Imaging Camera Processing Unit for User-Defined Object Segmentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current camera systems lack user control over image capturing and rendering, particularly in handling complex scenes with varying illumination and contrast, leading to issues like harsh shadows, loss of detail, and unharmonious color representation, which are difficult to correct post-processing.

Innovation Solution

An imaging camera unit with a user-interface for specifying object preferences, object segmentation, color composition monitoring, and transformation capabilities, allowing users to adjust capturing parameters and image rendering to achieve optimal image quality by segmenting objects, analyzing their color properties, and applying transformations based on user input.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If automatic exposure and optimization procedures are used, then the user is freed from manual photo-measuring and conversion tables, but the user loses control over artistic quality and geometric composition, resulting in images that may look plain ugly or have unrecognizable buildings

Engineering Contradiction:
Improveautomatic exposureVSAvoidimage quality
Core Design Contradiction:
Ease of operationVSManufacturing precision

Solution Approach 1:

The image is segmented into multiple depth planes or regions (foreground, midground, background) with different sharpness requirements. The system allows selective optimization of different regions, enabling the user to control which areas should be sharp and which can be softer, thus maintaining artistic quality while using automated processing.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Different regions of the image are assigned different quality characteristics. The system applies local sharpness optimization, local exposure adjustment, and selective focus to specific areas rather than uniform processing, preserving artistic intent while automating technical aspects.

Inventive Principle:
Principle #3Local quality

2Adaptability or versatility

If the camera captures a wide dynamic range scene (e.g., city-scape with sky), then more of the scene is recorded, but the buildings may become unrecognizable when rendered on a low dynamic range display

Engineering Contradiction:
Improvedynamic rangeVSAvoiddetail recognition
Core Design Contradiction:
Adaptability or versatilityVSManufacturing precision

Solution Approach 1:

The system performs preliminary tone mapping and dynamic range compression during the capturing phase, preparing the image data in advance for optimal rendering on standard displays. This preliminary processing ensures that buildings and other important elements maintain recognizability while preserving the benefits of wide dynamic range capture.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system dynamically adjusts rendering parameters such as tone mapping curves, contrast, and brightness based on the scene content and display characteristics. This allows optimal presentation of high dynamic range images on low dynamic range displays, preventing loss of detail in important regions like buildings.

Inventive Principle:
Principle #35Parameter changes

3Manufacturing precision

If the user has full control over capturing parameters during image capture, then the user can optimize the image at the time of capturing, but the user must manually optimize each parameter which is tedious

Engineering Contradiction:
Improveimage optimizationVSAvoidmanual optimization
Core Design Contradiction:
Manufacturing precisionVSEase of operation

Solution Approach 1:

The system provides dynamic, adaptive optimization that automatically adjusts capturing parameters based on scene analysis while allowing user intervention when needed. The optimization process is flexible and can be adjusted in real-time, combining automated convenience with user control where artistic judgment is required.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system provides feedback mechanisms that show the user the effect of automatic optimization in real-time, allowing the user to accept or modify the results. This feedback loop enables the user to benefit from automated optimization while maintaining control over the final artistic outcome.

Inventive Principle:
Principle #23Feedback

4Manufacturing precision

If post-processing is applied to correct image issues, then some improvements can be made, but irreparable data loss has already occurred between the original scene and the photographic representation

Engineering Contradiction:
Improveimage correctionVSAvoiddata loss
Core Design Contradiction:
Manufacturing precisionVSLoss of information

Solution Approach 1:

The system performs critical optimization actions during the capturing phase rather than relying solely on post-processing. By optimizing exposure, sharpness, and tone mapping at the time of capture, the system preserves more information in the original data, preventing irreversible data loss before post-processing even begins.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP1922862B1Imaging camera processing unit and method
Publication Date: 2017.08.02 KONINKLIJKE PHILIPS NV
  • EP1922862B1 patent drawingFigure 1
  • EP1922862B1 patent drawingFigure 2
  • EP1922862B1 patent drawingFigure 3

AI summary

To allow much better user control of how a camera output image captures an original scene, the imaging camera unit (401), arranged to form part of a image-capturing camera system (400), comprising: a user- interface (420), allowing a user to specify at least one indication (gp) of a geometric position of an object (101) of his preference in a captured image (Io) received from an imaging sensor (406) via an input (403); a user-adaptable object segmentation unit (410), arranged to determine a set of pixels (sg) being part of the object (101), on the basis of the indication (gp); and a color composition monitor unit (412), arranged to determine at least one statistic (ST) on the basis of at least one color property of pixels in the set of pixels (sg).