Driver Assistance Object Detection Performance Estimation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing driver assisting systems for motor vehicles face reliability issues due to varying external conditions, such as temperature and humidity, which can lead to misleading or suboptimal control, as the driver is unaware of the current object detection performance.

Innovation Solution

A driver assisting system that estimates the object detection performance using tracking and classification means, providing actionable feedback to the driver through indicators or system adjustments based on detected performance metrics like missed detections and detection distance, ensuring the driver's vigilance is maintained and system reliability is managed.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the driver assisting system operates under unfavourable external conditions (close to 37°C temperature, rain, humidity), then the system continues to provide driver assistance functions, but the object detection performance decreases leading to misleading detection results

Engineering Contradiction:
Improveobject detection performanceVSAvoidtemperature, rain, humidity
Core Design Contradiction:
ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The system continuously monitors detection performance metrics (number of detected objects, confidence levels, false alarm rates) and provides feedback to the driver through the driver assisting means. This feedback loop allows the driver to be aware of reduced detection performance under unfavourable conditions and adjust their reliance on the system accordingly, preventing misleading decisions while maintaining system operation.

Inventive Principle:
Principle #23Feedback

2Ease of operation

If the driver relies on the driver assistant system without knowing the current object detection performance, then the system operates automatically, but the driver may have incorrect expectations about system reliability

Engineering Contradiction:
Improveautomatic system operationVSAvoiddriver awareness of detection performance
Core Design Contradiction:
Ease of operationVSLoss of information

Solution Approach 1:

The system provides real-time information about detection performance to the driver through the driver assisting means. This feedback mechanism bridges the information gap, allowing the driver to understand the current reliability state of the system without interrupting automatic operation. The driver can make informed decisions about whether to trust or override the system based on the provided performance metrics.

Inventive Principle:
Principle #23Feedback

3Device complexity

If the system provides continuous driver assistance functions without performance monitoring, then the system maintains simple operation, but the driver may be misled by low-reliability detection results

Engineering Contradiction:
Improvesystem operation simplicityVSAvoiddetection result accuracy
Core Design Contradiction:
Device complexityVSReliability

Solution Approach 1:

The system monitors detection performance metrics and provides feedback to the driver through the driver assisting means. This feedback mechanism does not significantly increase operational complexity while substantially improving reliability by alerting the driver to poor detection conditions. The system maintains continuous operation while providing transparency about detection quality, preventing driver misuse of unreliable information.

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP2385482B1A driver assisting system and method for a motor vehicle
Publication Date: 2016.04.20 AUTOLIV DEV AB
  • EP2385482B1 patent drawingFigure 1
  • EP2385482B1 patent drawingFigure 2~3

AI summary

A driver assisting system (10) for a motor vehicle comprises an imaging means (11) adapted to record images of a region surrounding the motor vehicle, an object detection means (15) for detecting objects in the recorded images by image processing, an object processing means (16, 17) for applying further processing to objects detected in the recorded images, and a driver assisting means (18) controlled depending on the result of said object detection and object processing. The driver assisting system (10) comprises a detection performance estimating means (20) adapted to provide an estimation of the detection performance of said object detection means (15) using a result from said object processing means (16, 17).