← Embedded Track
Embedded Systems & IoT · Course 07

Edge AI &
Computer Vision

Build camera projects that are useful and responsible: capture, OpenCV basics, motion detection, object detection concepts, notifications, and performance tuning.

Start Course 07 ← Course 06 Course 08 →
10Modules
OpenCVCamera + images
AI eventsDetection + alerts
CapstoneAI camera
Course Progress
0%
Module 01

Edge AI Mindset

Edge AI means useful intelligence near the camera or sensor rather than only in a cloud dashboard.

👁️ Device AI goals
  • Capture useful input.
  • Process it reliably.
  • Respect privacy and consent.
  • Send only necessary alerts or summaries.
  • Measure performance.
🧪 Lab: AI Use Case Filter

Pick three camera ideas and decide whether each should run locally, call an API, or not be built.

🧠 Quick Check
What should come before adding AI to a camera project?
Module 02

Camera Capture

Learners capture still images and video frames, then understand resolution, frame rate, lighting, and focus.

👁️ Capture factors
  • Resolution affects detail and performance.
  • Lighting affects detection quality.
  • Frame rate affects CPU load.
  • Stable mounting improves results.
🧪 Lab: First Capture

Capture a test image, change lighting, and compare quality.

🧠 Quick Check
Why does lighting matter?
Module 03

Image Basics

Images are arrays of pixels. Learners understand width, height, channels, grayscale, and why preprocessing matters.

👁️ Image terms
  • Pixels hold color or brightness values.
  • Grayscale reduces data.
  • Cropping focuses on the useful area.
  • Resizing can improve speed.
🧪 Lab: Image Inspection

Load an image and print its width, height, and channel count.

🧠 Quick Check
Why resize images before processing?
Module 04

OpenCV Preprocessing

Preprocessing prepares frames for detection: grayscale, blur, threshold, edges, and regions of interest.

👁️ Preprocessing tools
  • Grayscale simplifies color data.
  • Blur reduces noise.
  • Thresholding separates light/dark regions.
  • Regions of interest avoid wasted work.
🧪 Lab: Preprocess Pipeline

Create a simple pipeline that grayscales, blurs, and thresholds an image.

🧠 Quick Check
What is a region of interest?
Module 05

Motion Detection

Motion detection is often more practical than heavy AI. Learners compare frames and trigger alerts only when change matters.

👁️ Motion ideas
  • Background comparison detects change.
  • Thresholds ignore tiny differences.
  • Cooldowns prevent alert spam.
  • False positives must be tested.
🧪 Lab: Motion Alert

Build a motion detector that logs when movement is detected.

🧠 Quick Check
Why use cooldowns in motion alerts?
Module 06

Object Detection

Learners understand object detection outputs: labels, confidence, boxes, and why model choice affects speed.

👁️ Detection outputs
  • Label tells what was detected.
  • Confidence estimates certainty.
  • Bounding box locates the object.
  • Small devices need efficient models.
🧪 Lab: Detection Review

Run or mock object detection output and explain label, confidence, and box values.

🧠 Quick Check
What does confidence mean?
Module 07

Face Recognition Concepts & Privacy

This module explains face recognition at a high level with strong privacy boundaries: consent, local-only testing, and alternatives like person detection.

👁️ Privacy boundaries
  • Use consent-based datasets only.
  • Prefer person detection when identity is unnecessary.
  • Do not build covert identification tools.
  • Store as little biometric data as possible.
🧪 Lab: Privacy Decision

Rewrite a face-recognition idea into a safer person-detection or opt-in visitor project.

🧠 Quick Check
When is person detection better than face recognition?
Module 08

Notifications & Events

AI is useful when it produces an action. Learners turn detections into clean events, logs, dashboard updates, or alerts.

👁️ Event design
  • Only alert on meaningful events.
  • Include timestamp and confidence.
  • Avoid sending private images unnecessarily.
  • Throttle repeated events.
🧪 Lab: Event Message

Design an alert payload with event type, time, confidence, and device name.

🧠 Quick Check
What makes an alert useful?
Module 09

Performance Optimization

Learners improve device performance through resolution control, frame skipping, local caching, and measuring latency.

👁️ Performance levers
  • Lower resolution can be faster.
  • Frame skipping reduces workload.
  • Cropping focuses compute.
  • Measure before optimizing.
🧪 Lab: Benchmark Pass

Time three image-processing runs and compare resolution versus speed.

🧠 Quick Check
What should you do before optimizing?
Module 10

Capstone: AI Camera

The capstone builds an ethical AI camera that detects motion or objects, logs events, shows a dashboard, and sends restrained alerts.

👁️ Final requirements
  • Camera capture works.
  • Detection or motion pipeline works.
  • Dashboard shows recent events.
  • Alerts have cooldowns.
  • Privacy choices are documented.
  • README includes setup and demo evidence.
🧪 Lab: Ship AI Camera

Build a local-first AI camera demo with documentation, event logs, and a short recorded demo.

🧠 Quick Check
What makes the AI camera responsible?