Welcome to the Object Detection and Tracking project! This repository contains the inference code for an object detection and tracking solution, leveragin YOLO-NAS (You Only Look Once - Neural Architecture Search) for object detection and Deep Sort for robust object tracking.
Object detection and tracking are fundamental tasks in computer vision and have a wide range of applications, from video surveillance and autonomous driving to interactive systems.
YOLO-NAS (You Only Look Once - Neural Architecture Search) is a highly optimized variant of the YOLO family of object detection models. It has been fine-tuned for efficient and real-time object detection tasks.
Deep Sort is a state-of-the-art object tracking algorithm that combines deep learning techniques with traditional computer vision methods. Its ability to maintain object identities across frames, even in challenging scenarios, makes it an essential part of accurately tracking detected objects.