Vehicle Vision System Using Gray Level Transition Sensitive Pixels
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current vehicle vision systems using imaging sensors face limitations in detecting moving objects and providing accurate distance information, especially in environments with flickering lights, due to their frame-based image capture and limited dynamic range.
Innovation Solution
A vehicle vision system employing a combination of image vision pixels (IV pixels) and dynamic vision sensor (DVS) pixels, which capture gray level transitions, allowing for event-based detection and processing of motion, along with a LASER for ranging detection, to enhance object detection and distance measurement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If frame-based image capture is used, then complete scene information is captured, but motion detection accuracy and dynamic range are limited
Solution Approach 1:
The pixel array is segmented into two distinct types: image vision (IV) pixels for capturing complete scene information and dynamic vision sensor (DVS) pixels for detecting gray level transitions. This segmentation allows each pixel type to specialize in its optimal function, with DVS pixels providing superior motion detection accuracy through event-based detection while IV pixels maintain comprehensive scene coverage.
Solution Approach 2:
The system transitions from static frame-based capture to dynamic event-based detection by incorporating DVS pixels that continuously monitor and report gray level transitions. This dynamic approach allows the system to adapt to changing scene conditions in real-time, capturing motion events as they occur rather than at fixed intervals, thereby improving motion detection accuracy and dynamic range.
2Measurement precision
If event-based detection is used, then motion detection accuracy improves, but complete scene information may be missed
Solution Approach 1:
The system merges IV pixels and DVS pixels into a single integrated pixel array, allowing both complete scene information capture and event-based motion detection to occur simultaneously. The IV pixels provide comprehensive scene coverage while the DVS pixels detect gray level transitions, and both data streams are processed together to produce a complete picture of the scene including both static and dynamic elements.
3Measurement precision
If single sensor type is used, then device complexity is reduced, but detection accuracy and dynamic range are limited
Solution Approach 1:
Different regions of the pixel array have different qualities and functions: IV pixels are optimized for capturing complete scene information with high spatial resolution, while DVS pixels are optimized for detecting gray level transitions with high temporal resolution. This local differentiation of pixel qualities allows the system to achieve superior detection accuracy and dynamic range by placing the right type of pixel in the right location for its optimal performance.
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
The system effectively detects moving objects and provides accurate distance information, reducing aliasing effects and improving dynamic range, enabling better object detection and scene understanding, even in challenging lighting conditions.
Implementation Method 1
along with a LASER for ranging detection
Implementation Method 2
event-based gray level transition sensitive pixels or dynamic vision sensor (DVS) pixels
Data Source
AI summary
A vision system of a vehicle includes at least one camera disposed at a vehicle and having a field of view exterior of the vehicle. The camera has at least one pixelated imaging array having a plurality of photosensing elements. The pixelated imaging array includes a plurality of event-based gray level transition sensitive photosensing elements. A processor is operable to process data captured by the camera and, responsive to processing of captured data, the processor is operable to detect objects present in the field of view of the camera. The pixelated imaging array may include a first imaging array having visible light sensitive photosensing elements and a second imaging array having the plurality of event-based gray level transition sensitive photosensing elements.