At 10-15 hrs/week
Get access to classroom immediately on enrollment
In collaboration with
This program requires experience with Python, statistics, machine learning, and deep learning.See detailed requirements.
Master computer vision and image processing essentials. Learn to extract important features from image data, and apply deep learning techniques to classification tasks.Facial Keypoint Detection
Learn to apply deep learning architectures to computer vision tasks. Discover how to combine CNN and RNN networks to build an automatic image captioning application.Automatic Image Captioning
Learn how to locate an object and track it over time. These techniques are used in a variety of moving systems, such as self-driving car navigation and drone flight.Landmark Detection & Tracking
from industry experts
Personal career coach and
As the founder and president of Udacity, Sebastian’s mission is to democratize education. He is also the founder of Google X, where he led projects including the Self-Driving Car, Google Glass, and more.
Cezanne is an expert in computer vision with a Masters in Electrical Engineering from Stanford University. As a former researcher in genomics and biomedical imaging, she’s applied computer vision and deep learning to medical diagnostic applications.
Alexis is an applied mathematician with a Masters in Computer Science from Brown University and a Masters in Applied Mathematics from the University of Michigan. She was formerly a National Science Foundation Graduate Research Fellow.
Juan is a computational physicist with a Masters in Astronomy. He is finishing his PhD in Biophysics. He previously worked at NASA developing space instruments and writing software to analyze large amounts of scientific data using machine learning techniques.
Jay has a degree in computer science, loves visualizing machine learning concepts, and is the Investment Principal at STV, a $500 million venture capital fund focused on high-technology startups.
Ortal Arel has a PhD in Computer Engineering, and has been a professor and researcher in the field of applied cryptography. She has worked on design and analysis of intelligent algorithms for high-speed custom digital architectures.
Luis was formerly a Machine Learning Engineer at Google. He holds a PhD in mathematics from the University of Michigan, and a Postdoctoral Fellowship at the University of Quebec at Montreal.
Exceptionally well rounded and wholesome introduction to Computer Vision methods going from the very basic 'classical' OpenCV based techniques to all the way to sophisticated Deep Learning based applications. However, I do wish that Udacity 'updates' this course soon as the state of the art techniques discussed have changed a lot since 2017-18. After the completion of this ND, you'd be deft with state of the art advances in Computer Vision that have happened around till late 2017/early 2018. I would still give this ND a 5-star rating because it is so well made!
I've found the program more challenging than I expected. That's a good thing. My mentor has been very helpful and generally responds very promptly. I think the online help could be improved. The chat room with other students hasn't been very helpful. The course materials are pretty good and I like the idea of extra project activities to dig deeper into the topics. It took me so much time to complete the first project that I did not have time to do any of the extra activities. this time.
Its pretty good. Just expected a little more portions where we are supposed to write code and handle things on my own. While it has been perfect for me, a guy trying to do complete 2 Nanodegrees (CVND and DRLND) and have full-time job and a few other things. But a bit more letting the students handle, might let the ones who are just getting started with these a bit more experienced. Just a thought. Keep rocking!
This program is excellent for teaching the fundamentals of computer vision. The projects are interesting and fun too. I recommend it to anyone that has an interest in CV for robotics or AI. Some background knowledge is already assumed, but they provide all of the necessary information in the lectures for escential learning!
The program exceeded my expectation to be honest, I learned a lot and it was lots of fun. What was really good as well was the extra feedback on how your models can be improved. I appreciated the course a lot and thanks to everyone who participated in the program on the teaching/logistics side, it was a great experience.
It was very good that I could get familiarized with OpenCV library, and deep learning (CNN/RNN) with PyTorch. It was also very good that this program covers the latest topics, such as YOLO and SLAM. Lesson explanations are very carefully made and I could learn difficult concepts step by step.
The demand for engineers with computer vision and deep learning skills far exceeds the current supply. This program offers a unique opportunity to develop these in-demand skills and is for anyone seeking to launch or advance their skills in modern computer vision techniques. You’ll complete several computer vision applications using a combination of Python, computer vision, and deep learning libraries that will serve as portfolio pieces that demonstrate the skills you’ve acquired.
This program is designed to build on your skills in machine learning and deep learning. As such, it doesn't prepare you for a specific job, but expands your skills in the computer vision domain. These skills can be applied to various applications such as image and video processing, automated vehicles, smartphone apps, and more.
If you’re new to Computer Vision, and eager to explore applications like facial recognition and object tracking, the Computer Vision Nanodegree program is an ideal choice. The curriculum introduces you to image analysis with Python and OpenCV, then goes on to cover deep learning techniques that can be applied to a variety of image classification and regression tasks. Over the course of the program, you’ll leverage your Python coding experience to build a broad portfolio of applications that showcase your newly-acquired Computer Vision skills.
No. This Nanodegree program accepts all applicants regardless of experience and specific background.
You must have completed a course in Deep Learning equivalent to the Deep Learning Nanodegree program prior to entering the program. Additionally, you should have the following knowledge: Intermediate Python programming knowledge, including:
Basic shell scripting:
Basic statistical knowledge, including:
Intermediate differential calculus and linear algebra, including:
We have a number of courses and programs we can recommend that will help prepare you for the program, depending on the areas you need to address. For example:
The Computer Vision Nanodegree program is comprised of content and curriculum to support three (3) projects. We estimate that students can complete the program in three (3) months working 10 hours per week.
Each project will be reviewed by the Udacity reviewer network. Feedback will be provided and if you do not pass the project, you will be asked to resubmit the project until it passes.
Please see the Udacity Program FAQs for policies on enrollment in our programs.
Many of our graduates continue on to our Artificial Intelligence Nanodegree program, Natural Language Processing Nanodegree Program, Robotics Engineer Nanodegree program, and our Self-Driving Car Engineer Nanodegree programs. Feel free to explore other Nanodegree program options as well.
You will need a computer running a 64-bit operating system (most modern Windows, OS X, and Linux versions will work) with at least 8GB of RAM, along with administrator account permissions sufficient to install programs including Anaconda with Python 3.5 and supporting packages. Your network should allow secure connections to remote hosts (like SSH). We will provide you with instructions to install the required software packages. Udacity does not provide any hardware.