Fast Opencv people pedestrian detection Tutorial by CascadeClassifier

Simple Opencv C++ tutorial and example of people detection in video samples and pictures. There is nothing you cannot achieve in a few simple steps. People detection and performance tasks in opencv could be solved if you have a little bit of knowledge of programming. Or just simply follow the steps. 

Opencv tutorial installation of OpenCV

You can simply prepare the project inside the Visual Studio 2015 by Nuget Packages. This approach is easy for beginners and better than standard installation with all the environmental variables problems. Just follow the installation steps here 

Cascade Classifier detect Multi Scale


Opencv is a great and complex tool. There are a lot of image processing and also machine learning features. You can simply learn your own detector. I would like to prepare some tutorials on how to learn your own detector. It is a long time run. 

All, you need to do, is have some experience and basic opencv tools. 
under opencv/build/x64/vc14/bin

opencv_createsamples.exe
opencv_traincascade.exe

Prepare your dataset and files with labels that are better under Linux. You can use simple shell scripts. 
This is really for long tutorial, but you can do image annotation in Windows as well and maybe use the new tool opencv_annotation,exe, but i don't have any experience with this. My own scripts and programs crop, save and annotate data. I have my own image cropper to prepare datasets. You can build your own dataset in a few days. It is tricky too.

First step
Use basic opencv cascades to crop some positive samples from the video or better crop precisely the positive samples from your images. Negative samples are not a problem. Generate them randomly from your images.  Clean and prepare data manually. This is the worst part. Crop also images selected correctly by default opencv cascade to achieve better results.

Second step
Build your initial detector, which is used for other positive data collecting.  Again Clean and prepare data manually. Stupid boring and it takes a long time.


Third
!!Use this at your own risk. !!
Run the cloud machine on aws and install OpenCV 3.1. 
Better is memory than a number of cores. Something like 

r3.4xlarge   cores 16  memory 52                              $1.33 per Hour
 !!!!On your own risk!!!!
8000 positive and 15000 negative datasets with 10- 20 stages could take minutes - hours instead of days of learning on your own computer. And it's cheaper than the electricity bill. Time to learn depends on a number of data, parameters, selected machines, and many other things.I can not guarantee that it goes so fast with your data and parameters. I do it this way save time. I am pretty sure that your first detector will be terrible. In the cloud, you can learn 10 detectors a day. Which is great

Performance detectMultiScale and parameters

  • The source image is 640x480 image. My PC is a notebook I7, 4 cores, 8 threads, and a huge amount of RAM :). Opencv version is 3.1 default for Windows machines. 
  • I have 2 people detectors detectMultiScale in the main loop. 
  • The main performance issue is in the scaleFactor parameter and minSize of the object. In the faster case, I have 1.1, and in the slower case is 1.02 scaleFactor.  
  • Choose appropriately as needed the minSize parameter. If you have to small a window, your program needs to check far more options. Size(40,70)

CascadeClassifier at approximately 13 FPS

detectorBody.detectMultiScale(img, human, 1.1, 1, 0 | 1, Size(40,70), Size(80, 300));
detectorUpper.detectMultiScale(img, upperBody, 1.1, 1, 0 | 1, Size(40, 70), Size(80, 300));


Cascade Classifier detect Multi Scale


CascadeClassifier at approximately 2 FPS

detectorBody.detectMultiScale(img, human, 1.02, 2, 0 | 1, Size(40,70), Size(80, 300));
detectorUpper.detectMultiScale(img, upperBody, 1.02, 2, 0 | 1, Size(40, 70), Size(80, 300));

Cascade Classifier detect Multi Scale


Opencv  HAAR LBP cascade download

I also learned some mine cascade on my own datasets. They are here. To be sure that you can reach them here are the links.

Cascade for car detector download

This is just a basic 5 stage haar cascade car detector, post where to find my cascade to detect cars

Cascade for head and people download 

This cascade is also able to use by the tutorial code below. For head and for people detection. 
Learned by me on my own data set. cascade for head and people detection

Opencv CascadeClassifier tutorial code

!!Simple as OpenCV Sample. Let me add some useful remarks. Some Windows OpenCV versions detect multiScale return errors.. 2.9.4 -3.0 maybe 3.1. I don't know why. The classifier returns to many output rectangles out of bound. This does not make sense and kills your program.
If this is an issue of your error on Windows. Switch from debug to release. It helps. !! Really


#include "opencv2\highgui.hpp"
#include "opencv2\imgproc.hpp"
#include "opencv2\objdetect\objdetect.hpp"
#include "opencv2/video/tracking.hpp"
#include <vector>
#include <stdio.h>
#include <Windows.h>
#include <iostream>
#include <time.h>
#include <ctime>

    using namespace cv;
    using namespace std;

