Vehicle Multi-Camera Subject Localization Using Road Lines

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing electronic devices struggle to accurately obtain and process location information of multiple subjects around a vehicle using a limited number of cameras, leading to incomplete or inaccurate spatial awareness.

Innovation Solution

An electronic device equipped with multiple cameras, including front, left, right, and rear cameras, synchronizes and processes frames using neural networks to identify and calibrate subjects, providing comprehensive spatial awareness through a top-view image generation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If multiple cameras are used to capture subjects around the vehicle, then spatial awareness and measurement precision are improved, but device complexity increases

Engineering Contradiction:
Improvelocation information accuracyVSAvoidcamera system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system divides the surrounding space into multiple zones (front, rear, left, right) and assigns dedicated cameras to each zone. This segmentation allows precise location measurement in each direction while managing overall system complexity through modular camera placement and independent processing channels.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system transitions from 2D image data to 3D spatial awareness by using multiple cameras at different positions and angles. Through coordinate transformation and calibration, the system reconstructs three-dimensional location information from two-dimensional camera images, enhancing spatial measurement precision.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Loss of information

If multiple cameras are used to obtain comprehensive spatial information, then spatial awareness is improved, but processing time and computational resources increase

Engineering Contradiction:
Improvespatial information completenessVSAvoidprocessing time
Core Design Contradiction:
Loss of informationVSLoss of time

Solution Approach 1:

The system performs preliminary calibration of camera coordinates and intrinsic parameters before actual operation. By pre-establishing the geometric relationships and transformation matrices between multiple cameras, the system reduces computational burden during real-time processing, thereby decreasing processing time while maintaining complete spatial information.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system uses a unified coordinate system and processing framework that handles data from all cameras simultaneously. This multi-functional approach allows the same processing pipeline to handle front, rear, left, and right camera data, improving processing efficiency while maintaining comprehensive spatial awareness.

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

3Area of stationary object

If cameras are positioned at front, left, right, and rear of the vehicle, then coverage area is improved, but device complexity and calibration difficulty increase

Engineering Contradiction:
Improvesurrounding space coverageVSAvoidcamera arrangement complexity
Core Design Contradiction:
Area of stationary objectVSDevice complexity

Solution Approach 1:

The surrounding space is segmented into four distinct directional zones (front, rear, left, right), with one camera assigned to each zone. This segmentation achieves comprehensive 360-degree coverage while simplifying the calibration process by treating each camera's field of view as an independent zone with standardized coordinate transformations.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system uses coordinate system transformation to unify the four spatially distributed cameras into a single three-dimensional reference frame. By establishing transformation relationships between camera coordinates and vehicle body coordinates, the system achieves comprehensive coverage while managing calibration complexity through mathematical modeling.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Data Source

PatentEP4207102B1Electronic device, method, and computer readable storage medium for obtaining location information of at least one subject by using plurality of cameras
Publication Date: 2025.10.08 THINKWARE
  • EP4207102B1 patent drawingFigure 1
  • EP4207102B1 patent drawingFigure 2A
  • EP4207102B1 patent drawingFigure 2B

AI summary

An electronic device mountable in a vehicle, include a plurality of cameras disposed toward different directions of the vehicle, a memory, and a processor. The processor obtains a plurality of frames obtained by the plurality of cameras which are synchronized with each other. The processor identifies, from the plurality of frames, one or more lines included in a road in which the vehicle is disposed. The processor identifies, from the plurality of frames, one or more subjects disposed in a space adjacent to the vehicle. The processor obtains, based on the one or more lines, information for indicating locations in the space of the one or more subjects in the space. The processor stores the obtained information in the memory.