Multi-Class Object Detection System Using Diverse Visual Categories

Project Code :TCMAPY2139

Objective

This project presents a robust multi-class object detection system using YOLOv8 and YOLOv9 for fast and accurate visual recognition. The system is trained on the COCO dataset, which provides a diverse set of labeled categories including vehicles, animals, humans, and everyday objects. Python is used for backend processing, while Streamlit enables a simple and interactive user interface. The model can accurately detect objects such as cars, bicycles, pedestrians, dogs, cats, laptops, and televisions. The integration of YOLOv8 and YOLOv9 ensures high detection accuracy with efficient performance. Overall, the project demonstrates a scalable and reliable object detection framework. It offers a solid foundation for further enhancements in automated visual recognition applications.

Abstract

This project presents a comprehensive multi-class object detection system capable of identifying and classifying diverse visual categories. The system leverages the YOLO V8 AND V9 algorithm, known for its high speed and accuracy in object detection tasks. The dataset used contains a wide range of categories, including vehicles, animals, humans, and various objects, ensuring effective detection across multiple types. The system is implemented with Python for backend processing and Streamlit for a simple, interactive interface. It can detect categories such as bicycle, car, pedestrian, aeroplane, motorbike, bus, dog, cat, laptop, and television, among others. The integration of YOLO V8 AND V9 enables precise detection while maintaining high processing efficiency. This multi-class detection approach provides a flexible framework suitable for diverse scenarios requiring automated object recognition. Streamlit allows seamless interaction with the detection module, providing instant visual feedback of detection results. Overall, the project demonstrates a reliable and scalable object detection system capable of handling a large number of categories with accuracy and speed, offering a foundation for further enhancements in automated visual classification tasks.

Keywords: YOLO V8 AND V9, multi-class detection, Python, Streamlit, bicycle, car, pedestrian, aeroplane, motorbike, object classification

NOTE: Without the concern of our team, please don't submit to the college. This Abstract varies based on student requirements.