Multi-Camera Imaging System for Automated View Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing driver assistance systems require manual selection between visible light and infrared camera views, which can be distracting and inefficient, especially in conditions where ambient light impairs visibility, relying on driver understanding and expensive sensors.
Innovation Solution
An automated system using AI, machine learning, and onboard/offboard sensors to monitor driver reactions and environmental conditions to automatically switch between camera views, selecting infrared images when visibility is impaired, based on predetermined classifications and user feedback.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If manual selection between visible light and infrared camera views is implemented, then driver can control the camera view, but driver distraction and cognitive load increase
Solution Approach 1:
The system automatically detects driving conditions and selects the appropriate camera view without driver intervention. The control circuit monitors environmental sensors and autonomously switches between visible light and infrared views based on detected conditions such as low light, glare, or adverse weather, eliminating the need for manual driver control while maintaining optimal visibility
Solution Approach 2:
The system continuously monitors driving conditions through environmental sensors and feedback from the driver's use of manual controls. This feedback loop allows the automated system to learn from driver preferences and adjust its automatic selection behavior, improving the accuracy of automatic view selection while reducing distraction
2Device complexity
If automated selection system uses only camera images to detect impairment conditions, then system complexity is reduced, but detection accuracy becomes ineffective
Solution Approach 1:
The control circuit performs multiple functions using the same hardware components. Environmental sensors originally designed for other vehicle functions are repurposed to detect visibility impairment conditions. The system integrates data from multiple sensor types (light sensors, temperature sensors, humidity sensors) to accurately determine when to switch between camera views, achieving high detection accuracy without adding specialized expensive sensors
3Measurement precision
If specialized sensors and high capacity computing devices are used to identify impairment conditions, then detection accuracy improves, but system cost increases
Solution Approach 1:
The system uses inexpensive, commonly available environmental sensors instead of expensive specialized sensors. The control circuit processes sensor data efficiently using standard automotive computing resources, avoiding the need for high-capacity computing devices. This approach maintains adequate detection accuracy while significantly reducing system cost and making the technology economically viable for mass production
Data Source
AI summary
In order to display driving assistance images to a driver in a vehicle, visible light images are captured using a visible light camera mounted for viewing a roadway on which the vehicle travels and infrared images overlapping with the visible light images are captured using an infrared camera mounted for viewing the roadway. The visible light images are normally displayed on a display screen when a visible light brightness around the vehicle is greater than a brightness threshold. Trigger conditions are monitored which are indicative of limitations of a driver visibility when directly viewing the roadway. The trigger conditions include a driver reaction. The monitored trigger condition is classified according to a plurality of predetermined classifications which indicate an occurrence of an impairment event. The infrared images are selected for display on the display screen upon occurrence of the impairment event.