Projects completed under Udacity's Computer Vision nanodegree program.
PyTorch library is used to complete the projects 1 and 2.
Project-1: Facial Keypoint Detection
In this project, we'll build a Facial keypoint detection system. The system consists of a face detector that uses Haar cascades and a Convolutional Neural Network, that predicts the keypoints on the detected face.
_Original Repo: Link
Project-2: Image Captioning
In this project, we'll design and train a ENCODER-DECODER(Convolutional Neural Network - Recurrent Neural Network) model for automatically generating image captions. The network is trained on the Microsoft Common Objects in COntext (MS COCO) dataset.
Original Repo: Link
Project-3: Landmark Detection and Tracking (SLAM)
In this project, we'll implement SLAM (Simultaneous Localization and Mapping) for a 2-dimensional world. Sensor and motion data gathered by a simulated robot is used to create a map of an environment. SLAM gives us a way to track the location of a robot in the world in real-time and identify the locations of landmarks such as buildings, trees, rocks, etc.
Original Repo: Link
Images credits: Flaticon