Clear path detection through road modeling

A change analysis and smooth technology, applied in image analysis, traffic control system, road network navigator, etc., can solve problems such as poor effectiveness, large processing capacity, and bulkiness

Active Publication Date: 2011-02-02
GM GLOBAL TECH OPERATIONS LLC
View PDF7 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although this method is effective in identifying clear paths, it requires a lot of processing power, for example, to distinguish and classify different objects in the visual image, such as distinguishing a tree on the side of the road from a pedestrian walking towards the curb
These methods are slow or ineffective when dealing with complex situations, or require bulky and expensive equipment to provide the necessary processing power

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Clear path detection through road modeling
  • Clear path detection through road modeling
  • Clear path detection through road modeling

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0057] After filtering, feature extraction is performed on the selected patch using a feature extraction algorithm (208). The feature extraction algorithm can analyze the selected patch to obtain a predetermined feature and / or shape, where the predetermined feature includes, for example, edges, corners, and stains; and the shape includes, for example, circles, ellipses, and lines. It should be recognized that some features are meaningful while others are not. The process of selecting features can be used to identify the best set of features for analysis. The classifier training algorithm analyzes each feature and assigns a probability value (210). As mentioned above, the classifier or logic used in the derivation of the probability value is initially trained offline. Based on fuzzy logic, neural networks, or other learning mechanisms known in the art, training can optionally continue in the vehicle. These trained classifiers perform probability analysis based on the extracted...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to clear path detection through road modeling. The method involves monitoring an image from a camera, and analyzing the image through clear path detection analysis to determine a clear path of travel within the image. An area in front of a vehicle is analyzed by utilizing a topographical variation analysis to determine a flat surface upon which the vehicle is made to travel.The clear path of travel and determined flat surface are combined to describe an enhanced clear path of travel. The enhanced clear path of travel is utilized to navigate the vehicle.

Description

[0001] This application is a partial continuation of the U.S. application with application number 12 / 581,659 filed on October 19, 2009, and the previous application is a partial continuation of the U.S. application with application number 12 / 474,594 filed on May 29, 2009 Application, and the aforementioned earlier application is a partial continuation application of the U.S. application with application number 12 / 108,581 filed on April 24, 2008. The U.S. application with application number 12 / 581,659 filed on October 19, 2009 claims priority to the U.S. provisional application with application number 61 / 215,745 filed on May 8, 2009. The US application with application number 12 / 581,659, the US application with application number 12 / 474,594, the US application with application number 12 / 108,581, and the US provisional application with application number 61 / 215,745 are incorporated by reference into this application. Technical field [0002] The invention relates to automatic or se...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06T7/00G01C21/34
CPCG06K9/00798B60W30/00B60W2420/42G08G1/16G08G1/165G08G1/166G06V20/588B60W2420/403
Inventor W·张S·M·奈克
Owner GM GLOBAL TECH OPERATIONS LLC
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap