Computer Vision for Embedded Systems
About this courseSkip About this course
This course provides an overview of running computer vision (OpenCV and PyTorch) on embedded systems (such as Raspberry Pi and Jetson). The course emphasizes the resource constraints imposed by embedded systems and examines methods (such as quantization and pruning) to reduce resource requirements. This course will have programming assignments and projects proposed by the students.
Required texts or technologies:
This course does not have a required text. The course will read recently published papers. Students will use Google Colab for programming assignments.
At a glance
- Language: English
- Video Transcript: English
- Associated skills: Pruning, Google Colaboratory, Computer Vision, PyTorch (Machine Learning Library), Quantization, Resource Constraints, Embedded Systems, OpenCV
What you'll learnSkip What you'll learn
i. Use computer vision to analyze images.
ii. List the constraints of embedded systems.
iii. Explore design space of computer vision.
iv. Evaluate different methods for accuracy/time tradeoffs.
- Overview, image data formats, OpenCV
- Edge detection and segmentation
- Applications of computer vision in embedded systems
- Datasets, bias, privacy, competitions
- Machine learning and PyTorch
- Performance and resources (time, memory, accuracy)
- Object detection and motion tracking
- Data annotation and generation
- Pruning and network architecture search
- Tree modular networks
- Vision in context, MobileNet
- Real-time scheduling
Learner testimonialsSkip Learner testimonials
Fall 2021 course feedback:
- The organization of the content is superb.
- It was a very innovative class. It was refreshing that this class was focused on learning, rather than only testing the students.
- I think the concepts are delivered very well.
- I enjoyed having the exposure to quantization.
- The project structure was great in my opinion.
Spring 2022 course feedback:
(Dr. Lu gave the short course at the Seoul National University in South Korea)
- Instruction for the assignments is clear and explicit, and these assignments help me to fully understand the contents learned in the lecture.
- Lectures were very well done.
- I can feel the professor prepared the lecture well.
- Good quiz, good lecture, good lecturer
- Everything was perfect.
Frequently Asked QuestionsSkip Frequently Asked Questions
Q: Does this course focus on theory or practice?
A: The emphasis is using machine learning, not about deriving equations for the theory of machine learning. For example, we will use the tools in PyTorch.