How to Do Multiple Object Tracking Using OpenCV

In this tutorial, we will learn how to track multiple objects in a video using OpenCV, the computer vision library for Python. By the end of this tutorial, you will be able to generate the following output:

Real-World Applications

Object tracking has a number of real-world use cases. Here are a few:

Drone Surveillance
Aerial Cinematography
Tracking Customers to Understand In-Store Consumer Behavior
Any Kind of Robot That You Want to Follow You as You Move Around

Let’s get started!

Prerequisites

Python 3.7 or higher

Installation and Setup

We first need to make sure we have all the software packages installed. Check to see if you have OpenCV installed on your machine. If you are using Anaconda, you can type:

conda install -c conda-forge opencv

Alternatively, you can type:

pip install opencv-python

Find Video Files

Find a video file that contains objects you would like to detect. I suggest finding a file that is 1920 x 1080 pixels in dimensions and is in mp4 format. You can find some good videos at sites like Pixabay.com and Pexels.com.

Save the video file in a folder somewhere on your computer.

Write the Code

Navigate to the directory where you saved your video, and open a new Python program named multi_object_tracking.py.

Here is the full code for the program. You can copy and paste this code directly into your program. The only line you will need to change is line 10. The video file I’m using is named fish.mp4, so I will write ‘fish’ as the file prefix.

If your video is not 1920 x 1080 dimensions, you will need to modify line 12 accordingly.

# Project: How to Do Multiple Object Tracking Using OpenCV
# Author: Addison Sears-Collins
# Date created: March 2, 2021
# Description: Tracking multiple objects in a video using OpenCV

import cv2 # Computer vision library
from random import randint # Handles the creation of random integers

# Make sure the video file is in the same directory as your code
file_prefix = 'fish'
filename = file_prefix + '.mp4'
file_size = (1920,1080) # Assumes 1920x1080 mp4

# We want to save the output to a video file
output_filename = file_prefix + '_object_tracking.mp4'
output_frames_per_second = 20.0 

# OpenCV has a bunch of object tracking algorithms. We list them here.
type_of_trackers = ['BOOSTING', 'MIL', 'KCF','TLD', 'MEDIANFLOW', 'GOTURN', 
                     'MOSSE', 'CSRT']

# CSRT is accurate but slow. You can try others and see what results you get.			 
desired_tracker = 'CSRT'

# Generate a MultiTracker object	
multi_tracker = cv2.MultiTracker_create()

# Set bounding box drawing parameters
from_center = False # Draw bounding box from upper left
show_cross_hair = False # Don't show the cross hair
										 
def generate_tracker(type_of_tracker):
  """
  Create object tracker.
	
  :param type_of_tracker string: OpenCV tracking algorithm 
  """
  if type_of_tracker == type_of_trackers[0]:
    tracker = cv2.TrackerBoosting_create()
  elif type_of_tracker == type_of_trackers[1]:
    tracker = cv2.TrackerMIL_create()
  elif type_of_tracker == type_of_trackers[2]:
    tracker = cv2.TrackerKCF_create()
  elif type_of_tracker == type_of_trackers[3]:
    tracker = cv2.TrackerTLD_create()
  elif type_of_tracker == type_of_trackers[4]:
    tracker = cv2.TrackerMedianFlow_create()
  elif type_of_tracker == type_of_trackers[5]:
    tracker = cv2.TrackerGOTURN_create()
  elif type_of_tracker == type_of_trackers[6]:
    tracker = cv2.TrackerMOSSE_create()
  elif type_of_tracker == type_of_trackers[7]:
    tracker = cv2.TrackerCSRT_create()
  else:
    tracker = None
    print('The name of the tracker is incorrect')
    print('Here are the possible trackers:')
    for track_type in type_of_trackers:
      print(track_type)
  return tracker

def main():

  # Load a video
  cap = cv2.VideoCapture(filename)

  # Create a VideoWriter object so we can save the video output
  fourcc = cv2.VideoWriter_fourcc(*'mp4v')
  result = cv2.VideoWriter(output_filename,  
                           fourcc, 
                           output_frames_per_second, 
                           file_size) 

