Description:Title:

Facial Movements Identification for Vehicle Drivers using Machine Learning

Field of the Invention

[0001] The present invention is related to the computer science domain and computer vision field.
[0002] This innovation refers to an endeavor to build a precise and robust framework for distinguishing diverted drivers. While driving the vehicle, drivers frequently perform secondary activities that distract driving. A decrease in driver distraction is a critical aspect of the smart transportation system.

Background

[0003] The background description provided here includes all the relevant information that may be beneficial in understanding the present invention. It is not an acceptance that any of the information or a fact provided herein is a prior invention or relevant to the currently claimed invention, or that any publication categorically or implicitly referenced is a prior art.
[0004] The pursuit of generating this system was cultivated after comparative observations of the real-life events that are occurring in and around the globe. With the advent of technology, we endeavor to build a precise and robust framework for distinguishing diverted drivers. While driving the vehicle, drivers frequently perform secondary activities that distract driving. A decrease in driver distraction is a critical aspect of the smart transportation system. Different convolutional networks had been trained on images by eliminating the final layer to get their feature vectors. By using the stacking ensemble technique, we stack all the feature vectors to train it on a convolutional network.
[0005] The main aim of the invention is to detect the distracted driver posture accurately. The study shows how models predict the desired classes. Real-time driver distraction detection is the core to many distraction counter-measures and fundamental for constructing a driver-centered driver assistance system.
[0006] There is a scope for enhancement of this invention. As technology evolves rapidly, there can be new advancements that can be integrated in this invention. By using the stacking ensemble technique, we stack all the feature vectors to train it on a convolutional network. This stacking technique is used to detect the distracted driver posture with very precise detection.
[0007] Machine learning can be used to analyze and detect patterns in driving behavior that are indicative of distracted driving. For example, sensors in a vehicle can collect data on the driver's steering, braking, and acceleration patterns, as well as their use of turn signals and other controls. This data can then be analyzed using algorithms to identify patterns that are consistent with distracted driving, such as sudden swerves, erratic braking, or prolonged periods of inactivity. It can be a useful tool in detecting distracted driving; it should be used in conjunction with other measures, such as driver education and awareness campaigns, to reduce the risk of accidents caused by distracted driving.

Objects of the Invention

[0008] Following are the objectives of the present disclosure:
• Focus on roads to minimize the chances of drivers getting distracted.
• Using CNN and Stacking Enumerable along with Eye detection to prevent accidents on the road.
• Detecting and improving the warning systems and identify black spots.

Summary

[0009] This system can help in detection and prevention of accidents by using the following steps:
• Installation of system on vehicles.
• Use of Camera and Sensors to detect distracted driver while driving.
• Warn the driver about distraction and record the data.
• Use of data to analyze and improve the system.
• Prevention of further accidents by giving early warning.

Drawings

Figure 1: Algorithm Process Flowchart

Brief Description of the Drawing

[0010] The figure 1 represents Algorithm Process Flowchart of the working model in the present invention.

Detailed Description

[0011] Different convolutional networks had been trained on images by eliminating the final layer to get their feature vectors. By using the stacking ensemble technique, we stack all the feature vectors to train it on a convolutional network.
[0012] Real-time driver distraction detection is the core of many distraction countermeasures and fundamental for constructing a driver-cantered driver assistance system.
[0013] The Technology used in the invention is as follows:
• Windows-10 operating systems
• Python Programming Language
• NumPy and Panda Libraries
• Cameras and Sensors
[0014] Following are the end users of the invention:
• Government and Private Car Manufactures
• Security Management Services
• Customers or Clients in Automobile Industries

Advantages of the Invention

[0015] Following are the advantages of the invention:
• Improved Road Safety: One of the most significant advantages of using machine learning to detect distracted driving is the potential to improve road safety. By identifying drivers who are distracted, authorities can take proactive measures to prevent accidents before they happen.
• Early Warning System: Machine learning algorithms can provide an early warning system to drivers who may be distracted. This can help drivers become more aware of their behavior and take corrective action to prevent accidents.
• Versatility: Machine learning algorithms can be trained to detect a wide range of distractions, including using a phone, eating, drinking, and even drowsiness. This versatility makes machine learning a valuable tool in promoting safe driving practices.
• Cost-Effective: Once implemented, machine learning algorithms can be cost-effective in detecting distracted driving. This is because they can be integrated into existing sensors in vehicles and do not require additional hardware.
• Continuous Monitoring: Machine learning algorithms can monitor driver behavior continuously, providing a more accurate assessment of driver distraction than human observation alone.
• Data Analytics: Machine learning algorithms can analyze large amounts of data quickly and accurately. This can help authorities identify patterns of distracted driving behavior and develop targeted interventions to prevent accidents. , Claims:Following are the claims of the invention:

1. Analysis and detection of patterns in driving behavior that is indicative of distracted driving.
2. Sensors in a vehicle can be used to collect data on the driver's steering, braking, and acceleration patterns, as well as their use of turn signals and other controls.
3. This data can then be analyzed using machine learning algorithms to identify patterns that are consistent with distracted driving, such as sudden swerves, erratic braking, or prolonged periods of inactivity.
4. This stacking technique, which is used to detect the distracted driver posture, achieves high accuracy.