• For any query, contact us at
  • +91-9872993883
  • +91-8283824812
  • info@ris-ai.com

Human Detection And Counting With Python

Project Objective: In this python project, we are going to build the Human Detection and Counting System through images provided. This is an intermediate level deep learning project on computer vision, which will help you to master the concepts and make you an expert in the field of Data Science.

Importing the libraries

The project in Python requires you to have basic knowledge of python programming and the OpenCV library. We will be needing following libraries: OpenCV: A strong library used for machine learning, Imutils: To Image Processing, Numpy: Used for Scientific, Computing. Image is stored in a numpy array and Argparse: Used to give input in command line.

In [ ]:
import cv2
import imutils
import numpy as np
import argparse

Detect() method:

Here, the actual magic will happen. It will take a frame to detect a person in it. Make a box around a person and show the frame..and return the frame with person bounded by a green box.

Everything will be done by detectMultiScale().

It returns 2-tuple. List containing Coordinates of bounding Box of person. Coordinates are in form X, Y, W, H. Where x,y are starting coordinates of box and w, h are width and height of box respectively and Confidence Value that it is a person.

In [ ]:
def detect(frame):
    bounding_box_cordinates, weights =  HOGCV.detectMultiScale(frame, winStride = (4, 4), padding = (8, 8), scale = 1.03)
    
    person = 1
    for x,y,w,h in bounding_box_cordinates:
        cv2.rectangle(frame, (x,y), (x+w,y+h), (0,255,0), 2)
        cv2.putText(frame, 'person: {}'.format(person), (x,y), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0,0,255), 1)
        person += 1
    
    cv2.putText(frame, 'Status : Detecting ', (40,40), cv2.FONT_HERSHEY_DUPLEX, 0.8, (255,0,0), 2)
    cv2.putText(frame, 'Total Persons : {}'.format(person-1), (40,70), cv2.FONT_HERSHEY_DUPLEX, 0.8, (255,0,0), 2)
    cv2.imshow('output', frame)

    return frame

This method is used when user needs to be detected from an image.

In [3]:
def detectByPathImage(path, output_path):
    image = cv2.imread(path)

    image = imutils.resize(image, width = min(800, image.shape[1]))

    result_image = detect(image)

    if output_path is not None:
        cv2.imwrite(output_path, result_image)

    cv2.waitKey(0)
    cv2.destroyAllWindows()

HumanDetector() method

This method is used to detec the human in the image.

In [4]:
def humanDetector(args):
    image_path = args["image"]
    video_path = args['video']
    if str(args["camera"]) == 'true' : camera = True
    else : camera = False

    writer = None
    if args['output'] is not None and image_path is None:
        writer = cv2.VideoWriter(args['output'],cv2.VideoWriter_fourcc(*'MJPG'), 10, (600,600))

    if camera:
        print('[INFO] Opening Web Cam.')
        detectByCamera(ouput_path,writer)
    elif video_path is not None:
        print('[INFO] Opening Video from path.')
        detectByPathVideo(video_path, writer)
    elif image_path is not None:
        print('[INFO] Opening Image from path.')
        detectByPathImage(image_path, args['output'])

Argparse() method

The function argparse() simply parses and returns as a dictionary the arguments passed through your terminal to our script. Here it will take one argument for image.

In [5]:
def argsParser():
    arg_parse = argparse.ArgumentParser()
    arg_parse.add_argument("-i", "--image", default=None, help="/home/webtunix/my_project_dir/human_detect/two_human.jpeg ")
    args = vars(arg_parse.parse_args())
    return args

Main function

We have reached the end of our project. Here we will give the path of the image with in detectByPathImage() function as its argument and the second argument as the image which will detect and count number of humans in the image.

In [ ]:
if __name__ == "__main__":
    HOGCV = cv2.HOGDescriptor()
    HOGCV.setSVMDetector(cv2.HOGDescriptor_getDefaultPeopleDetector())
    
    detectByPathImage("/home/webtunix/my_project_dir/human_detect/two_human.jpeg","count.jpeg")

Here is the picture of input image and output of the image counting and detecting number of humans.

INPUT:
Human Detection and Counting in Python Human Detection and Counting in Python
OUTPUT
Human Detection and Counting in Python Human Detection and Counting in Python
Conclusion:

In this deep learning project, we have learned how to create a people counter using HOG and OpenCV to generate an efficient people counter. We developed the project where you can supply the input as image. This is an intermediate level project, which will surely help you in mastering python and deep learning libraries.