Radar–Image Object Matching for Stationary Vehicle Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing traffic control systems using radar sensors face challenges in accurately extracting signals from stationary vehicles due to ground reflection, leading to limitations in vehicle shape analysis and object classification, while image sensor integration introduces accuracy issues from camera distortion and road surface curvature.

Innovation Solution

An object detection apparatus and method utilizing both radar and image sensors to match objects, generating a lookup table based on coordinated data from both sensors to complement sensing results, enhancing accuracy and reliability through linear regression and homography.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If radar sensors are used for detecting objects, then detection of moving objects with speed and distance information is improved, but detection of stationary vehicles is worsened due to ground reflection

Engineering Contradiction:
Improvedetection accuracyVSAvoidstationary vehicle detection reliability
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The patent combines radar sensor data with image sensor data to create a complementary detection system. The radar provides speed and distance information for moving objects, while the image sensor captures stationary vehicles that radar misses due to ground reflection. By merging these two sensing modalities, the system achieves both motion detection accuracy and stationary object reliability.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent introduces an intermediary processing system that matches radar-detected objects with image sensor objects. This intermediary matching process resolves the contradiction by using image data to supplement radar data for stationary vehicles, while using radar data to enhance motion information for moving objects detected by the image sensor.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Adaptability or versatility

If image sensors are used in addition to radar sensors, then object classification capability is improved, but accuracy is worsened due to camera distortion and road surface curvature

Engineering Contradiction:
Improveobject classification capabilityVSAvoiddetection accuracy
Core Design Contradiction:
Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The patent introduces an intermediary lookup table that maps image sensor coordinates to radar sensor coordinates. This intermediary structure allows the system to correct for camera distortion and road surface curvature effects by referencing pre-established correspondence relationships, thereby maintaining classification versatility while improving measurement precision.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent changes the coordinate system parameters by establishing a lookup table that transforms image sensor coordinates into radar sensor coordinates. This parameter transformation allows the system to compensate for optical distortion and geometric curvature effects, maintaining accurate object classification while correcting measurement precision issues.

Inventive Principle:
Principle #35Parameter changes

3Loss of information

If radar and image sensors are integrated, then comprehensive object information is improved, but system complexity is worsened

Engineering Contradiction:
Improveobject information completenessVSAvoidsensor integration complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The patent segments the sensor integration process into distinct functional modules: radar sensing unit, image sensing unit, object matching unit, and lookup table management unit. This segmentation allows comprehensive object information gathering while managing system complexity through modular architecture, where each unit performs a specific function and can be independently optimized or replaced.

Inventive Principle:
Principle #1Segmentation

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

Improves object detection accuracy by resolving issues with ground reflection and camera distortion, enabling reliable object classification and size determination, and addressing misdetections of large vehicles and vulnerable road users.

Implementation Method 1

radar sensors which are excellent for detecting vehicle speed, distance, and angle

Methodology Applied
Scientific EffectRadar: Radar

Implementation Method 2

image sensors in addition to radar sensors for road and traffic control

Methodology Applied
Scientific EffectPhotography: Photography

Data Source

PatentEP4624992A1Apparatus, method and computer program for detecting object by using radar sensor and image sensor
Publication Date: 2025.10.01 BITSENSING INC
  • EP4624992A1 patent drawingFigure 1~2A
  • EP4624992A1 patent drawingFigure 2B~2C
  • EP4624992A1 patent drawingFigure 3

AI summary

An apparatus for detecting an object using a radar sensor and an image sensor includes an object sensing unit configured to: sense a first object through the radar sensor installed to sense a target road and sense a second object through the image sensor installed to sense the target road; an object matching unit configured to match the first object with the second object; a lookup table management unit configured to generate a lookup table for the target road based on the first object and the second object which are matched with each other; and a complementation unit configured to complement a sensing result from the radar sensor or a sensing result from the image sensor based on the generated lookup table.