US 7,526,103 · Granted 2009-04-28
The Patent That Teaches Cars to Read Road Signs
Imagine a camera on your car's dashboard that doesn't just see the road ahead—it actually reads and understands traffic signs. This patent describes a system that snaps photos of signs, figures out what type they are (stop sign, speed limit, etc.), and extracts the actual information, like the number on a speed-limit sign. It's the brain behind modern driver-assist features that warn you when you're speeding.
The plain-English version
What it protects
The claim covers a camera system that captures forward-facing video of the road, combined with software that first identifies what kind of sign it's looking at, then reads the specific details on that sign (like numbers or text). What's protected is the specific two-step process: sign detection followed by character recognition triggered only when an interesting sign is found. Someone building a competing road-sign-reading system would need to design around this method.
Why it matters
This patent underpins a whole category of driver-assistance features that modern cars now take for granted. As vehicles have become smarter, the ability to automatically detect and interpret traffic signs became essential for adaptive cruise control, speed-limit warnings, and eventual autonomous driving. Donnelly Corporation, a major supplier to automakers, patented a foundational approach that competitors in the automotive electronics space would need to license or invent around.
Real-world use
When your car's dashboard displays a notification that you're exceeding the speed limit, or when lane-departure warnings activate, this patented vision system is working behind the scenes reading the actual road signs to know what the current limit is.
Original USPTO abstract
An imaging system for a vehicle includes an imaging device having a field of view exteriorly and forward of the vehicle in its direction of travel, and an image processor operable to process the captured images in accordance with an algorithm. The algorithm comprises a sign recognition routine and a character recognition routine. The image processor processes the image data captured by the imaging device to detect signs in the field of view of the imaging device and applies the sign recognition routine to determine a sign type of the detected sign. The image processor is operable to apply the character recognition routine to the image data to determine information on the detected sign. The image processor applies the character recognition routine to the captured images in response to an output of the sign recognition routine being indicative of the detected sign being a sign type of interest.
Patent details
- Publication number
- US 7,526,103
- Filing date
- 2005-04-14
- Grant date
- 2009-04-28
- Assignee
- Donnelly Corporation
- Inventor(s)
- SCHOFIELD KENNETH, LYNAM NIALL R.
- CPC class
- G06V20/582
Want to file your own patent?
If you're dreaming up the next generation of vehicle safety features, use our free scanner to see what's already locked down in automotive vision tech.
Free patentability scan