Lane Determination Using Image and Position Data

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for determining a vehicle's lane location are costly and require high-precision maps or sensor modules, which limits their applicability and accuracy.

Innovation Solution

A method that determines the lane location by combining image lane information from lane line images with actual lane information from existing data, using image recognition to identify lane types and associate them with actual lane positions, thereby reducing the need for costly sensors and high-precision maps.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If high-precision positioning and high-precision maps are used to determine lane location, then the accuracy of lane determination is improved, but the cost and complexity of the system increases

Engineering Contradiction:
Improvelane determination accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent uses image lane information from camera images as a copy or representation of actual lane information. By recognizing lane lines in images and mapping them to actual lane positions, the system achieves accurate lane determination without requiring expensive high-precision maps or sensors, thus resolving the contradiction between accuracy and complexity

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent introduces image lane information as an intermediary between the vehicle's positioning system and the actual lane determination. The image processing module extracts lane line information from images, which then serves as a bridge to determine the vehicle's actual lane position, avoiding the need for direct high-precision mapping

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If sensor modules are laid in the road to sense lane location, then the accuracy of lane determination is improved, but the cost and infrastructure requirements increase

Engineering Contradiction:
Improvelane determination accuracyVSAvoidimplementation cost
Core Design Contradiction:
Measurement precisionVSEase of manufacture

Solution Approach 1:

The system uses the vehicle's own image acquisition device to capture and process lane line images for determining lane position. This self-service approach eliminates the need for external sensor modules to be laid in the road, reducing infrastructure costs while maintaining accurate lane determination through image recognition and processing

Inventive Principle:
Principle #25Self-service

3Ease of manufacture

If image recognition is used to determine lane information, then the cost is reduced, but the measurement precision may be affected

Engineering Contradiction:
Improvesystem costVSAvoidlane information accuracy
Core Design Contradiction:
Ease of manufactureVSMeasurement precision

Solution Approach 1:

The patent merges image lane information with actual lane information through a mapping process. The image processing module recognizes lane lines and determines their positions, which are then combined with the vehicle's positioning data to accurately determine the actual lane position, maintaining precision while using cost-effective image recognition

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentUS11867513B2Method, apparatus, device and storage medium for determining lane where vehicle located
Publication Date: 2024.01.09 APOLLO INTELLIGENT CONNECTIVITY (BEIJING) TECH CO LTD
  • US11867513B2 patent drawing
  • US11867513B2 patent drawing
  • US11867513B2 patent drawing

AI summary

Embodiments of the present disclosure provide a method, apparatus, device, and storage medium for determining a lane where a vehicle is located. In the method, the image lane information of the position where the vehicle is located is determined from a lane line image; actual lane information of a position where the vehicle is located is acquired from existing lane information according to the positioning information of the vehicle; and an actual lane where the vehicle is located is determined based on the image lane information and the actual lane information.