harshinir4/human-detection-using-opencv

Detect and count the number of humans in pictures of crowded places using OpenCV

Human-Detection-Using-OpenCV

The purpose of this project is to build a Human detection model using OpenCV. For that purpose we are going to first detect humans in the image, then create a function that returns the count of humnas in the picture

Dataset

Human Detection Dataset from Kaggle

Assumptions: As the model utilises the HOG model of OpenCV the data to be used must only be restricted to full-body clear colour images of humans in the location.

Modules

• cv2
• imutills

Steps

• Import necessary modules
• Read image needed using the cv2 module
• Load the pre-trained HOG and Linear SVM Model
• Load the People Detector function in the HOG model of OpenCV
• Resize the image according to the requirements- taken 500 as standard
• With the detectMultiScale() function identify the boxes i.e., humans in the picture and their weights -Apply the contours for the humans detected and display the final output
• Developed a function that takes in the image path and returns the number of humans identified in the picture with the image displayed.

Output

Harshini Raju