This repository contains four computer vision modules that utilize machine learning and deep learning techniques covering a range of topics, including object detection, instance segmentation, and object tracking.

This module focuses on detecting objects in images using deep learning techniques. It demonstrates how to use a pre-trained DNN Mobilenet architecture model for object detection using model inference.

This module focuses on leveraging TensorFlow Hub to detect objects in images. It provides a step-by-step guide on how to use a pre-trained object detection EfficientDet D4 architecture model for object detection using model inference.

This project focuses on classifying and segmenting objects in images using deep learning techniques. It demonstrates how to use a pre-trained Mask RCNN model for instance segmentation tasks. The project includes data preparation, model training, evaluation, and visualization of the segmentation results.

This module focuses on tracking objects in video streams using deep learning techniques. It demonstrates how to build an object tracking system using a pre-trained model. It includes a demonstration of the tracking system in action, showcasing its performance on real-time video streams.