OpenCV Python program for Vehicle detection in a Video frame

Face Detection Basics

The objective of the program given is to detect object of interest(Car) in video frames and to keep tracking the same object. This is an example of how to detect vehicles in Python.

Why Vehicle Detection?

The startling losses both in human lives and finance caused by vehicle accidents.
Detecting vehicles in images acquired from a moving platform is a challenging problem.

Steps to download the requirements below:

Download Python 2.7.x version, numpy and OpenCV 2.4.x version.Check if your Windows either 32 bit or 64 bit is compatible and install accordingly.
```
sudo apt-get install python
pip install numpy
```

install OpenCV from here
Make sure that numpy is running in your python then try to install opencv.
Put the cars.xml file in the same folder. Save this as .xml file.
Download this video from here as input

# OpenCV Python program to detect cars in video frame 
# import libraries of python OpenCV  
import cv2 
  
# capture frames from a video 
cap = cv2.VideoCapture('video.avi') 
  
# Trained XML classifiers describes some features of some object we want to detect 
car_cascade = cv2.CascadeClassifier('cars.xml') 
  
# loop runs if capturing has been initialized. 
while True: 
    # reads frames from a video 
    ret, frames = cap.read() 
      
    # convert to gray scale of each frames 
    gray = cv2.cvtColor(frames, cv2.COLOR_BGR2GRAY) 
      
  
    # Detects cars of different sizes in the input image 
    cars = car_cascade.detectMultiScale(gray, 1.1, 1) 
      
    # To draw a rectangle in each cars 
    for (x,y,w,h) in cars: 
        cv2.rectangle(frames,(x,y),(x+w,y+h),(0,0,255),2) 
  
   # Display frames in a window  
   cv2.imshow('video2', frames) 
      
    # Wait for Esc key to stop 
    if cv2.waitKey(33) == 27: 
        break
  
# De-allocate any associated memory usage 
cv2.destroyAllWindows() 

References:

This article is contributed by Afzal Ansari. If you like GeeksforGeeks and would like to contribute, you can also write an article using contribute.geeksforgeeks.org or mail your article to contribute@geeksforgeeks.org. See your article appearing on the GeeksforGeeks main page and help other Geeks.

Please write comments if you find anything incorrect, or you want to share more information about the topic discussed above.

My Personal Notes

Suggest a Topic

Recommended Posts: