Patch Smoothing for Clear Path Detection in Autonomous Vehicles

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current autonomous driving systems face challenges in efficiently processing complex road conditions to identify a clear path for vehicle navigation, requiring significant computational power and often bulky equipment to distinguish between various objects on the road.

Innovation Solution

The method involves analyzing images from a camera system using patch-based clear path detection, where patches are identified, smoothed, and validated to define a clear path for vehicle navigation, reducing the need for individual object classification and processing power by focusing on the likelihood of a path being clear based on visual cues from the ground and surrounding objects.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional object recognition methods are used to identify clear path, then object classification accuracy is improved, but processing time increases and computational power requirements increase

Engineering Contradiction:
Improveobject classification accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The image is divided into multiple patches that are processed independently and in parallel. Each patch is analyzed for clear path indication rather than processing the entire image as a single unit, which reduces processing time while maintaining accuracy through localized analysis.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent extracts only the relevant clear path indication information from patches rather than performing full object recognition and classification. By taking out only the necessary clear path data from each patch, the system avoids the computational overhead of complete object identification while still achieving accurate clear path detection.

Inventive Principle:
Principle #2Taking out (Extraction)

2Reliability

If comprehensive object analysis is performed to ensure accurate clear path identification, then detection reliability is improved, but device complexity increases

Engineering Contradiction:
Improveclear path detection reliabilityVSAvoidprocessing system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system extracts only the clear path indication from each patch rather than performing comprehensive object analysis. This extraction approach maintains detection reliability by focusing on the essential clear path information while significantly reducing device complexity by eliminating unnecessary object classification components.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

Instead of identifying objects and determining whether they block the path, the patent inverts the approach by directly analyzing whether each patch indicates a clear path. This inversion simplifies the system complexity while maintaining or improving reliability by focusing directly on the clear path determination.

Inventive Principle:
Principle #13The other way round (Inversion)

3Measurement precision

If detailed object recognition is performed to distinguish between different road objects, then detection precision is improved, but processing speed decreases

Engineering Contradiction:
Improveobject detection precisionVSAvoidprocessing speed
Core Design Contradiction:
Measurement precisionVSSpeed

Solution Approach 1:

The image is segmented into multiple patches that can be processed independently and in parallel, increasing processing speed. Each patch analysis focuses on clear path indication rather than detailed object recognition, maintaining sufficient detection precision for clear path determination while dramatically improving processing throughput.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent performs partial object analysis by focusing only on clear path indication within patches rather than complete object recognition. This partial action approach achieves sufficient detection precision for navigation purposes while significantly improving processing speed by avoiding unnecessary detailed classification.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS8890951B2Clear path detection with patch smoothing approach
Publication Date: 2014.11.18 GM GLOBAL TECHNOLOGY OPERATIONS LLC
  • US8890951B2 patent drawing
  • US8890951B2 patent drawing
  • US8890951B2 patent drawing

AI summary

A method for detecting a clear path of travel for a vehicle utilizing analysis of an image generated by a camera device located upon the vehicle includes monitoring the image, identifying through patch-based clear path detection analysis of the image a first patch within the image that indicates a not clear path, analyzing the first patch through patch smoothing, invalidating the first patch based upon the analyzing the first patch through patch smoothing, utilizing the invalidated first patch to define a clear path of travel for the vehicle, and utilizing the clear path of travel to navigate the vehicle.