Head and people detection in opencv

LBP cascade free to download to use in opencv to detect people and heads. Code example and cascade description. All you need to write your own people head detector from the youtube video.
Cascade is trained on my own people and head datasets. There are no perfect but in some cases are better then default opencv cascades. They are just different.. For example, you can count that the head detector have much more false detection than the people detector.. The shape and feature space is much more common and close to others shapes than the whole people detector.

detect peole head opencv haar cascade

Issues with opencv detectMultiScale head and people detector

Please let me know if the cascades worked as expected.. In code example there is ground threshold settings and reccomentation. 




LBP cascade head detection properties

Sure you can find it inside the file.

<!--
This is just basic 16 stage lbp cascade head detector develop by 
V.K. from https://funvision.blogspot.com
-->
<?xml version="1.0"?>
<opencv_storage>
<cascade>
  <stageType>BOOST</stageType>
  <featureType>LBP</featureType>
  <height>38</height>
  <width>38</width>
  <stageParams>
    <boostType>GAB</boostType>
    <minHitRate>9.9999994039535522e-01</minHitRate>
    <maxFalseAlarm>6.0000002384185791e-01</maxFalseAlarm>
    <weightTrimRate>9.4999999999999996e-01</weightTrimRate>
    <maxDepth>25</maxDepth>
    <maxWeakCount>60</maxWeakCount></stageParams>
  <featureParams>
    <maxCatCount>256</maxCatCount>
    <featSize>1</featSize></featureParams>
  <stageNum>16</stageNum>
  <stages>


New LBP cascade people detection properties

<!--
This is just a basic 10-stage LBP cascade head detector developed by 
V.K. from https://funvision.blogspot.com
-->
<?xml version="1.0"?>
<opencv_storage>
<cascade>
  <stageType>BOOST</stageType>
  <featureType>LBP</featureType>
  <height>64</height>
  <width>32</width>
  <stageParams>
    <boostType>GAB</boostType>
    <minHitRate>9.9999499320983887e-01</minHitRate>
    <maxFalseAlarm>3.0000001192092896e-01</maxFalseAlarm>
    <weightTrimRate>9.4999999999999996e-01</weightTrimRate>
    <maxDepth>20</maxDepth>
    <maxWeakCount>80</maxWeakCount></stageParams>
  <featureParams>
    <maxCatCount>256</maxCatCount>
    <featSize>1</featSize></featureParams>
  <stageNum>10</stageNum>
  <stages>


Opencv cascade for car detection conditions of use


Also, Do not worry about the condition of use. Use only at your own risk. That's it. The dataset to train this cascade is only mine. I also collect positive and negative data. I just want to say, that there is also no conditions based on the datasets. There is no other conditions of use. Maybe check the Opencv train cascade utility. Thanks. Yes, share and cite. Just small minimal conditions like send me a million dollars. It's up to you.

Head cascade and people cascade download link.


Head detection download link

People detection download link


Head and people detection tutorial code


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

This code is based on my previous tutorial Fast people detection.
Inside the video capture loop just modify the part like this. Include cascade inside your project and play with different settings.. This is not an ideal one.


// Name of the downloaded my cascades.. 
 string cascadeHead = "cascadeH5.xml";
 string cascadeName = "cascadG.xml";
// Load the cascade
 CascadeClassifier detectorBody;
 bool loaded1 = detectorBody.load(cascadeName);
 CascadeClassifier detectorHead;
 bool loaded2 = detectorHead.load(cascadeHead);
        
// save original make img gray
// draw rectangle back to the original colored sample
 Mat original;
 img.copyTo(original);
// Prepare vector for results 
vector<Rect> human;
vector<Rect> head;
// Prepare gray image
 cvtColor(img, img, CV_BGR2GRAY);
// equalize Histogram  
        equalizeHist(img, img);
// detect body and head in the img 
// Set the proper min and max size for your case
 detectorBody.detectMultiScale(img, human, 1.0440 | 1Size(3080), Size(80,200));
 detectorHead.detectMultiScale(img, head, 1.140 | 1Size(4040), Size(100100));
 if (human.size() > 0) {
  for (int gg = 0; gg < human.size(); gg++) {
   rectangle(original, human[gg].tl(), human[gg].br(), Scalar(00255), 280);
     }
  }
 if (head.size() > 0) {
  for (int gg = 0; gg < head.size(); gg++) {
   rectangle(original, head[gg].tl(), head[gg].br(), Scalar(00255), 280);
     }
 }
Next Post Previous Post
13 Comments
  • Unknown
    Unknown February 27, 2017 at 1:02 PM

    I want code for Real time Face Recognition System using LBP Algorithm code for opencv 3.1 (C++) in Linux.
    Contact Details:-

    Email:- perrykakkar.1993@gmail.com
    Ph. No:- +91-8930228000

    • Vl
      Vl March 2, 2017 at 10:30 AM

      Code is same cascade is different.. There is lots of cascade detect faces. I do not spent time to doing training of that detector..

  • Unknown
    Unknown May 17, 2017 at 12:28 AM

    what a nice blog it is!
    Can i share the video file??
    yunjung.erica@gmail.com

  • Unknown
    Unknown June 2, 2017 at 7:51 AM

    Hi. I'm using the head cascade in my project.
    And my question is if the parameters are the same with the face cascade. All this implemented from python. Also, what would be the correct syntax to call the cascade.
    Thanks for your help.

    • Unknown
      Unknown March 7, 2019 at 7:41 PM

      Mam can you please provide me the head cascade, i urgently needed, please.Thanks in advance.

  • Unknown
    Unknown August 13, 2017 at 10:22 PM

    شرکت هوشمند افزار آسیا یکی از قدرتمند ترین شرکت های حوزه سیستم های امنیتی و نظارت تصویری و دوربین های مداربسته
    نماینده فروش دوربین های مداربسته هایک ویژن در کرج و تهران

    نصب دوربین مداربسته
    نماینده فروش دوربین های مداربسته هایک ویژن در کرج و تهران
    نماینده فروش دوربین های مداربسته هایک ویژن در کرج و تهران

    مجله تخصصی دوربین مداربسته و سیستم های حفاظتی و امنیتی
    02634216001-02634216002

  • Unknown
    Unknown December 25, 2017 at 12:26 AM

    Thanks.
    holiday palace
    ทางเข้า sbobet

  • Anonymous
    Anonymous January 7, 2018 at 12:05 AM

    Thank you for sharing your knowledge.

    maxbet

    แทงบอล maxbet

    แทงบอล maxbet

  • Linktekc Systems Group
    Linktekc Systems Group March 3, 2018 at 9:18 AM

    Enthusiastic words written in this blog helped me to enhance my skills as well as helped me to know how I can help myself on my own. I am really glad to come at this platform. freelance website development

  • Unknown
    Unknown August 1, 2018 at 6:02 AM

    Do you have implementation in Python? of the same LBP cascade?

  • Anonymous
    Anonymous August 8, 2018 at 4:53 AM

    I need some suggestions on training data more precisely. can you guide me to train my own cascade in a efficient way.
    It would be really helpful for me.

  • basha
    basha March 23, 2019 at 4:48 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

  • PoL
    PoL July 9, 2019 at 2:29 PM

    You have a question Where to Find Software Developers? Youteam is a massive professional networking platform with over 590 million registered members, and over 250 million active users in over 200 countries. As you can imagine, it’s become quite the recruiting platform for employers looking for connected professionals.

Add Comment
comment url