Real-Time Image Sequence Reversal for Triangulation Accuracy

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current location-based services face challenges in achieving accurate feature triangulation, particularly when features are small relative to the image frame, leading to large triangulation errors due to limited parallax and difficulty in feature detection.

Innovation Solution

The system dynamically reverses the chronological order of real-time image sequences captured by a vehicle's sensor to increase parallax, processing features that appear larger or closer to the image edge first, thereby improving triangulation accuracy without requiring offline data processing.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional chronological image sequence processing is used, then processing simplicity is maintained, but triangulation accuracy deteriorates due to limited parallax when features are small relative to image frame

Engineering Contradiction:

Improvetriangulation accuracyVSAvoidprocessing complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent reverses the chronological order of image sequences before processing. Instead of processing images in the order they were captured, the system reverses the sequence so that images where features appear larger and closer to image edges are processed first. This inversion increases parallax and improves triangulation accuracy for small features.

Inventive Principle:

Principle #13The other way round (Inversion)

2Productivity

If real-time processing is implemented, then processing speed is improved, but triangulation accuracy worsens due to limited parallax from small features

Engineering Contradiction:

Improveprocessing speedVSAvoidtriangulation accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The system implements real-time reversal of image sequences, allowing the processing to occur continuously without offline delays. By reversing the sequence in real-time, features that appear larger and closer to image edges are processed first, increasing parallax and improving triangulation accuracy while maintaining real-time processing capabilities.

Inventive Principle:

Principle #13The other way round (Inversion)

3Area of stationary object

If features small relative to image frame are processed, then coverage area is maximized, but feature detection difficulty increases leading to large triangulation errors

Engineering Contradiction:

Improvegeographic coverage areaVSAvoidfeature detection difficulty

Core Design Contradiction:

Area of stationary objectVSDifficulty of detecting and measuring

Solution Approach 1:

By reversing the chronological order of image sequences, the system processes images where small features appear larger and closer to image edges before processing images where they appear smaller and closer to the center. This inversion makes feature detection easier and reduces triangulation errors while maintaining wide geographic coverage.

Inventive Principle:

Principle #13The other way round (Inversion)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This approach enhances the accuracy of 3D feature triangulation in real-time or near real-time, addressing the limitations of traditional methods by increasing parallax and improving feature detection, resulting in more precise digital map data generation.

Implementation Method 1

The system dynamically reverses the chronological order of real-time image sequences captured by a vehicle's sensor to increase parallax

Methodology Applied

Scientific EffectParallax: Parallax

Data Source

PatentUS11188765B2Method and apparatus for providing real time feature triangulation

Publication Date: 2021.11.30 HERE GLOBAL BV

AI summary

An approach is provided for generating a reverse sequence or real-time streamed images for triangulation. The approach includes receiving a real-time stream of images captured by a sensor of a vehicle during a drive; extracting a sequence of two or more images from the real-time stream; reversing the sequence of the two or more images; and providing the reversed sequence of the two or more images for feature triangulation.