MATLAB: The ‘bboxes’ and ‘scores’ variables are all empty while certainly the image contains a person

bboxescomputer visionComputer Vision Toolboxface detectionhuman detectionimage processingpeopledetectorstep

Hi,

This is my example image clearly with a person in it.

I would like to use Matlab's 'people detector' to detect the person in the image.

So I tried:

peopleDetector = vision.PeopleDetector;
I = imread('executive1.jpg');
[bboxes,scores] = step(peopleDetector,I);

I was hoping 'bboxes' could give me the position so that I could draw a box around the human in the image. However, 'bboxes' and 'scores' are all empty which I don't understand.

I'm a beginner to human detection. Please help.

Best Answer

Have you tried changing the peopledetector properties? For example, you get a result just changing the model:

peopleDetector = vision.PeopleDetector('ClassificationModel','UprightPeople_96x48');
I = imread('executive1.jpeg');
[bboxes,scores] = step(peopleDetector,I);
bboxes =
   103    66    73   125

Related Solutions

MATLAB: Select largest bounding box

Hello nataliya,

Find the area of all the bounding box. Take out the bounding box having maximum area.

MATLAB: Standing People Detector in Matlab, want to filter out scores below 0.03

Try this:

clc;    % Clear the command window.
clearvars;
close all;  % Close all figures (except those of imtool.)
workspace;  % Make sure the workspace panel is showing.
format long g;
format compact;
fontSize = 20;
peopleDetector = vision.PeopleDetector;
rgbImage = imread('visionteam1.jpg');
% Find people.
[boundingBoxes,scores] = peopleDetector(rgbImage)
% Burn boxes into a new image.
rgbImage2 = insertObjectAnnotation(rgbImage,'rectangle',boundingBoxes,scores);
% Display image with boxes burned into it.

subplot(1, 2, 1);
imshow(rgbImage2);
title('All Detected Boxes with All Scores', 'FontSize', fontSize);
% Extract only those boxes with scores > 0.03
rowsToExtract = scores > 0.03
goodBoxes = boundingBoxes(rowsToExtract, :)
scores = scores(rowsToExtract)
% Burn only "good" boxes into a new image.
rgbImage3 = insertObjectAnnotation(rgbImage,'rectangle',goodBoxes,scores);
% Display image with boxes burned into it.
subplot(1, 2, 2);
imshow(rgbImage3);
title('People with Detection Scores > 0.3', 'FontSize', fontSize);
% Enlarge figure to full screen.
set(gcf, 'Units', 'Normalized', 'OuterPosition', [0, 0.04, 1, 0.96]);
uiwait(msgbox('Done!'))

Note how there are only 3 (instead of 4) detected people on the right image.

Best Answer

Related Solutions

MATLAB: Select largest bounding box

MATLAB: Standing People Detector in Matlab, want to filter out scores below 0.03

Related Question