Roadside Object Detection Using Adaptive Height Thresholds

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The road model used in roadside object detection systems can decrease in accuracy, leading to failures in accurate detection of roadside objects.

Innovation Solution

A height-related threshold is determined based on the positional relationship between the host vehicle and roadside object candidates to identify potential roadside objects, adjusting the detection criteria according to distance and vehicle conditions such as speed and acceleration.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a fixed road model is used for roadside object detection, then the detection process is simple and fast, but the detection accuracy decreases when road conditions vary

Engineering Contradiction:
Improveroadside object detection accuracyVSAvoiddetection system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies dynamics by making the detection threshold adaptive rather than fixed. The height-related threshold is dynamically adjusted based on the positional relationship between the host vehicle and roadside object candidates, allowing the system to adapt to varying road conditions and maintain high detection accuracy without requiring an overly complex system

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The patent changes the parameter of the detection threshold based on positional relationships. By varying the height-related threshold according to distance and vehicle conditions (speed and acceleration), the system optimizes detection accuracy for different scenarios without fundamentally changing the detection architecture

Inventive Principle:
Principle #35Parameter changes

2Reliability

If the detection threshold is lowered to detect more objects, then false negatives decrease, but false positives increase

Engineering Contradiction:
Improvedetection reliabilityVSAvoiddetection accuracy
Core Design Contradiction:
ReliabilityVSMeasurement precision

Solution Approach 1:

The patent applies local quality by setting different detection thresholds for different spatial locations and vehicle conditions. Instead of using a uniform threshold, the system adjusts the height-related threshold based on the specific positional relationship between the vehicle and detected candidates, ensuring optimal detection accuracy for each local context while maintaining overall reliability

Inventive Principle:
Principle #3Local quality

3Measurement precision

If the detection threshold is raised to reduce false positives, then detection precision improves, but false negatives increase

Engineering Contradiction:
Improvedetection precisionVSAvoiddetection completeness
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The system dynamically adjusts the detection threshold based on vehicle conditions such as speed and acceleration. When the vehicle is stationary or moving slowly, a higher threshold can be used to reduce false positives. When the vehicle is moving quickly, the threshold is adjusted to prevent false negatives, thus maintaining both precision and reliability across different operating conditions

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP3667612B1Roadside object detection device, roadside object detection method, and roadside object detection system
Publication Date: 2024.08.28 ASTEMO LTD
  • EP3667612B1 patent drawingFigure 1
  • EP3667612B1 patent drawingFigure 2
  • EP3667612B1 patent drawingFigure 3

AI summary

The roadside object detection device, roadside object detection method, and roadside object detection system according to the present invention make it possible to accurately detect roadside objects by: determining a first feature value regarding positional relationship between a host vehicle and a roadside object candidate and a second feature value regarding a height of the roadside object candidate, based on external environment information acquired by an external environment recognition unit; determining a height-related threshold for identifying the roadside object candidate as a roadside object, based on the first feature value; and identifying the roadside object candidate as a roadside object when the second feature value exceeds the threshold.