Shape-from-shading algorithm for monoscopic endoscope depth perception

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional minimally invasive surgery using monoscopic endoscopes lacks depth information, making it challenging for surgeons to accurately position surgical instruments, while dual-camera endoscopes providing stereo images are expensive and less accepted.

Innovation Solution

A stereoscopic visualization system using a monoscopic endoscope with an image conversion device applying the shape-from-shading algorithm to generate stereo images from 2D images, calculating depth maps and disparity maps to create left and right images for 3D display without requiring a dual-lens endoscope.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a dual-camera endoscope is used to provide stereo images, then depth perception is improved, but device cost and complexity increase significantly

Engineering Contradiction:
Improvedepth perceptionVSAvoidendoscope structure
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent creates a virtual copy of the monoscopic endoscope's imaging capability by generating a synthetic stereoscopic image pair from a single 2D image. The first virtual image is the original 2D image, and the second virtual image is generated by applying depth map and disparity information to create a stereoscopic effect, effectively copying the function of a dual-camera system without the physical hardware

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent replaces the mechanical dual-camera system with an algorithmic approach. Instead of using two physical cameras to capture stereo images, the system uses shape-from-shading algorithms, depth map generation, and image processing techniques to synthesize stereoscopic images from a single 2D capture, substituting mechanical complexity with computational processing

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

2Loss of information

If a dual-camera endoscope is used to provide stereo images, then depth information is improved, but device cost increases

Engineering Contradiction:
Improvedepth informationVSAvoidendoscope cost
Core Design Contradiction:
Loss of informationVSEase of manufacture

Solution Approach 1:

The patent creates a virtual copy of the depth information that would normally require a dual-camera system to capture. By generating depth maps through shape-from-shading algorithms and using these depth maps to create stereoscopic image pairs, the system copies the essential depth information function without requiring expensive dual-camera hardware

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent uses computationally generated virtual images instead of expensive physical dual-camera systems. The virtual stereoscopic images are created through algorithms that process single 2D images, providing depth information at minimal additional cost compared to the expensive dual-camera hardware alternative

Inventive Principle:
Principle #27Cheap short-living objects (Disposable)

3Device complexity

If motion parallax and monocular cues are used for depth perception, then stereoscopic visualization is avoided, but positioning accuracy deteriorates

Engineering Contradiction:
Improvevisualization systemVSAvoidpositioning accuracy
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The patent replaces indirect depth perception methods (motion parallax, monocular cues) with direct stereoscopic visualization generated through algorithmic processing. Instead of relying on the surgeon's brain to interpret indirect cues, the system directly presents stereoscopic image pairs that provide authentic depth information, substituting cognitive processing with optical/computational depth encoding

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

Data Source

PatentUS11463676B2Stereoscopic visualization system and method for endoscope using shape-from-shading algorithm
Publication Date: 2022.10.04 MEDICALTEK CO LTD
  • US11463676B2 patent drawing
  • US11463676B2 patent drawing

AI summary

A stereoscopic visualization system using shape from shading algorithm is an image conversion device connected between a monoscopic endoscope and a 3D monitor. The system applies the algorithm which generates a depth map for a 2D image of video frames. The algorithm first calculates a direction of a light source for the 2D image. Based upon the information of light distribution and shading for the 2D image, the depth map is generated. The depth map is used to calculate another view of the original 2D image by depth image based rendering algorithm in generation of stereoscopic images. After the new view is rendered, the stereoscopic visualization system also needs to convert the display format of the stereoscopic images for different kinds of 3D displays. Based on this method, it can replace the whole monoscopic endoscope with a stereo-endoscope system and no modification is required for the monoscopic endoscope.