  # Capture the first video frame
  success, frame = cap.read() 

  bounding_box_list = []
  color_list = []	

  # Do we have a video frame? If true, proceed.
  if success:

    while True:
    
		  # Draw a bounding box over all the objects that you want to track_type
      # Press ENTER or SPACE after you've drawn the bounding box
      bounding_box = cv2.selectROI('Multi-Object Tracker', frame, from_center, 
        show_cross_hair) 

      # Add a bounding box
      bounding_box_list.append(bounding_box)
			
      # Add a random color_list
      blue = 255 # randint(127, 255)
      green = 0 # randint(127, 255)
      red = 255 #randint(127, 255)
      color_list.append((blue, green, red))

      # Press 'q' (make sure you click on the video frame so that it is the
      # active window) to start object tracking. You can press another key
      # if you want to draw another bounding box.			
      print("\nPress q to begin tracking objects or press " + 
        "another key to draw the next bounding box\n")

      # Wait for keypress
      k = cv2.waitKey() & 0xFF

      # Start tracking objects if 'q' is pressed			
      if k == ord('q'):
        break

    cv2.destroyAllWindows()
		
    print("\nTracking objects. Please wait...")
		
    # Set the tracker
    type_of_tracker = desired_tracker	
			
    for bbox in bounding_box_list:
		
      # Add tracker to the multi-object tracker
      multi_tracker.add(generate_tracker(type_of_tracker), frame, bbox)
      
    # Process the video
    while cap.isOpened():
		
      # Capture one frame at a time
      success, frame = cap.read() 
		
      # Do we have a video frame? If true, proceed.
      if success:

        # Update the location of the bounding boxes
        success, bboxes = multi_tracker.update(frame)

        # Draw the bounding boxes on the video frame
        for i, bbox in enumerate(bboxes):
          point_1 = (int(bbox[0]), int(bbox[1]))
          point_2 = (int(bbox[0] + bbox[2]), 
            int(bbox[1] + bbox[3]))
          cv2.rectangle(frame, point_1, point_2, color_list[i], 5)
				
        # Write the frame to the output video file
        result.write(frame)

      # No more video frames left
      else:
        break
		
  # Stop when the video is finished
  cap.release()
	
  # Release the video recording
  result.release()

main()

Run the Code

Launch the program.

python multi_object_tracking.py

The first frame of the video will pop up. With this frame selected, grab your mouse, and draw a rectangle around the object you would like to track.

When you’re done drawing the rectangle, press Enter or Space.

If you just want to track this object, press ‘q’ to run the program’. Otherwise, if you want to track more objects, press any other key to draw some more rectangles around other objects you want to track.

After you press ‘q’, the program will run. Once the program is finished doing its job, you will have a new video file. It will be named something like fish_object_tracking.mp4. This file is your final video output.

Video Output

Here is my final video:

How the Code Works

OpenCV has a number of object trackers: ‘BOOSTING’, ‘MIL’, ‘KCF’,’TLD’, ‘MEDIANFLOW’, ‘GOTURN’, ‘MOSSE’, ‘CSRT’. In our implementation, we used CSRT which is slow but accurate.

When we run the program, the first video frame is captured. We have to identify the object(s) we want to track by drawing a rectangle around it. After we do that, the algorithm tracks the object through each frame of the video.

Once the program has finished processing all video frames, the annotated video is saved to your computer.

That’s it. Keep building!

How to Detect Objects in Video Using MobileNet SSD in OpenCV

In this tutorial, we will go through how to detect objects in a video stream using OpenCV. We will use MobileNet SSD, a special type of convolutional neural network architecture.

Our output will look like this:

Real-World Applications

Object Detection
Object Tracking
Object Classification
Autonomous Vehicles
Self-Driving Cars

Let’s get started!