    int main(int argc, const char **argv)
    {
        // prepare video input
        VideoCapture cap("input.mov");
        // prepare video output
        VideoWriter outputVideo;
        outputVideo.open("video4.wmv"CV_FOURCC('W''M''V''2'), cap.get(CV_CAP_PROP_FPS), Size(640480), true);
        // prepare cascadeClassifier
        CascadeClassifier detectorBody;
        CascadeClassifier detectorUpper;
        // !! Put your cascade or opencv cascede into project folder !!
        string cascadeName1 = "cascadeName.xml";
        string cascadeName2 = "cascadeName.xml";
        // Load cascade into CascadeClassifier
        bool loaded1 = detectorBody.load(cascadeName1);
        bool loaded3 = detectorUpper.load(cascadeName2);
        // Basic video input loop
        for (;;)
        {
            bool Is = cap.grab();
            if (Is == false)
            {
                cout << "Video Capture Fail" << endl;
                break;
            }
            else
            {
                // Just for measure time
                const clock_t begin_time = clock();
                // Store results in these 2 vectors
                vector<Rect> human;
                vector<Rect> upperBody;
                // prepare 2 Mat container
                Mat img;
                Mat original;
                // capture frame from video file
                cap.retrieve(img, CV_CAP_OPENNI_BGR_IMAGE);
                // Resize image if you want with same size as your VideoWriter
                resize(img, img, Size(640480));
                // Store original colored image
                img.copyTo(original);
                // color to gray image
                cvtColor(img, img, CV_BGR2GRAY);
                // detect people, more remarks in performace section
                detectorBody.detectMultiScale(img, human, 1.120 | 1Size(4070), Size(80300));
                detectorUpper.detectMultiScale(img, upperBody, 1.120 | 1Size(4070), Size(80300));
                // Draw results from detectorBody into original colored image
                if (human.size() > 0)
                {
                    for (int gg = 0; gg < human.size(); gg++)
                    {
                        rectangle(original, human[gg].tl(), human[gg].br(), Scalar(00255), 280);
                    }
                }
                // Draw results from detectorUpper into original colored image
                if (upperBody.size() > 0)
                {
                    for (int gg = 0; gg < upperBody.size(); gg++)
                    {
                        rectangle(original, upperBody[gg].tl(), upperBody[gg].br(), Scalar(25500), 280);
                    }
                }
                // measure time as current - begin_time
                clock_t diff = clock() - begin_time;
                // convert time into string
                char buffer[126];
                sprintf(buffer, "%d", diff);
                // display TIME ms on original image
                putText(original, buffer, Point(10020), 12Scalar(255255255), 280);
                putText(original, "ms"Point(15020), 12Scalar(255255255), 280);
                // draw results
                namedWindow("prew", WINDOW_AUTOSIZE);
                imshow("prew", original);
                // make video output

                outputVideo << original;
                int key1 = waitKey(20);
            }
        }
    }


Next Post Previous Post
20 Comments
  • Unknown
    Unknown July 21, 2016 at 4:39 AM

    I will try this code on my own. Hope it will help me.

    Splendid Skyline Review

  • Gabriel
    Gabriel August 6, 2016 at 11:06 AM

    Awesome! Thanks for sharing code!!

    • Unknown
      Unknown May 17, 2019 at 12:40 AM

      where is the complete code? I haven't seen .hpp files

  • Unknown
    Unknown August 5, 2017 at 7:50 PM

    Hi. I am referening this tutorial. Could you give me this code? I want to reference it. Thanks a lot. My email: tiennt@mta.edu.vn

  • Unknown
    Unknown September 29, 2017 at 4:49 AM

    This comment has been removed by the author.

  • Unknown
    Unknown September 29, 2017 at 4:50 AM

    Hi! What an interesting blog!!
    I'm working on a ROS module for person detection and I was wondering if you could give me the CascadeClassifier(body detector) you used because I couldn't find the link in this tutorial.
    Thanks for your help!
    My email: marisofia.iglesias@gmail.com

  • Unknown
    Unknown October 19, 2017 at 8:52 AM

    Hi,
    Very good example and useful for some use cases. It is possible to send the code? My email: madeirajp@gmail.com
    Thanks and good work

  • cannava
    cannava November 30, 2017 at 7:41 PM

    ^
    ^
    nice nice

    sbobet
    maxbet
    แทงบอลออนไลน์

  • Mozmee007
    Mozmee007 December 24, 2017 at 11:28 PM

    Good articles, well presented and informative articles.


    แทงบอล sbobet
    sbobet mobile
    รับแทงบอล

  • Toni444
    Toni444 January 23, 2018 at 9:54 PM

    Wow, use, I have to admit that what I see. There is a very interesting story.


    แทงบอล maxbet

    แทงบอล maxbet

    ทางเข้า maxbet

  • rocklaam
    rocklaam April 1, 2018 at 8:07 PM

    This comment has been removed by the author.

  • rocklaam
    rocklaam April 2, 2018 at 2:27 AM

    Hi ad! In step 1, you mean using default .xml file of openCV to crop and get location for positive images, right ? And this solution is work for detecting human in different position like 'sitting'? thank you very much!!

  • Unknown
    Unknown April 16, 2018 at 11:50 PM

    This comment has been removed by the author.

    • Unknown
      Unknown April 16, 2018 at 11:53 PM

      Thanks for your help.
      could you give me this code? i'm student, i want to reference it.
      My email: "gpham378@gmail.com"

  • Unknown
    Unknown April 16, 2018 at 11:54 PM

    Thanks for your help.
    could you give me this code? i'm student, i want to reference it.
    My email: "gpham378@gmail.com"

  • Unknown
    Unknown September 24, 2018 at 8:33 PM

    This comment has been removed by the author.

  • Unknown
    Unknown September 24, 2018 at 8:35 PM

    Thanks a lot for such a nice tutorial....can i get this code of people tracking...i'm a student..my id aratimcs@gmail.com....Thanks

  • basha
    basha March 23, 2019 at 4:47 AM

    Excellent blog I visit this blog it's really awesome. The important thing is that in this blog content written clearly and understandable. The content of information is very informative.
    Oracle Fusion HCM Online Training
    Oracle Fusion SCM Online Training
    Oracle Fusion Financials Online Training
    Big Data and Hadoop Training In Hyderabad
    oracle fusion financials classroom training
    Workday HCM Online Training
    Oracle Fusion HCM Classroom Training
    Workday HCM Online Training

  • Unknown
    Unknown May 17, 2019 at 12:42 AM

    can you send me complete code?
    rimsha479@gmail.com

  • wepeachstuff
    wepeachstuff October 29, 2019 at 8:38 PM

    Excellent blog

    UFABET

Add Comment
comment url