Calculating frame rate per second for object detection

Hi Guys

Kindly i want to know how to calculate framerate per second for object detection using R-CNN in the following code:-

close all
clear
clc
load('Detector.mat');
vidReader = VideoReader('vs_014_00.avi');
vidPlayer = vision.DeployableVideoPlayer;
i = 1;
results = struct('Boxes',[],'Scores',[]);
while(hasFrame(vidReader))    
    % GET DATA
    I = readFrame(vidReader);    
    
    % PROCESS
    [bboxes, scores] = detect(detector,I,'Threshold',1);
    
     % Select strongest detection 
    [~,idx] = max(scores);
    results(i).Boxes = bboxes;
    results(i).Scores = scores;
        
    
    % VISUALIZE
    annotation = sprintf('%s , (Confidence = %f)',detector.ModelName,scores(idx));

   I = insertObjectAnnotation(I,'rectangle',bboxes(idx,:),annotation);
    step(vidPlayer,I);
    i = i+1;   
end
results = struct2table(results);
release(vidPlayer);

Answer 1

[Wanbin Song]

You can add some of code as belows:

Declare some variables before while loop as below:

fps = 0;
avgfps = [];

Include below tic/toc commands and fps inside the loop.

tic;
[bboxes, scores] = detect(detector,I,'Threshold',1);
newt = toc;
% fps
fps = .9*fps + .1*(1/newt);
avgfps = [avgfps, fps];

Include below for fps visualization.

I  = insertText(I , [1, 1],  sprintf('FPS %2.2f', fps), 'FontSize', 26, 'BoxColor', 'y');