3D Object Detection Device Speed-Based Lens Contamination Filtering

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing three-dimensional object detection systems face challenges in accurately identifying adjacent vehicles when mud or foreign matter is deposited on the camera lens, particularly in low luminance conditions, leading to errant detection of such debris as vehicles.

Innovation Solution

The system compares the travel speed of detected objects with the host vehicle's speed and modifies detection thresholds to suppress assessment of objects as adjacent vehicles when their speed is equal to or less than the host vehicle's speed or within a prescribed difference, preventing misidentification of mud or foreign matter as vehicles.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If detection sensitivity is increased to detect adjacent vehicles in low luminance conditions, then detection capability is improved, but false detection of foreign matter on the lens increases

Engineering Contradiction:
Improvedetection capabilityVSAvoidfalse detection rate
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The system changes detection parameters dynamically based on luminance conditions and speed comparisons. In low luminance conditions, the system adjusts detection thresholds and uses speed-based filtering to distinguish between stationary foreign matter on the lens and moving adjacent vehicles, thereby maintaining detection capability while reducing false detections

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The system uses feedback from multiple detection cycles to improve reliability. By continuously monitoring detection results, luminance levels, and speed data, the system adjusts its detection criteria to reduce false positives from lens contamination while maintaining sensitivity to actual vehicles

Inventive Principle:
Principle #23Feedback

2Measurement precision

If detection threshold is lowered to identify adjacent vehicles in low light, then detection accuracy is improved, but misidentification of foreign matter as vehicles increases

Engineering Contradiction:
Improvedetection accuracyVSAvoiderrant detection
Core Design Contradiction:
Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The system dynamically adjusts detection parameters including threshold values based on luminance conditions and speed comparisons. When foreign matter is detected but speed comparison indicates it matches host vehicle speed (suggesting lens contamination), the system modifies detection thresholds to suppress false identification while maintaining accuracy for actual vehicles

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The system introduces speed comparison as an intermediary criterion between image detection and final vehicle identification. This intermediate check helps distinguish between actual vehicles (which may have different speed profiles) and foreign matter on the lens (which moves with the host vehicle), thereby reducing errant detection

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP2879385B1Three-dimensional object detection device and three-dimensional object detection method
Publication Date: 2017.04.26 NISSAN MOTOR CO LTD
  • EP2879385B1 patent drawingFigure 1
  • EP2879385B1 patent drawingFigure 2
  • EP2879385B1 patent drawingFigure 3

AI summary

A three-dimensional object detection device characterized in being provided with a three-dimensional object detection means (33) for detecting a three-dimensional object based on captured images, and calculating the traveling speed of the three-dimensional object, a light source detection means (35) for detecting a light source corresponding to a headlight of another vehicle, and a control means (37) which, in the event that a light source corresponding to a headlight of another vehicle has not been detected, and additionally the traveling speed of the three-dimensional object is equal to or less than the traveling speed of the host vehicle, or the difference between the traveling speed of the three-dimensional object and the traveling speed of the host vehicle is less than a predetermined value, suppresses detection of the three-dimensional object based on differential waveform information.