Vehicle Idling Classification Using Driver and Road Video
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current vehicle idling practices waste fuel, cause environmental pollution, health issues, and vehicle damage, and consume excessive computing resources due to inefficient management of vehicle idling.
Innovation Solution
A video system utilizing machine learning models processes RFC, DFC, and idling events data to classify vehicle idling, providing alerts and training to drivers, and conserving resources by reducing unnecessary idling.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Temperature
If vehicle idling is extended to warm up the engine, then engine warmth is improved, but air pollution increases and fuel is wasted
Solution Approach 1:
The patent segments the vehicle warming process into two distinct phases: engine warming (which can occur while idling) and component warming (which requires vehicle movement). This segmentation allows the system to identify when idling is unnecessary by detecting that components like wheels, steering, and suspension cannot be warmed without movement, thereby reducing harmful idling emissions.
Solution Approach 2:
The patent implements a feedback mechanism using sensors to detect vehicle operation parameters and a classification system that provides feedback to drivers about whether their idling behavior is necessary or excessive. This feedback loop enables drivers to adjust their behavior, reducing unnecessary idling and associated air pollution while maintaining necessary engine warmth.
2Temperature
If vehicle idling is extended to warm up components, then component warmth is improved, but fuel consumption increases
Solution Approach 1:
The patent segments the warming requirements into engine-specific (can be met by idling) and component-specific (requires movement) needs. This segmentation allows the system to recommend minimal idling duration for engine warmth while encouraging immediate driving for component warmth, thereby minimizing fuel waste from prolonged idling.
Solution Approach 2:
The patent performs preliminary classification of idling events to determine whether they are necessary or excessive before the idling period ends. This preliminary action allows the system to provide timely feedback to drivers about whether their idling behavior is appropriate, enabling them to adjust their behavior for subsequent trips and reduce overall fuel consumption.
3Measurement precision
If machine learning models are used to classify idling events, then detection accuracy is improved, but computing resources are consumed
Solution Approach 1:
The patent applies partial machine learning classification only to idling events that meet certain criteria (duration, context) rather than all idling events. This partial application maintains detection accuracy for problematic idling while reducing overall computing resource consumption by skipping analysis for clearly necessary or clearly unnecessary idling events.
Data Source
AI summary
A device may receive road facing camera (RFC) video data, driver facing camera (DFC) video data, and idling events data associated with a vehicle, and may receive traffic data associated with the vehicle. The device may determine that an idling event of the idling events data is an idling event trigger, and may process the idling event and the DFC video data, based on the idling event being an idling event trigger and with a first machine learning model, to determine a behavior of a driver of the vehicle. The device may process the behavior of the driver, the RFC video data, and the traffic data, with a second machine learning model, to determine a score for the idling event, and may determine a classification for the idling event based on the score and a score threshold. The device may perform one or more actions based on the classification.