Prerequisites

Python 3.7 or higher

Installation and Setup

We now need to make sure we have all the software packages installed. Check to see if you have OpenCV installed on your machine. If you are using Anaconda, you can type:

conda install -c conda-forge opencv

Alternatively, you can type:

pip install opencv-python

Download the Required Files

Download all the video files and other neural network-related files at this link. Place the files inside a directory on your computer.

Code

In the same folder where your image file is, open a new Python file called object_detection_mobile_ssd.py.

Here is the full code for the system. The only things you’ll need to change in this code is the name of your desired input video file on line 10 and the name of your desired output file on line 14.

# Project: How to Detect Objects in Video Using MobileNet SSD in OpenCV
# Author: Addison Sears-Collins
# Date created: March 1, 2021
# Description: Object detection using OpenCV

import cv2 # Computer vision library
import numpy as np # Scientific computing library 

# Make sure the video file is in the same directory as your code
filename = 'edmonton_canada.mp4'
file_size = (1920,1080) # Assumes 1920x1080 mp4

# We want to save the output to a video file
output_filename = 'edmonton_canada_obj_detect_mobssd.mp4'
output_frames_per_second = 20.0 

RESIZED_DIMENSIONS = (300, 300) # Dimensions that SSD was trained on. 
IMG_NORM_RATIO = 0.007843 # In grayscale a pixel can range between 0 and 255

# Load the pre-trained neural network
neural_network = cv2.dnn.readNetFromCaffe('MobileNetSSD_deploy.prototxt.txt', 
        'MobileNetSSD_deploy.caffemodel')

# List of categories and classes
categories = { 0: 'background', 1: 'aeroplane', 2: 'bicycle', 3: 'bird', 
               4: 'boat', 5: 'bottle', 6: 'bus', 7: 'car', 8: 'cat', 
               9: 'chair', 10: 'cow', 11: 'diningtable', 12: 'dog', 
              13: 'horse', 14: 'motorbike', 15: 'person', 
              16: 'pottedplant', 17: 'sheep', 18: 'sofa', 
              19: 'train', 20: 'tvmonitor'}

classes =  ["background", "aeroplane", "bicycle", "bird", "boat", "bottle", 
            "bus", "car", "cat", "chair", "cow", 
           "diningtable",  "dog", "horse", "motorbike", "person", 
           "pottedplant", "sheep", "sofa", "train", "tvmonitor"]
					 
# Create the bounding boxes
bbox_colors = np.random.uniform(255, 0, size=(len(categories), 3))
	
def main():

  # Load a video
  cap = cv2.VideoCapture(filename)

  # Create a VideoWriter object so we can save the video output
  fourcc = cv2.VideoWriter_fourcc(*'mp4v')
  result = cv2.VideoWriter(output_filename,  
                           fourcc, 
                           output_frames_per_second, 
                           file_size) 
	
  # Process the video
  while cap.isOpened():
		
    # Capture one frame at a time
    success, frame = cap.read() 

    # Do we have a video frame? If true, proceed.
    if success:
		
      # Capture the frame's height and width
      (h, w) = frame.shape[:2]

      # Create a blob. A blob is a group of connected pixels in a binary 
      # frame that share some common property (e.g. grayscale value)
      # Preprocess the frame to prepare it for deep learning classification
      frame_blob = cv2.dnn.blobFromImage(cv2.resize(frame, RESIZED_DIMENSIONS), 
                     IMG_NORM_RATIO, RESIZED_DIMENSIONS, 127.5)
	
      # Set the input for the neural network
      neural_network.setInput(frame_blob)

      # Predict the objects in the image
      neural_network_output = neural_network.forward()

      # Put the bounding boxes around the detected objects
      for i in np.arange(0, neural_network_output.shape[2]):
			
        confidence = neural_network_output[0, 0, i, 2]
    
        # Confidence must be at least 30%		
        if confidence > 0.30:
				
          idx = int(neural_network_output[0, 0, i, 1])

          bounding_box = neural_network_output[0, 0, i, 3:7] * np.array(
            [w, h, w, h])

