Published Paper Details:

Our project aims to implement object detection using the YOLO (You Only Look Once) algorithm, facilitating real-time detection of specified objects from both camera feeds and images. Object detection is a crucial task in computer vision with numerous applications ranging from surveillance to autonomous vehicles. YOLO is known for its efficiency in processing speed while maintaining high accuracy. The project involves training the YOLO model on a dataset containing annotated images of target objects. These objects may include commonly encountered items like cars, persons, and more, depending on the project's scope. Once trained, the model can identify and localize these objects within an image and camara. The implementation includes a user-friendly interface that allows users to input live camera feeds or static images for object detection. The system provides realtime feedback on detected objects, including their class labels and bounding box coordinates. Additionally, the accuracy of detection is displayed, giving users confidence in the reliability of the results. Overall, this project demonstrates the practical application of machine learning techniques, specifically the YOLO algorithm, in real-world scenarios where fast and accurate object detection is essential. The system's ability to operate in real-time makes it suitable for various applications, including surveillance, traffic monitoring, and object tracking.