Advanced Driver Assistance Systems (ADAS) are technologies designed to improve driving safety, reduce human error, and support the path toward fully autonomous vehicles. This repo is a simple and structured place to learn the core concepts behind ADAS, the sensors used, how AI fits in, and how modern safety features work.
ADAS includes systems that monitor the surroundings of a vehicle, support the driver, and prevent accidents. These systems rely on multiple sensors, real‑time processing, and intelligent decision‑making.
In this repo, you will find notes and explanations based on the Udemy course content, organized into clear sections:
- Road Safety
- Why ADAS
- How ADAS Help Drivers
- General Working of ADAS
- Role of ADAS towards AD
- Automotive Radar
- Camera Vision System
- Ultrasonic Sensor
- Lidar Sensor
- GNSS, GPS and IMU
| Sensor Type | Description |
|---|---|
| Radar | Measures distance and velocity of objects. Used for ACC, FCW, BSD. |
| Camera (Mono/Stereo) | Recognizes lanes, signs, objects, pedestrians. |
| Lidar | High‑resolution 3D mapping for AD and advanced perception. |
| Ultrasonic | Short‑range detection for parking assist. |
| GNSS / GPS | Provides global positioning. |
| IMU | Measures acceleration and rotation for vehicle state estimation. |
- Overview
- Sensors and Sensor Fusion
- Processors
- Adaptive Cruise Control (ACC)
- Rear Cross Traffic Alert (RCTA)
- Vehicle Exit Alert
- Forward Cross Traffic Alert
- Forward Collision Warning (FCW)
- Vehicle Turn Assist
- Blind Spot Detection (BSD)
- Parking Assist
- Intelligent Headlight Control
- Occupant Protection
- Pedestrian Protection
- Evasive Steering Support
- Traffic Sign Recognition (TSR)
- Speed Limit Assist
- Lane Departure Warning (LDW)
- 360° Surround View
- Driver Monitoring System
- Driver Drowsiness Detection
- Emergency Brake Assist
- Anti‑lock Braking System (ABS)
- Cross Wind Assist
- ADAS Testing Overview
- Virtual Simulation Testing
- On-Field Testing
Additional learning resources are stored in the Resources folder, such as books, technical papers, and reference materials on ADAS and autonomous driving. These materials can help you deepen your understanding beyond the course content.
Optional Python programming activities and practical exercises are provided in the Projects folder. They cover computer vision, machine learning, and deep learning tasks related to ADAS, with 7 guided exercises including problem statements for self-practice.
You can explore them here:
- Coding Activity 1 - Development of Lane Detection System for ADAS Application
- Coding Activity 2 - Development of Traffic Sign Recognition System for ADAS
- Coding Activity 3 - Development of Speed Limit Recognition System for ADAS
- Coding Activity 4 - Object Detection from Camera Images using YOLOv3
- Coding Activity 5 - Street Light Detection and Recognition for ADAS
- Coding Activity 6 - Instrument Cluster (GUI) Development using Python
- Coding Activity 7 - Let's Put All Together
Each activity includes a detailed problem statement and full implementation code to help you practice and apply the concepts learned in the course.
Note: The implementations are created by me and are not part of the Udemy course.
If you find this repo useful, feel free to share it. Contributions and suggestions are always welcome!