Vehicle Camera Exposure Split for Flickering Light Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicle cameras struggle to capture images of flickering illuminated objects, such as traffic lights and LED signs, due to their short exposure times, which are inadequate for capturing the brief light pulses from these sources.
Innovation Solution
The system employs two cameras on a vehicle: a first camera with a short exposure time and no neutral density (ND) filter, and a second camera with a longer exposure time and an ND filter. The second camera's longer exposure time, typically on the order of milliseconds, allows it to capture images of flickering objects more effectively.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Illumination intensity
If the exposure time is set to a short duration (microseconds) based on ambient lighting conditions, then the camera can capture images with proper brightness and avoid overexposure, but the camera fails to capture flickering illuminated objects such as traffic lights and LED signs
Solution Approach 1:
The system divides the imaging task into two separate cameras: one camera captures images with short exposure time for general scene illumination, while the other camera captures images with long exposure time specifically for detecting flickering illuminated objects. This segmentation allows each camera to be optimized for its specific function, resolving the contradiction between capturing proper brightness and detecting illuminated objects.
Solution Approach 2:
The system dynamically switches between different exposure time settings based on the imaging needs. The first camera uses short exposure time (microseconds) for general illumination capture, while the second camera uses long exposure time (milliseconds) for illuminated object detection. This dynamic adaptation of exposure parameters allows the system to handle both requirements effectively.
2Reliability
If the exposure time is increased to capture flickering light pulses, then illuminated objects can be detected, but the captured images become overexposed and lose detail in normal lighting conditions
Solution Approach 1:
The system segments the imaging function into two specialized cameras: the first camera with short exposure time handles normal illumination capture to avoid overexposure, while the second camera with long exposure time handles illuminated object detection. This segmentation allows long exposure time to be used without causing overexposure in normal lighting conditions.
Solution Approach 2:
The system introduces an intermediary processing stage that combines images from both cameras. The processor uses the long exposure time images to detect illuminated objects and their locations, then integrates this information with the short exposure time images for final image output. This intermediary processing allows the benefits of both exposure times to be combined without the drawbacks of either alone.
3Device complexity
If a single camera is used with variable exposure time, then the system complexity is reduced, but the system cannot simultaneously optimize for both short and long exposure time requirements
Solution Approach 1:
Rather than using a single camera with complex variable exposure mechanisms, the system segments the function into two dedicated cameras, each optimized for a specific exposure time requirement. This segmentation simplifies the control logic for each individual camera while achieving the versatility of handling both short and long exposure scenarios.
Solution Approach 2:
The dual-camera system achieves multi-functionality where the first camera handles general scene capture and the second camera handles illuminated object detection. Together, they provide a universal solution that can adapt to both short and long exposure time requirements, making the overall system versatile despite the added hardware.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This configuration significantly increases the likelihood of capturing images of flickering illuminated objects, such as traffic lights and LED signs, which improves the reliability of object identification and enables more accurate control of the vehicle in autonomous driving mode.
Implementation Method 1
a second camera having a second exposure time that is greater than or equal to the first exposure time and having an ND filter
Data Source
AI summary
The technology relates to camera systems for vehicles having an autonomous driving mode. An example system includes a first camera mounted on a vehicle in order to capture images of the vehicle's environment. The first camera has a first exposure time and being without an ND filter. The system also includes a second camera mounted on the vehicle in order to capture images of the vehicle's environment and having an ND filter. The system also includes one or more processors configured to capture images using the first camera and the first exposure time, capture images using the second camera and the second exposure time, use the images captured using the second camera to identify illuminated objects, use the images captured using the first camera to identify the locations of objects, and use the identified illuminated objects and identified locations of objects to control the vehicle in an autonomous driving mode.