Turn Signal Detection Using Spatiotemporal Vision Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems struggle to accurately detect turn signal indicators in vehicles, particularly in autonomous driving scenarios, due to challenges in distinguishing between turn signals and other bright objects like sunlight glare.
Innovation Solution
A method and system that utilizes an imaging system with short exposure time imaging and oscillation analysis of pixel intensity to identify turn signal indicators by calculating oscillations between 0.75 and 2.5 Hz, combined with color analysis to differentiate between turn signals and other bright objects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Illumination intensity
If traditional imaging systems with long exposure time are used, then more light is captured and images are brighter, but turn signal indicators cannot be distinguished from other bright objects like sunlight glare
Solution Approach 1:
The system uses short exposure time imaging to capture periodic oscillations of turn signal indicators (0.75-2.5 Hz blinking pattern). By capturing multiple images at different time points and analyzing the temporal oscillation pattern, the system can distinguish turn signals from static bright objects like sunlight glare, thereby maintaining detection accuracy while using short exposure times.
Solution Approach 2:
The system transitions from static image capture to dynamic temporal analysis. By capturing a sequence of images and analyzing the oscillation pattern over time, the system exploits the dynamic blinking characteristic of turn signals to achieve accurate detection without requiring long exposure times that would cause overexposure.
2Measurement precision
If short exposure time imaging is used, then turn signal oscillations can be captured, but the overall image brightness decreases
Solution Approach 1:
The system captures multiple copies (sequential images) with short exposure times and processes them collectively through temporal analysis. By analyzing the oscillation pattern across multiple image copies, the system achieves accurate turn signal detection while maintaining short exposure times, compensating for the reduced brightness in individual images through statistical and temporal processing.
3Device complexity
If color analysis alone is used to identify turn signals, then processing is simpler, but accuracy decreases due to inability to distinguish from other colored objects
Solution Approach 1:
The system merges multiple detection approaches: color analysis (identifying yellow/amber hues) is combined with temporal oscillation analysis (0.75-2.5 Hz blinking pattern detection). This combination allows the system to distinguish turn signals from other colored objects that may not exhibit the characteristic oscillation pattern, thereby improving accuracy while maintaining reasonable processing complexity through integrated multi-feature analysis.
Data Source
AI summary
An autonomous vehicle is configured to detect an active turn signal indicator on another vehicle. An image-capture device of the autonomous vehicle captures an image of a field of view of the autonomous vehicle. The autonomous vehicle captures the image with a short exposure to emphasize objects having brightness above a threshold. Additionally, a bounding area for a second vehicle located within the image is determined. The autonomous vehicle identifies a group of pixels within the bounding area based on a first color of the group of pixels. The autonomous vehicle also calculates an oscillation of an intensity of the group of pixels. Based on the oscillation of the intensity, the autonomous vehicle determines a likelihood that the second vehicle has a first active turn signal. Additionally, the autonomous vehicle is controlled based at least on the likelihood that the second vehicle has a first active turn signal.