Mobile Camera Exposure Control Using SLAM Feature Points

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Cameras mounted on autonomous mobile bodies like drones and robots face challenges in maintaining proper exposure control due to varying imaging objects and styles, leading to inconsistent exposure of important imaging objects.

Innovation Solution

An exposure control device that includes a camera, edge/corner detection section, feature point extraction section, self-location estimation section, environment map storage section, matching section, area weight selection section, and camera control section, which uses Visual-SLAM and environment maps to adjust exposure based on feature points and semantic information for accurate exposure control.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If a large number of applications are held in the active state to improve accessibility, then ease of operation is improved, but memory resource consumption increases

Engineering Contradiction:
Improveaccessibility of applicationsVSAvoidmemory resource consumption
Core Design Contradiction:
Ease of operationVSQuantity of substance

Solution Approach 1:

The system dynamically adjusts the state of applications based on user interaction patterns. Frequently used applications are maintained in active state for quick access, while less used applications are transitioned to inactive or suspended states to free memory resources. This dynamic state management resolves the contradiction by making the system adaptable to actual usage needs rather than statically maintaining all applications in memory.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system changes the parameter of application state (active, inactive, suspended) based on usage frequency and memory availability. By transitioning applications between different states with different memory footprint characteristics, the system optimizes the balance between accessibility and memory consumption.

Inventive Principle:
Principle #35Parameter changes

2Speed

If application state information is stored in memory to maintain quick access, then speed is improved, but memory resource consumption increases

Engineering Contradiction:
Improveapplication launch speedVSAvoidmemory resource consumption
Core Design Contradiction:
SpeedVSQuantity of substance

Solution Approach 1:

The system applies different quality levels of state preservation to different applications based on their usage characteristics. Frequently accessed applications receive full state preservation in memory for instant restoration, while less frequently accessed applications use partial state information or rely on faster initialization procedures, optimizing the overall balance between launch speed and memory usage.

Inventive Principle:
Principle #3Local quality

3Productivity

If the system monitors and manages application states actively to improve productivity, then productivity is improved, but device complexity increases

Engineering Contradiction:
Improvesystem resource management efficiencyVSAvoidstate management complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The system implements self-service mechanisms where applications automatically report their state information and usage patterns to the management system. The operating system autonomously makes decisions about which applications to keep active, suspend, or terminate based on aggregated state information, eliminating the need for complex manual management interfaces while maintaining high productivity through automated resource optimization.

Inventive Principle:
Principle #25Self-service

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

Enables effective exposure control of captured images, ensuring accurate self-location estimation and improved image quality even in dynamic environments with varying brightness, particularly suitable for autonomous vehicles and drones.

Implementation Method 1

The image pickup device photo-electrically converts an image of an object into an electric signal and generates an image signal as the electric signal

Methodology Applied
Scientific EffectPhotoelectric conversion: Photoelectric Effect

Data Source

PatentEP3761629B1Information processing device, autonomous mobile body, information processing method, and program
Publication Date: 2024.05.01 SONY GROUP CORP
  • EP3761629B1 patent drawingFigure 1
  • EP3761629B1 patent drawingFigure 2
  • EP3761629B1 patent drawingFigure 3

AI summary

The present technology relates to an information processing device, an information processing method, and a program that make it possible to provide proper exposure control of a captured image. A matching section matches a feature point extracted from a captured image against a registered feature point stored in a predetermined storage section, and extracts a corresponding feature point in the captured image that corresponds to the registered feature point. A control section sets an exposure control value in accordance with an area image that is the image of an area near the corresponding feature point in the captured image. The present technology is applicable, for example, to an exposure control device that provides exposure control of a camera mounted on a mobile body.