Computer Vision with Embedded ML
Course provided by Model Institute of Engineering & Technology
5 modules
Build smart vision systems with Embedded ML
3-4 Level NCrF
National Credit Framework
40 Hours
Flexible Learning
Intermediate Level
Nano Course
01 Credit
Course Overview
This course provides hands-on training in integrating computer vision (CV) capabilities with embedded machine learning (ML) systems. You will learn to deploy intelligent vision-based applications on resource-constrained devices, such as microcontrollers and edge devices.
Key Learning Highlights
Understanding the fundamentals of computer vision and image processing.
Building and training lightweight ML models optimized for embedded systems.
Implementing real-time object detection, recognition, and classification on edge devices.
Leveraging popular frameworks and libraries for embedded ML, including TensorFlow Lite, OpenCV, and Edge Impulse.
Designing efficient workflows for data collection, model deployment, and performance optimization.
Exploring practical applications in robotics, IoT, smart cameras, and industrial automation.
Tools & Platforms Used
Learning Outcome
By the end of this course, students will be able to:
- Understand the basics of digital image formation and representation.
- Apply neural networks for basic image classification tasks.
- Understand convolutional neural networks (CNNs) and apply them for visual recognition.
- Utilize data augmentation to improve model robustness.
- Train and evaluate object detection models using Edge Impulse.
Master the course with just 3 Modules
This course, enables you to master the subject in just 3 modules. It begins with the fundamentals of computer vision and embedded systems, then guides you through data acquisition and preprocessing for real-time applications. You will learn to train lightweight machine learning models optimized for embedded devices and implement them efficiently for real-time inference at the edge. Finally, you will apply your skills in practical projects across robotics, IoT, and smart devices, gaining hands-on experience that bridges AI innovation with edge computing.
Image Classification with Neural Networks
Introduction to computer vision and image structure
Basics of neural networks for image classification
Training and deploying a basic image classifier to an embedded device
Convolutional Neural Networks (CNNs)
CNN architecture: convolution, pooling, activation
Visualization techniques for CNNs
Data augmentation techniques
Hands-on deployment of CNN to edge platforms
Object Detection on Embedded Systems
Object detection principles and key differences from classification
Evaluation metrics: IoU, precision, recall, mAP
Introduction to object detection models: SSD, YOLO, MobileNet
Training and deploying object detection models on Edge Impulse
Roles
Embedded ML Engineer
Computer Vision Engineer
AI/ML Developer for IoT
Robotics Engineer
Edge AI Specialist
