Imaging Sensor Occlusion Detection via Compressed File Size

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing imaging sensors in autonomous vehicles face challenges in detecting occlusions, which can lead to inaccurate image capture and critical decision-making issues, often requiring redundant systems and significant processing resources.

Innovation Solution

A method and system for detecting sensor occlusion by analyzing the file size of compressed image files generated by imaging sensors, using threshold values and statistical methods to determine if an imaging sensor is occluded, allowing for real-time assessment and control adjustments.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If redundant imaging sensor systems are used to detect occlusions, then reliability improves, but device complexity increases

Engineering Contradiction:
Improveocclusion detection reliabilityVSAvoidsensor system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The imaging sensor system performs self-diagnosis by analyzing its own compressed image data to detect occlusions. The processor compresses image data and analyzes the compressed representation to determine if the sensor is occluded, eliminating the need for separate redundant sensor systems while maintaining reliability.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

Compressed image data serves as an intermediary between the raw image sensor output and the occlusion detection decision. By using compressed data as the analysis medium, the system achieves reliable occlusion detection without requiring additional physical sensor components, thus reducing device complexity.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Productivity

If image data is compressed to reduce processing load, then productivity improves, but measurement precision deteriorates

Engineering Contradiction:
Improveprocessing efficiencyVSAvoidocclusion detection precision
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The system changes the parameter of data representation from uncompressed to compressed image data for the detection process. By analyzing occlusions in the compressed domain rather than the raw domain, the system maintains detection precision while significantly improving processing efficiency and productivity.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP3881282B1Detecting sensor occlusion with compressed image data
Publication Date: 2025.08.20 WAYMO LLC
  • EP3881282B1 patent drawingFigure 1
  • EP3881282B1 patent drawingFigure 2
  • EP3881282B1 patent drawingFigure 3

AI summary

The technology relates to detecting possible imaging sensor occlusion. In one example, a system including an imaging sensor 300 and one or more processors 120 may be configured to capture first image data using the imaging sensor. The one or more processors may encode the first image data into an uncompressed image file and generate a compressed image file based on the uncompressed image file. The file size of the compressed image file may be determined and based on the file size of the compressed image file, the system may determine that the imaging sensor is possibly occluded.