Augmented Vehicle Surround View with Pose Estimation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing vehicle camera systems are limited in functionality and often disabled during vehicle motion to prevent driver distraction, lacking the ability to provide augmented and interactive surround view imaging for enhanced safety and entertainment.

Innovation Solution

A system and method for generating and presenting an augmented virtual vehicle view using surround view image data from multiple cameras, incorporating pose estimation and virtual camera position data to overlay graphical elements, allowing for interactive and dynamic display of points of interest and gaming elements.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If multiple image sensors are used to provide surround view imaging, then the functionality and safety assistance are improved, but the device complexity and cost increase

Engineering Contradiction:
Improvevehicle safetyVSAvoidsystem complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent combines multiple image sensor systems (surround view cameras and additional image sensors) into a unified processing system that generates a single augmented reality display. The image processing module integrates data from multiple sources to create a composite stitched image view with overlaid graphical elements, reducing the complexity of managing separate display systems while improving safety through comprehensive environmental awareness.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The system uses a single augmented reality display interface to serve multiple functions: displaying surround view imaging, overlaying graphical elements for parking assistance, showing gaming entertainment content, and providing navigation information. This multi-functional approach improves vehicle safety and user experience without requiring separate complex display systems for each function.

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Adaptability or versatility

If cameras are enabled during vehicle motion to provide additional functions, then the versatility and entertainment capability are improved, but the risk of driver distraction increases

Engineering Contradiction:
Improvecamera functionalityVSAvoiddriver distraction
Core Design Contradiction:
Adaptability or versatilityVSObject-affected harmful factors

Solution Approach 1:

The system provides different display qualities and information types to different users based on their needs. The augmented reality display can show comprehensive surround view information to the driver when needed, while simultaneously providing entertainment content to passengers. The graphical elements and image processing are optimized for specific viewing contexts, allowing versatile camera functionality without uniformly exposing all users to potentially distracting information.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The system dynamically adjusts the display content and graphical elements based on vehicle motion state, driver attention level, and user preferences. When the vehicle is in motion, the system can reduce or modify certain graphical overlays to minimize driver distraction while maintaining essential safety information. The augmented reality module adapts the presentation of camera feeds and graphical elements in real-time based on driving conditions.

Inventive Principle:
Principle #15Dynamics

3Loss of information

If augmented reality elements are overlaid on the stitched image view, then the information density and user experience are improved, but the processing complexity and computational requirements increase

Engineering Contradiction:
Improveinformation deliveryVSAvoidprocessing complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The system performs preliminary processing of image data from multiple sensors to create the stitched image view before overlaying graphical elements. The image processing module pre-aligns and merges images from different camera angles, and pre-calculates the positioning of graphical elements based on the vehicle's pose estimation. This preliminary processing reduces the computational burden during real-time rendering by preparing data structures and coordinate transformations in advance.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent introduces an augmented reality module as an intermediary layer between the raw image sensor data and the final display output. This module handles the complex tasks of pose estimation, graphical element generation, and overlay composition, isolating the computational complexity from the core image processing functions. The intermediary module manages the integration of multiple data streams (surround view images, pose data, graphical elements) without requiring fundamental changes to the underlying sensor or display systems.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentUS11094132B2System and method for presentation and control of augmented vehicle surround views
Publication Date: 2021.08.17 HARMAN INT IND INC
  • US11094132B2 patent drawing
  • US11094132B2 patent drawing
  • US11094132B2 patent drawing

AI summary

Methods and systems for presentation and control of an augmented virtual vehicle view with surround view imaging, that include generating a stitched image view based on surround view image data for a vehicle and generating a pose estimation for the vehicle, wherein the pose estimation provides a vehicle position and a vehicle orientation relative to the stitched image view. In one or more examples, the methods and systems include augmenting the stitched image view to include one or more graphical elements based on the pose estimation for the vehicle, presenting a graphical display of the stitched image view including the one or more graphical elements and a vehicle avatar. Further, in at least one example, the methods and systems may include detecting position commands for a position of the vehicle avatar within the graphical display and updating the avatar position and iconography in response to the position commands.