Scribd
Upload
69 views

Python Project Final Report

This document summarizes a project on real-time object detection in videos. The project uses OpenCV in Python to import a video, perform background subtraction to isolate moving objects, and apply contours to draw boundaries around detected vehicles. Region of interest is used to specify the road area. The output displays attributes of detected vehicles like coordinates, dimensions, and object IDs. Object tracking is implemented using a tracker file. Applications of this object detection include traffic monitoring, people counting, and industrial defect detection.

Uploaded by

Ayusha Jagtap
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
69 views

Python Project Final Report

This document summarizes a project on real-time object detection in videos. The project uses OpenCV in Python to import a video, perform background subtraction to isolate moving objects, and apply contours to draw boundaries around detected vehicles. Region of interest is used to specify the road area. The output displays attributes of detected vehicles like coordinates, dimensions, and object IDs. Object tracking is implemented using a tracker file. Applications of this object detection include traffic monitoring, people counting, and industrial defect detection.

Uploaded by

Ayusha Jagtap
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 3

VEERMATA JIJABAI TECHNOLOGICAL INSTITUTE,MATUNGA,MUMBAI

INSTRUCTOR : PROF.SHIVANI SUPE

ABSTRACT: Real time object detection is a vast area of computer vision. If there
is a single object to be detected in an image, it is known as Image Localization
and if there are multiple objects in an image, then it is Object Detection. This
detects the semantic objects of a class in digital videos. The applications of real
time object detection include tracking objects, self-driving cars, face
detection,counting people, ball tracking in sports and many more.By using
contours we have created boundaries over the mask.Hance by this way. This is
useful in counting no of people in certain area

KEYWORDS: Keywords: Computer vision, roi,contours

PROBLEM STATEMENT: Given video images of a scene, identify or verify one or


more objects on a road

METHODOLOGY:
In this project we have used open cv library of Python.Initially we have
imported an Video from which we want to track the objects from.If we want to
stop the video we can press the key on keyboard.Further we used the
background subtractor to only focus on objects and also we created the new
frame(mask) in which we made only vehicles seem white and all other
black.Also we used contours to create green boundaries around the vehicles.
To make the contours to focus only on the vehicles and not on other small
things we increased the area for contour.Also we used roi(region of interest),
We used it for specifying only the road area.Also the output displayed
contained the x,y of the vehicle as well as the height,width of the rectangle
around the vehicle as well as the object id which is also printed on the
frame.Also inorder to track the objects we used the tracker file.
WHY YOU CHOOSE THIS:
We choose this project as through Object tracking many daily life problems can
be solved also Computer Vision is our major field of interest.Also Object
tracking has many applications in day to day life.

IMAGES:
APPLICATIONS:
1.Counting no of people in a certain area.
2.Detecting objects passing by the conveyor belt.
3.We scan the digital images to locate instances of every object, separate
them, and analyze their necessary features for real-time prediction
4.Specific object detection applications includes, animal detection, vehicle
detection, people counting, face detection, text detection, pose detection, or
number-plate recognition.
CONCLUSION:
There are many applications of Computer Vision and Object Detection is one of
them. It takes the given video as input and produces the output having the
bounding boxes adequate to the number of objects present within the image.It
projects the scenario of the bounding box by height and width.

CONTRIBUTER:
SAKSHI SURESH KOLI AYUSHA VINAYAK JAGTAP

You might also like