          (startX, startY, endX, endY) = bounding_box.astype("int")

          label = "{}: {:.2f}%".format(classes[idx], confidence * 100) 
        
          cv2.rectangle(frame, (startX, startY), (
            endX, endY), bbox_colors[idx], 2)     
						
          y = startY - 15 if startY - 15 > 15 else startY + 15     

          cv2.putText(frame, label, (startX, y),cv2.FONT_HERSHEY_SIMPLEX, 
            0.5, bbox_colors[idx], 2)
		
      # We now need to resize the frame so its dimensions
      # are equivalent to the dimensions of the original frame
      frame = cv2.resize(frame, file_size, interpolation=cv2.INTER_NEAREST)

			# Write the frame to the output video file
      result.write(frame)
		
    # No more video frames left
    else:
      break
			
  # Stop when the video is finished
  cap.release()
	
  # Release the video recording
  result.release()

main()

To run the code, type the following command:

python object_detection_mobile_ssd.py

You will see the video output that is at the top of this tutorial.

That’s it. Keep building!

How to Detect and Draw Contours in Images Using OpenCV

In this tutorial, we will go through the basics of how to detect and draw contours around objects in an image using OpenCV. We will also learn how to draw a bounding box around these objects.

A contour is a boundary around an object. That boundary is made up of image pixels that have the same color or intensity.

Note that any given object can have multiple edges. However, it will only have one boundary.

Real-World Applications

Object Detection
Object Tracking
Object Classification

Let’s get started!

Prerequisites

Python 3.7 or higher

Find an Image File

Find an image of any size. Here is mine:

How Contour Detection Works

At a high level, here is the 5-step process for contour detection in OpenCV:

Read a color image
Convert the image to grayscale
Convert the image to binary (i.e. black and white only) using Otsu’s method or a fixed threshold that you choose.
If the objects in the image are black, and the background is white, we need to invert the image so that white pixels become black and black pixels become white. Otherwise, we leave the image as-is.
Detect the contours

Code

In the same folder where your image file is, open a new Python file called detecting_contours.py.

Here is the full code for the system. The only thing you’ll need to change (if you wish to use your own image) in this code is the name of your desired input image file on line 11.

# Project: How to Detect and Draw Contours in Images Using OpenCV
# Author: Addison Sears-Collins
# Date created: February 28, 2021
# Description: How to detect and draw contours around objects in 
# an image using OpenCV.

import cv2 # Computer vision library

# Read the color image
image = cv2.imread("shapes-small.jpg")

# Make a copy
new_image = image.copy()

# Convert the image to grayscale
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

# Display the grayscale image
cv2.imshow('Gray image', gray)  
cv2.waitKey(0) # Wait for keypress to continue
cv2.destroyAllWindows() # Close windows

# Convert the grayscale image to binary
ret, binary = cv2.threshold(gray, 100, 255, 
  cv2.THRESH_OTSU)

# Display the binary image
cv2.imshow('Binary image', binary)
cv2.waitKey(0) # Wait for keypress to continue
cv2.destroyAllWindows() # Close windows

# To detect object contours, we want a black background and a white 
# foreground, so we invert the image (i.e. 255 - pixel value)
inverted_binary = ~binary
cv2.imshow('Inverted binary image', inverted_binary)
cv2.waitKey(0) # Wait for keypress to continue
cv2.destroyAllWindows() # Close windows

# Find the contours on the inverted binary image, and store them in a list
# Contours are drawn around white blobs.
# hierarchy variable contains info on the relationship between the contours
contours, hierarchy = cv2.findContours(inverted_binary,
  cv2.RETR_TREE,
  cv2.CHAIN_APPROX_SIMPLE)
	
# Draw the contours (in red) on the original image and display the result
# Input color code is in BGR (blue, green, red) format
# -1 means to draw all contours
with_contours = cv2.drawContours(image, contours, -1,(255,0,255),3)
cv2.imshow('Detected contours', with_contours)
cv2.waitKey(0)
cv2.destroyAllWindows()

