Udacity Computer Vision Nanodegree Projects

This is a showcase of Udacity's Computer Vision Nanodegree projects carried out for professional development.

Table of Contents

• ProjectOne
• Projecttwo
• Projectthree
• References
• Credits

ProjectOne:

Facial Key Points:

Applied knowledge of image processing and deep learning to create a CNN for facial keypoints (eyes, mouth, nose, etc.) detection.

ProjectTwo:

Image Captioning:

Trained a CNN-RNN model to predict captions for a given image, using the Microsoft Common Objects in COntext (MS COCO) dataset.

ProjectThree:

Landmark Detection and Tracking (SLAM):

Implement SLAM, a robust method for tracking an object over time and mapping out its surrounding in a 2-dimensional world. The goal is to combine what we know about robot sensor measurements and movement to create a map of an environment from only sensor and motion data gathered by a robot, over time.

Credits

Special thanks and appreciation to the Secure and Private AI Scholarship Program

References

Reviewed Courses on Introduction to Computer Vision, Advanced Computer Vision & Deep Learning, and Object Tracking and & Localization.

© 2020 GitHub, Inc.