People Counting in real time using OpenCV



The people counting detection is used to detect the object by using a deep neural network. by using this process we can get more accuracy. before that, we used the k means algorithm. but we can get only less accuracy. So, we can move to the neural gives better accuracy. for the identification we are taking blob detection. Basically, used in commercial applications, face identification, object tracking, image retrieval, and automated parking system. In this project, we will dive deeper and look at various algorithms that can be used for object detection

People Counting in real time using OpenCV


The article recognition is applied to the objects of the person. not just a person we can distinguish any kind of picture. this procedure will be applied to recognize the article for the utilization of the wide scope of businesses, picture recovery and so on calculation applies a neural system to a whole picture. The system isolates the picture into a S x S framework and concocts bounding boxes, which are boxes drawn around pictures and anticipated probabilities for each of these areas. The technique used to concoct these probabilities is calculated relapse. The bounding boxes are weighted by the related probabilities. For class expectations, free strategic classifiers are utilized. Right now, will exhibit how to actualize the YOLO calculation with a pre-prepared model. To begin with, we would need to introduce DarkNet. It is a neural system structure that is open source. what’s more, by utilizing mass location we can distinguish the picture by the square shape box. Utilizing this procedure we can distinguish questions with no problem at all. 


  • Edge recognition
  • Morphological Filter 
  • SVM order


  • Not a real-time application
  • Information about objects is very less


  • Pre-preparing
  • Darknet
  • Deep Learning Classification:

Block diagram 

People Counting in real time using OpenCV
People Counting in real-time using OpenCV

Software :

  1. Packages 
  2. Python idle 
  3. Opencv


In this project, we detect object detection based on blob detection and darknet.  This can be used in real-time applications which require object detection for pre-processing in their pipeline. An important scope would be to train the system on a video sequence for usage in tracking applications. The addition of a temporally consistent network would enable smooth detection and be more optimal than per-frame detection.

People Counting in real time using OpenCV


The performance of the object detection requirement in image processing for a more number of real-time applications. by using this application we can detect any type of object. This is the best performance. For future purposes, we can take different types of extraction process techniques. this technique is used at shopping malls, roads, theatres, airports, companies, parks, etc…optical flow is used for the next generation. And here we can develop new algorithms for the classification process. by using this we can detect a more number of objects by assigning different colors and names. These are used at malls, restaurants, and other applications.

Customer Reviews

There are no reviews yet.

Be the first to review “People Counting in real time using OpenCV”

This site uses Akismet to reduce spam. Learn how your comment data is processed.