Adaptive Neutral Density Filter for Self-Driving Camera Exposure

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Self-driving vehicles face challenges in capturing usable images due to overexposure or underexposure in varying light conditions, which can delay decision-making and potentially damage sensors, especially during sunrise, sunset, or direct sunlight.

Innovation Solution

An adaptive neutral density filter system that adjusts the amount of light entering cameras using graduated or multiple neutral density filters, controlled by actuators and ambient light sensors to ensure optimal exposure, minimizing overly bright regions and maintaining filter cleanliness.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Illumination intensity

If no filter is used to allow maximum light entry, then image brightness is sufficient in low light conditions, but sensor damage occurs and overexposure happens in bright conditions

Engineering Contradiction:
Improveimage brightnessVSAvoidsensor damage and overexposure
Core Design Contradiction:
Illumination intensityVSObject-affected harmful factors

Solution Approach 1:

The patent implements a dynamic filter system where neutral density filters with different optical densities are selectively positioned in front of the imaging sensor based on ambient light conditions. The system transitions from a static no-filter approach to a dynamic multi-density filter selection mechanism, allowing the filter density to adapt to varying light environments and prevent both overexposure and sensor damage.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system changes the optical density parameter of the filter based on lighting conditions. Multiple neutral density filters with different optical densities (e.g., ND2, ND4, ND8, ND16) are available, and the system selects the appropriate filter by adjusting this optical density parameter to match the ambient light level, thereby controlling the amount of light reaching the sensor.

Inventive Principle:
Principle #35Parameter changes

2Adaptability or versatility

If multiple filters with different optical densities are used to handle varying light conditions, then proper exposure is achieved across different lighting environments, but device complexity increases

Engineering Contradiction:
Improveexposure adaptabilityVSAvoidfilter system complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent divides the filter system into multiple discrete neutral density filter elements (ND2, ND4, ND8, ND16) rather than using a single continuous variable filter. This segmentation allows the system to handle different light conditions with distinct filter options while maintaining a relatively simple mechanical selection mechanism, balancing adaptability with system complexity.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The filter system is designed to serve multiple functions: it provides exposure control across various lighting conditions, protects the sensor from excessive light, and maintains a compact structure. The same multi-filter mechanism handles both imaging and depth sensing functions, reducing the need for separate systems and thereby managing complexity.

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

3Measurement precision

If filters are frequently adjusted to match changing light conditions, then optimal image quality is maintained, but response time delays occur in decision-making processes

Engineering Contradiction:
Improveimage qualityVSAvoiddecision-making delay
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system pre-positions multiple neutral density filters with different optical densities before operation, ready for rapid selection. When light conditions change, the controller can immediately switch to the appropriate pre-prepared filter without needing to manufacture or adjust a new filter on the fly, significantly reducing the response time while maintaining optimal image quality.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent replaces complex continuous mechanical adjustment mechanisms with a discrete electronic switching system that rapidly selects from pre-positioned filters. This substitution of mechanical adjustment with electronic control reduces adjustment time and improves response speed, allowing the system to quickly adapt to changing light conditions without delaying decision-making processes.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Ensures proper image exposure under any daylight conditions, preventing damage to sensors and enhancing the accuracy and speed of self-driving vehicle decision-making processes.

Implementation Method 1

The adaptive filter system can includes one or more filters to attenuate incoming light

Methodology Applied
Scientific EffectOptical absorption: Absorption (EM radiation)

Implementation Method 2

The one or more filters can be coupled to one or more actuators and can be moved by the one or more actuators in response to the attenuated incoming light

Methodology Applied
Scientific EffectMechanical actuation:

Data Source

PatentUS11317033B2Adaptive filter system for self-driving vehicle
Publication Date: 2022.04.26 PONY AI INC
  • US11317033B2 patent drawing
  • US11317033B2 patent drawing
  • US11317033B2 patent drawing

AI summary

An adaptive filter system and a method for controlling the adaptive filter system are described herein. The system can includes one or more filters to attenuate incoming light. The one or more filters can be moved by one or more actuators. The method can capture image data from an imaging device through the one or more filters. Information can be determined from the captured image data. The one or more filters can be moved to a position for capturing image data based on the information.