# Show the total number of contours that were detected
print('Total number of contours detected: ' + str(len(contours)))

# Draw just the first contour
# The 0 means to draw the first contour
first_contour = cv2.drawContours(new_image, contours, 0,(255,0,255),3)
cv2.imshow('First detected contour', first_contour)
cv2.waitKey(0)
cv2.destroyAllWindows()

# Draw a bounding box around the first contour
# x is the starting x coordinate of the bounding box
# y is the starting y coordinate of the bounding box
# w is the width of the bounding box
# h is the height of the bounding box
x, y, w, h = cv2.boundingRect(contours[0])
cv2.rectangle(first_contour,(x,y), (x+w,y+h), (255,0,0), 5)
cv2.imshow('First contour with bounding box', first_contour)
cv2.waitKey(0)
cv2.destroyAllWindows()

# Draw a bounding box around all contours
for c in contours:
  x, y, w, h = cv2.boundingRect(c)

	# Make sure contour area is large enough
  if (cv2.contourArea(c)) > 10:
    cv2.rectangle(with_contours,(x,y), (x+w,y+h), (255,0,0), 5)
		
cv2.imshow('All contours with bounding box', with_contours)
cv2.waitKey(0)
cv2.destroyAllWindows()

To run the code, type the following command:

python detecting_contours.py

Output

# Convert the image to grayscale
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

# Display the grayscale image
cv2.imshow('Gray image', gray)  
cv2.waitKey(0) # Wait for keypress to continue
cv2.destroyAllWindows() # Close windows

# Convert the grayscale image to binary
ret, binary = cv2.threshold(gray, 100, 255, 
  cv2.THRESH_OTSU)

# Display the binary image
cv2.imshow('Binary image', binary)
cv2.waitKey(0) # Wait for keypress to continue
cv2.destroyAllWindows() # Close windows

# To detect object contours, we want a black background and a white 
# foreground, so we invert the image (i.e. 255 - pixel value)
inverted_binary = ~binary
cv2.imshow('Inverted binary image', inverted_binary)
cv2.waitKey(0) # Wait for keypress to continue
cv2.destroyAllWindows() # Close windows

# Find the contours on the inverted binary image, and store them in a list
# Contours are drawn around white blobs.
# hierarchy variable contains info on the relationship between the contours
contours, hierarchy = cv2.findContours(inverted_binary,
  cv2.RETR_TREE,
  cv2.CHAIN_APPROX_SIMPLE)
	
# Draw the contours (in red) on the original image and display the result
# Input color code is in BGR (blue, green, red) format
# -1 means to draw all contours
with_contours = cv2.drawContours(image, contours, -1,(255,0,255),3)
cv2.imshow('Detected contours', with_contours)
cv2.waitKey(0)
cv2.destroyAllWindows()

# Show the total number of contours that were detected
print('Total number of contours detected: ' + str(len(contours)))

# Draw just the first contour
# The 0 means to draw the first contour
first_contour = cv2.drawContours(new_image, contours, 0,(255,0,255),3)
cv2.imshow('First detected contour', first_contour)
cv2.waitKey(0)
cv2.destroyAllWindows()

# Draw a bounding box around the first contour
# x is the starting x coordinate of the bounding box
# y is the starting y coordinate of the bounding box
# w is the width of the bounding box
# h is the height of the bounding box
x, y, w, h = cv2.boundingRect(contours[0])
cv2.rectangle(first_contour,(x,y), (x+w,y+h), (255,0,0), 5)
cv2.imshow('First contour with bounding box', first_contour)
cv2.waitKey(0)
cv2.destroyAllWindows()

# Draw a bounding box around all contours
for c in contours:
  x, y, w, h = cv2.boundingRect(c)

	# Make sure contour area is large enough
  if (cv2.contourArea(c)) > 10:
    cv2.rectangle(with_contours,(x,y), (x+w,y+h), (255,0,0), 5)
		
cv2.imshow('All contours with bounding box', with_contours)
cv2.waitKey(0)
cv2.destroyAllWindows()

That’s it! Keep building!