Structured Light Sensor Depth Correction for Capsule Endoscopy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing structured-light technologies for capturing 3D images in the gastrointestinal tract face challenges due to object movement and high power consumption, which complicates accurate depth information derivation and reduces frame rates in capsule camera applications.
Innovation Solution
A method and device that capture additional structured-light images before or after regular images to correct depth information, allowing for interpolation and non-linear transformations to combine sub-images, thereby improving depth accuracy and maintaining frame rates while reducing power consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If structured light is projected continuously to capture depth information, then depth accuracy is improved, but power consumption increases
Solution Approach 1:
The patent implements periodic projection of structured light patterns instead of continuous projection. The system alternates between projecting structured light patterns and capturing regular images, with multiple captures occurring during intervals between pattern projections. This periodic approach maintains sufficient depth measurement accuracy while significantly reducing power consumption in the power-sensitive capsule camera environment.
Solution Approach 2:
The patent captures multiple regular sub-images during the interval between structured light pattern projections, before the next pattern is projected. This preliminary capture of additional images during idle periods allows the system to accumulate sufficient image data without requiring continuous power-intensive pattern projection, thereby reducing overall power consumption while maintaining imaging quality.
2Measurement precision
If structured light patterns are projected frequently to maintain depth accuracy with moving objects, then depth information accuracy is improved, but frame rate decreases
Solution Approach 1:
The patent captures multiple regular sub-images during the time interval between structured light pattern projections, before the next pattern is projected. This preliminary action allows the system to accumulate multiple frames of regular images without waiting for the next structured light projection, effectively maintaining high frame rates even when objects are moving. The depth information from periodic patterns is interpolated across multiple sub-images to maintain accuracy.
Solution Approach 2:
The patent maintains continuous capture of regular images during the intervals between structured light projections by capturing multiple sub-images in sequence. This continuous useful action ensures that no imaging time is wasted, allowing the system to maintain high effective frame rates while still obtaining sufficient depth information from the periodic structured light patterns for accurate depth derivation with moving objects.
3Productivity
If multiple regular images are captured between structured light images, then frame rate is maintained, but depth information accuracy deteriorates due to object movement
Solution Approach 1:
The patent uses depth information derived from structured light patterns as feedback to guide the selection and processing of multiple regular sub-images. By analyzing the depth data and object motion characteristics, the system determines optimal ways to associate regular images with the correct depth information, compensating for object movement. This feedback mechanism allows maintaining high frame rates while preserving depth accuracy through intelligent image selection and processing.
Solution Approach 2:
The patent introduces depth information from structured light patterns as an intermediary to bridge the temporal gap between multiple regular sub-images captured during intervals. This intermediary depth data serves as a reference to correctly associate and process the regular images, enabling accurate depth derivation even when objects move significantly between captures. The intermediary depth information compensates for motion-induced discrepancies.
Data Source
AI summary
A method and device for improving the accuracy of depth information derived from a structured-light image for a regular image are disclosed. In one example, an additional structured-light image is captured before a first structured-light image or after a regular image. The depth information for the regular image can be derived from the first structured-light image and corrected by incorporating depth information from the additional structured-light image. A model for depth information can be used to predict or interpolate depth information for the regular image. In another example, two regular sub-images may be captured with a structured-light image in between. If substantial frame differences or substantial global motion vector/block motion vectors are detected, the two regular sub-images will not be combined in order to avoid possible motion smear. Instead, one of the two sub-images will be selected and scaled as the output regular image.