The trio of Luis Oliver, Victor Izquierdo and Alejandro Gutiérrez won the Jetson Project of the Month for their Drowsiness, Blindspot and Emotion Monitor (DBSE)…
Overview
The Jetson Project of the Month highlights the Drowsiness, Blindspot and Emotion Monitor (DBSE) developed by Luis Oliver, Victor Izquierdo, and Alejandro Gutiérrez. This innovative in-car assistance system utilizes NVIDIA Jetson Nano to enhance driver safety by detecting drowsiness, emotional state, and blindspot objects.
What You'll Learn
1
How to implement drowsiness detection using OpenCV and PyTorch
2
Why using Yolov3 for blindspot detection improves driver safety
3
How to utilize MQTT for alerting mechanisms in embedded systems
Prerequisites & Requirements
- Basic understanding of computer vision and machine learning concepts
- Familiarity with OpenCV and PyTorch libraries(optional)
- Experience with embedded systems and hardware integration(optional)
Key Questions Answered
How does the Drowsiness, Blindspot and Emotion Monitor function?
The DBSE system operates through three main modules: Drowsiness detection, Emotion detection, and Driving Monitor. It uses OpenCV's Haar Cascades for face detection and convolutional neural networks in PyTorch to assess the driver's eye state and emotional state, while Yolov3 identifies objects in blindspots.
What technologies are used in the DBSE project?
The DBSE project utilizes NVIDIA Jetson Nano for processing, OpenCV for face detection, PyTorch for neural networks, and the Yolov3 algorithm for blindspot detection. The system also employs MQTT for communication of alerts.
What are the statistics related to distracted and drowsy driving?
According to the NHTSA, 400,000 people were injured in crashes involving distracted drivers in 2018, and there were 4,111 fatalities due to drowsy driving from 2013 to 2017. These statistics highlight the importance of safety systems like DBSE.
How does the DBSE system alert drivers?
The DBSE system alerts drivers through visual and audio signals. It uses a mini-OLED display to show blindspot objects and LEDs to indicate their position, while an alarm sounds if the driver is distracted.
Key Statistics & Figures
Injuries from distracted driving
400,000
Reported by NHTSA in 2018
Fatalities from drowsy driving
4,111
Reported by NHTSA from 2013 to 2017
Technologies & Tools
Some links below are affiliate links. We may earn a commission if you make a purchase.
Hardware
Nvidia Jetson Nano
Used as the processing unit for the DBSE system
Software
Opencv
Utilized for face detection in drowsiness and emotion detection modules
Software
Pytorch
Framework for building convolutional neural networks for driver state detection
Software
Yolov3
Algorithm used for detecting objects in the driver's blindspot
Protocol
Mqtt
Used for sending alerts to the display and speaker
Key Actionable Insights
1Implementing the DBSE system can significantly enhance vehicle safety by providing real-time alerts to drivers.By integrating drowsiness and distraction detection, developers can create systems that proactively assist drivers, potentially reducing accident rates.
2Utilizing open-source resources allows developers to customize and improve upon existing projects like DBSE.The availability of the bill of materials and code on GitHub enables developers to adapt the system for various applications, fostering innovation in automotive safety.
3Leveraging MQTT for alert notifications streamlines communication between the monitoring system and user interfaces.This protocol is lightweight and efficient, making it suitable for embedded systems where bandwidth may be limited.
Common Pitfalls
1
Overlooking the importance of accurate face detection can lead to system failures.
If the face detection module fails to identify the driver properly, the entire monitoring system could be ineffective, emphasizing the need for robust testing and calibration.
Related Concepts
Computer Vision Techniques
Machine Learning In Automotive Applications
Real-time Alert Systems