Advanced Driver Assistance System Based on IoT V2V and V2I for Vision Enabled Lane Changing with Futuristic...

Area of Science:

• Automotive Engineering
• Computer Vision
• Internet of Things (IoT)

Background:

• Modern vehicles utilize IoT-based systems for data collection and cloud analytics.
• Existing systems focus on data logging rather than real-time, vision-aided inter-vehicle communication.

Purpose of the Study:

• To implement computer vision-aided vehicle-to-vehicle (V2V) communication using IoT for autonomous vehicles.
• To analyze in-vehicle system parameters and suggest custom driving modes for enhanced driver assistance.

Main Methods:

• Integration of computer vision algorithms for driver assistance (e.g., lane change, collision avoidance).
• Utilizing IoT for real-time data collection from sensors and electronic control units (ECUs).
• Employing vehicle-to-infrastructure (V2I) protocols and cloud platforms for data visualization and analysis.

Main Results:

• Demonstrated efficient performance in critical driving scenarios via computer vision-based assistance.
• ECU analysis of parameters like speed, distance, and fuel economy to predict driving conditions.
• Successful suggestion of custom driving modes and over-the-air (OTA) updates for improved drivability.

Conclusions:

• The proposed IoT-enabled, computer vision-driven system enhances autonomous vehicle safety and performance.
• Real-time data analytics and cloud integration enable adaptive driving modes and system upgrades.
• This approach offers a pathway to more intelligent and responsive autonomous driving systems.