https://github.com/hrolive/computer-vision-nanodegree

As one of the 300 scholars chosen among 6,000 from the first phase, "Secure and Private AI" by Facebook AI, I have earned a full scholarship to Udacity’s Computer Vision Nanodegree
https://github.com/hrolive/computer-vision-nanodegree

computer-vision computer-vision-nanodegree deep-learning face-detection image-captioning machine-learning object-detection opencv python slam

Last synced: 7 days ago
JSON representation

As one of the 300 scholars chosen among 6,000 from the first phase, "Secure and Private AI" by Facebook AI, I have earned a full scholarship to Udacity’s Computer Vision Nanodegree

• Host: GitHub
• URL: https://github.com/hrolive/computer-vision-nanodegree
• Owner: HROlive
• Created: 2019-12-06T17:20:46.000Z (almost 5 years ago)
• Default Branch: master
• Last Pushed: 2022-12-07T23:54:08.000Z (almost 2 years ago)
• Last Synced: 2023-03-04T03:38:57.641Z (over 1 year ago)
• Topics: computer-vision, computer-vision-nanodegree, deep-learning, face-detection, image-captioning, machine-learning, object-detection, opencv, python, slam
• Language: Jupyter Notebook
• Homepage:
• Size: 5.52 MB
• Stars: 2
• Watchers: 3
• Forks: 0
• Open Issues: 30
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Computer Vision Nanodegree 

This repository contains the projects that I've developed during Udacity's [Computer Vision Nanodegree](https://www.udacity.com/course/computer-vision-nanodegree--nd891).

## Projects

### [Facial Keypoints Detection](https://github.com/HROlive/Computer-Vision-Nanodegree/tree/master/project_1-facial_keypoint%20_detection)

Using image processing and deep learning techniques to create a facial keypoint detection system that takes in any image with faces, and predicts the location of 68 distinguishing keypoints on each face, such as the position of the eyes, nose, and mouth.



  



### [Automatic Image Captioning](https://github.com/HROlive/Computer-Vision-Nanodegree/tree/master/project_2-automatic_image_captioning)

Designed and trained a CNN-RNN model that automatically generates image captions. The network is trained on the Microsoft Common Objects in COntext (MS COCO) dataset.



  



### [Landmark Detection & Robot Tracking (SLAM)](https://github.com/HROlive/Computer-Vision-Nanodegree/tree/master/project_3-SLAM_landmark_detection_%26_robot_tracking)

Implementation of 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.