Cut-In Vehicle Detection for Camera-Radar Driver Assistance

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing driver assistance systems struggle to effectively avoid collisions with surrounding objects, particularly those cutting into the travel lane at close ranges, due to limited field of view and sensing capabilities.

Innovation Solution

A driver assistance system equipped with a camera and radar sensors that acquire external image and sensing data to determine a nearby vehicle's cut-in area, velocity, and acceleration, allowing for control of the vehicle's braking and steering systems to prevent collisions by identifying potential lane intrusions and calculating necessary avoidance maneuvers.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the field of view of sensors is increased to detect nearby vehicles cutting in at close ranges, then collision avoidance capability is improved, but device complexity and cost increase

Engineering Contradiction:
Improvecollision avoidance capabilityVSAvoidsensor system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent combines camera and radar sensors into an integrated sensing system that shares processing resources and data fusion algorithms. This merging approach enables comprehensive collision avoidance detection without proportionally increasing system complexity, as the combined system leverages complementary strengths of each sensor type.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The sensor system is designed to perform multiple functions: detecting vehicles in adjacent lanes, identifying cut-in maneuvers, measuring velocity and acceleration, and determining cut-in areas. This multi-functionality reduces the need for separate specialized sensors, thereby improving collision avoidance capability without linearly increasing device complexity.

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

2Measurement precision

If multiple sensors (camera and radar) are used to accurately determine nearby vehicle parameters, then measurement precision is improved, but device complexity increases

Engineering Contradiction:
Improvenearby vehicle parameter detection accuracyVSAvoidsensor system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent introduces a controller as an intermediary that fuses data from camera and radar sensors. This mediator processes and integrates information from both sensors to accurately determine nearby vehicle parameters including velocity, acceleration, and cut-in area, achieving high measurement precision while managing system complexity through centralized processing.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The sensing system uses a composite approach by combining different sensor types (camera for visual information, radar for range and velocity data) to create a more accurate and reliable detection system. This composite sensing strategy improves measurement precision by leveraging the complementary strengths of each sensor modality.

Inventive Principle:
Principle #40Composite materials

3Reliability

If the system processes detailed image data and radar data to calculate cut-in area and velocity, then collision avoidance reliability is improved, but processing time and computational load increase

Engineering Contradiction:
Improvecollision avoidance reliabilityVSAvoidprocessing time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary processing of image and radar data to identify potential cut-in scenarios before full collision avoidance calculations are required. By pre-processing data to detect vehicles in adjacent lanes and calculate preliminary parameters like velocity and acceleration, the system reduces computational load during critical decision-making moments, maintaining high reliability while minimizing processing time.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3690481B1Driver assistance system and control method thereof
Publication Date: 2023.11.29 HL KLEMOVE CORP
  • EP3690481B1 patent drawingFigure 1
  • EP3690481B1 patent drawingFigure 2
  • EP3690481B1 patent drawingFigure 3

AI summary

Disclosed are a driver assistance system for a vehicle, the driver assistance system comprising: a camera disposed on the vehicle to have a field of view of an outside of the vehicle, and configured to acquire external image data; a radar disposed on the vehicle to have a field of sensing of an outside of the vehicle, and configured to acquire radar data; and a controller including a processor configured to process the image data and the radar data, determine a cut-in area of a nearby vehicle on the basis of the image data acquired by the camera, determine a target vehicle on the basis of the determined cut-in area, and control at least one of a braking device or a steering device of the vehicle to avoid a collision with the target vehicle.