Depth Information Acquisition Using Shape Comparison Across Sensor Regions

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for acquiring depth information of objects, especially when they are outside the common sensing region of multiple sensors, face challenges in accurately determining depth due to limited parallax and varying shape information from different viewpoints.

Innovation Solution

The device employs a method to acquire first shape and depth information within the common sensing region and uses comparisons with second shape information from outside the region to calculate depth, leveraging the difference in shape information and depth information from multiple viewpoints to determine the object's depth accurately.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If depth information is acquired using stereo matching image processing within the common sensing region, then depth information can be obtained, but the method fails to accurately determine depth for objects outside the common sensing region due to limited parallax

Engineering Contradiction:
Improvedepth information accuracyVSAvoidapplicability to objects outside common sensing region
Core Design Contradiction:
Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The patent extends depth measurement from the two-dimensional image plane to a three-dimensional spatial representation by utilizing shape information from multiple viewpoints. This allows accurate depth determination for objects outside the common sensing region by projecting their 3D shape characteristics onto the measurement space, effectively adding a dimensional approach to overcome the parallax limitation.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

The patent introduces shape information as an intermediary element that mediates between the limited parallax data and the target depth measurement. By comparing shape information from multiple viewpoints with the shape information from the common sensing region, the system can infer depth for objects outside the common sensing region without requiring direct parallax measurement.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Adaptability or versatility

If shape information is compared between different viewpoints to determine depth, then depth information for objects outside common sensing region can be acquired, but the complexity of processing increases

Engineering Contradiction:
Improvedepth acquisition capabilityVSAvoidprocessing complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent makes shape information serve multiple functions: it acts as both a descriptor of the object's geometry and as a basis for depth calculation. By utilizing the same shape information from different viewpoints for both object recognition and depth estimation, the system reduces the need for separate processing pipelines, thereby managing complexity while enhancing versatility.

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

Data Source

PatentEP3461128B1Method and device for acquiring depth information of object, and recording medium
Publication Date: 2022.08.24 SAMSUNG ELECTRONICS CO LTD
  • EP3461128B1 patent drawingFigure 1
  • EP3461128B1 patent drawingFigure 2
  • EP3461128B1 patent drawingFigure 3

AI summary

Provided is a method of acquiring depth information of an object including acquiring first depth information of the object located at a first point in a common sensing region common to respective sensing regions of a plurality of sensors and first shape information of at least one view point, acquiring second shape information of the object at a second point when the object is located at the second point in a region excluding the common sensing region on the respective sensing regions of the plurality of sensors, and acquiring second depth information of the object at the second point based on a result of comparison between the first shape information of the at least one view point and the second shape information and the first depth information.