Depth-Based Salient Point Detection for Protuberant Objects

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current computer vision systems face challenges in accurately detecting salient objects in images, particularly when appearance contrast between the object and its background is low, leading to unreliable results.

Innovation Solution

An image processing method that involves obtaining a depth image of a protuberant object, selecting test points on a circle around a center pixel, calculating a protuberance value based on depth value comparisons, and determining salient points using these values, which reduces reliance on appearance contrast and enhances detection robustness.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If appearance contrast-based saliency models are used, then detection speed is maintained, but detection reliability deteriorates when appearance contrast is low

Engineering Contradiction:

Improvedetection reliabilityVSAvoidadaptability to low contrast scenarios

Core Design Contradiction:

ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent changes the detection parameter from appearance contrast (color, grayscale) to depth value contrast. By using depth information instead of appearance information, the system achieves reliable detection in scenarios where appearance contrast is low, directly resolving the technical contradiction between maintaining detection reliability and adapting to low contrast scenarios.

Inventive Principle:

Principle #35Parameter changes

2Reliability

If depth-based protuberance detection is implemented, then detection robustness against rotation and deformation is improved, but computation cost increases

Engineering Contradiction:

Improvedetection robustnessVSAvoidcomputation cost

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments the depth image processing into distinct stages: first identifying candidate regions using depth value comparisons, then calculating protuberance values only for these candidates using circular test point arrangements. This segmentation approach maintains high robustness against rotation and deformation while reducing overall computation cost by avoiding exhaustive processing of all pixels.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent applies partial action by using a fixed number of test points (e.g., 8 points) arranged on a circle for protuberance calculation, rather than exhaustive analysis. This provides sufficient robustness for most scenarios while keeping computation manageable, representing a balanced partial action approach.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentEP3479347B1Method and apparatus for detecting a salient point of a protuberant object

Publication Date: 2023.06.14 MICROSOFT TECHNOLOGY LICENSING LLC

Figure 1
Figure 2
Figure 3A~3B

AI summary

An image processing method and an apparatus (300) are provided, the method includes: obtaining a depth image of a protuberant object (210); selecting a plurality of test points placed on a circle around a pixel in the depth image as a center point of the circle; calculating a protuberance value of the center point based on a comparison between the depth value of the center point and the depth value of each of the selected test points (240); and determining one or more salient points of the protuberant object by using the protuberance value of each pixel in the depth image (250).