Thanks to visit codestin.com
Credit goes to www.scribd.com

Scribd
Upload
15 views3 pages

Object Detection Project Report

The mini project focuses on developing a Python-based AI system for real-time object detection using the YOLOv8 model. It supports both image and video detection, providing outputs with bounding boxes and confidence scores, while utilizing core packages like OpenCV and ultralytics. The project features a menu-driven interface and automatically saves results in an output folder.

Uploaded by

rockyash155
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
15 views3 pages

Object Detection Project Report

The mini project focuses on developing a Python-based AI system for real-time object detection using the YOLOv8 model. It supports both image and video detection, providing outputs with bounding boxes and confidence scores, while utilizing core packages like OpenCV and ultralytics. The project features a menu-driven interface and automatically saves results in an output folder.

Uploaded by

rockyash155
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Mini Project Report

Mini Project Title


Object Detection using AI with YOLOv8

Group Members

Roll no Name of Group Members


2413199 Vandre Yash Sushil
2413200 Kadam Vedant Vilas
2413203 Takalkar Shree Jalinder

1. Overview

Project Objective:
The objective of this project is to create a Python-based AI system that performs real-time
object detection on images and videos using the YOLOv8 model.

Scope of the Project:


- Detect multiple object classes (e.g., person, car, dog, etc.)
- Supports:
• Image detection
• Video detection
- Saves output files with bounding boxes and confidence scores
- Uses pre-trained YOLOv8 model (yolov8n.pt) from Ultralytics

Features Implemented:
- Menu-driven interface (CLI)
- Object detection using:
• Image input
• Video input
- Confidence score and bounding box drawn for each detected object
- Output saved automatically in output/ folder
2. Description about Python Packages used
Core Packages:

- cv2 (OpenCV): Read/write images & videos, draw bounding boxes & text
- ultralytics: Run YOLOv8 model for object detection
- os: File system operations
- time: For tracking FPS and performance
- numpy: Handle image array conversions

Functions and Classes Used:

From ultralytics:
- YOLO(): Loads the YOLOv8 model
• Used to run inference on images or frames

From cv2:
- imread, VideoCapture, VideoWriter, rectangle, putText, imshow, waitKey,
destroyAllWindows

From os:
- makedirs: Create output directory

From time:
- time(): Measure elapsed time for FPS calculation

3. Screenshots of the System

- Command-line interface showing the menu:


- Input and output image comparison

Input:

Output:

You might also like