seperate motion energy from static and unstructure energy
structure=max(SOE(:))/100;
SOE=max(bsxfun(@minus,SOE(:,:,:,1:end-1),SOE(:,:,:,end)+structure),0);
% normalization
SOE=bsxfun(@rdivide,SOE,sum(SOE,4)+eps);
% dense HOE
hoefeature=HOE(SOE,4,4,4);
% dense HOG
[gradient_x,gradient_y] = gradient(img);
hogfeature = HOG(gradient_x,gradient_y,4,4,4,8);

Answers (0)

Categories

Find more on Images in Help Center and File Exchange

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!