18074204. Method to Detect Lane Segments for Creating High Definition Maps simplified abstract (Ford Global Technologies, LLC)
Contents
Method to Detect Lane Segments for Creating High Definition Maps
Organization Name
Inventor(s)
Willibald Brems of Ingolstadt (DE)
Francesco Ferroni of Munich (DE)
Method to Detect Lane Segments for Creating High Definition Maps - A simplified explanation of the abstract
This abstract first appeared for US patent application 18074204 titled 'Method to Detect Lane Segments for Creating High Definition Maps
The patent application describes a system, method, and computer program product for detecting lane segments in an image to create high-definition (HD) maps using a neural network.
- Neural network classifies pixels in an image as part of a driving lane.
- Labeled pixels form boundary lines of the driving lane.
- Line drawings are constructed based on labeled pixels to create lane segments.
- Potential Applications:
This technology can be used in autonomous vehicles for accurate mapping of lanes and navigation systems.
- Problems Solved:
This technology addresses the challenge of accurately detecting and mapping lane segments in images for creating HD maps.
- Benefits:
- Improved accuracy in lane detection - Enhanced mapping capabilities for autonomous vehicles - Increased safety and efficiency in navigation systems
- Commercial Applications:
The technology can be utilized by companies developing autonomous vehicles, mapping services, and navigation software providers.
- Prior Art:
Prior art related to this technology may include image processing algorithms for lane detection and mapping.
- Frequently Updated Research:
Research on improving neural network algorithms for more precise lane segment detection may be relevant to this technology.
- Questions about Lane Segment Detection:
1. How does the neural network classify pixels in the image? 2. What are the key benefits of using this technology in autonomous vehicles?
Original Abstract Submitted
Disclosed herein are system, method, and computer program product embodiments for detecting lane segments in an image for creating high-definition (HD) maps. A neural network can be used to classify a pixel of an image of a location as belonging to a driving lane. If the pixel belongs to a first boundary line of the driving lane, it is labeled accordingly. Based on the labeled pixel and one or more additional labeled pixels as part of the first boundary line of the driving lane, a first line drawing of the first boundary line of the driving lane is constructed. A lane segment based on a combination of the first line drawing of the first boundary line of the driving lane and a second line drawing of a second boundary line of the driving lane can be created.
