Distance Estimation Using Single Camera OpenCV Python

Distance Estimation in computer vision is quite complicated, because you have to buy some extra hardware, like stereo camera, or depth sensor, to accomplish the task, here we are going to implement simple and effective solution, by using webcam, or smartphone camera.

Codebase

Here I am going to explain important code snippets, the complete codebase is available on my github repository, complete Tutorial available on Youtube as well.

Requirement

1. Python
2. OpenCV
3. Measurement tap

Requirements

Setup Environment for face detection:

You need Python 3.x Version, Opencv-python, and you need a haar cascade file for face detection,

Distance Estimation

• Capture Reference Image:
• Measure the distance from the object(face) to the camera, capture Reference image, and the measured distance, note it down
• Measure the object (face) width, make sure that measurement units are kept for reference image and object(face) width. mine Reference Image

In case you don't want to set up anything here then, just go with my repository,

git clone https://github.com/Asadullah-Dal17/Distance_measurement_using_single_camera

Let's talk about three important functions or modules.

Face Detector

This function will detect the face and return the face width in the pixels values. This face data function simply takes one argument, which image, returns the face width in the pixels, which is a requirement for the focal length finder and distance finder function.

def face_data(image):

    face_width = 0  # making face width to zero

    # coverting color image ot gray scale image
    gray_image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

    # detectiong face in the image
    faces = face_detector.detectMultiScale(gray_image, 1.3, 5)

    # looping through the faces detect in the image getting cooordinates x, y , width and height
    for (x, y, h, w) in faces:

        # draw the rectangle on the face
        cv2.rectangle(image, (x, y), (x+w, y+h), GREEN, 2)

        # getting face width in the pixels
        face_width = w

    # return the face width in pixel
    return face_width

Focal Length Finder

The Focal Length finder Function Tacks Three Arguments:

1. Measured_distance is the distance from the camera to object while capturing the Reference image, Known_distance = 72.2 #centimeter
2. Real_width Its measure the width of an object in real-world, here I measure the width of the face which is around Known_width =14.3 #centimeter
3. Width_in_rf_image is the width of the object in the image/frame it will be in pixels

This function will return the focal length, which is used to find the distance.

# focal length finder function

def FocalLength(measured_distance, real_width, width_in_rf_image):

    focal_length = (width_in_rf_image* measured_distance)/ real_width

    return focal_length

Distance Finder

This Function Tasks Three Argument,

1. Focal length in pixel, which is a return from the Focal length finder function
2. Real_width Its measure the width of an object in real-world, here I measure the width of the face which is around Known_width =14.3 #centimeter
3. Width_in_rf_image is the width of the object in the image/frame it will be in pixels

The distance finder function will return the distance in the centimeters

# distance estimation function

def Distance_finder(Focal_Length, real_face_width, face_width_in_frame):

    distance = (real_face_width * Focal_Length)/face_width_in_frame

    return distance

In case you have any question, please leave that down blow, another option would be, Github discussion tab, it's open for anyone,

I have no writing experience at all, I would love to get your suggestions, here as well,

thank you so much, Stay Safe....