Endoscope Autofocus Control Using Dual Area Scene Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Endoscope systems with large pixel image sensors experience shallow depth of field, leading to unnecessary focus operations during medical procedures, as existing autofocus techniques fail to distinguish between intentional and unintentional changes in the focus position, causing defocus or erroneous AF control.
Innovation Solution
An endoscope apparatus with a processor that performs a focus control process based on an in-focus evaluation value from a first area and detects changes in a second area, allowing the system to stop and resume focus control accordingly, thereby minimizing unnecessary focus operations during medical procedures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If autofocus control is continuously performed based on center area evaluation, then in-focus quality is improved, but unnecessary focus operations occur during treatment causing defocus
Solution Approach 1:
The image area is segmented into two distinct regions: a first area (center region) for calculating in-focus evaluation values to guide autofocus, and a second area (peripheral region) for detecting scene changes that indicate treatment activity. This spatial segmentation allows the system to differentiate between intentional focus-target changes and treatment-induced changes, resolving the contradiction by enabling precise focus control only when genuinely needed while maintaining stability during treatment procedures.
2Measurement precision
If focus operation is performed frequently to maintain in-focus, then image quality is improved, but treatment precision is reduced due to unintentional focus changes
Solution Approach 1:
The second area (peripheral region) acts as an intermediary indicator that indirectly signals whether treatment is occurring. By monitoring scene changes in this peripheral zone rather than directly in the treatment area, the system can infer treatment status and appropriately modulate focus operations, thereby preserving both image quality and treatment precision without interference from unintentional focus shifts.
3Measurement precision
If autofocus evaluates entire image area, then focus accuracy is improved, but processing complexity increases due to treatment tool movements
Solution Approach 1:
The evaluation process extracts only the essential information needed for focus control by calculating in-focus evaluation values exclusively from the first area (center region) where the lesion is located. The second area (peripheral region) is extracted solely for scene change detection to determine treatment status. This selective extraction eliminates the complexity introduced by treatment tool movements in the periphery while maintaining focus accuracy for the actual treatment target.
Data Source
AI summary
An endoscope apparatus includes a processor comprising hardware, a processor performs a focus control that controls a position of a focus lens to an in-focus position based on an in-focus evaluation value, the focus lens being included in an optical system that forms an image of a captured image that is acquired by an imaging section, and the in-focus evaluation value being calculated from a first area within the captured image, and a change-in-scene detection process that detects whether or not a change in scene has occurred from a second area that includes an area that differs from the first area, wherein the processor is set to a standby state when the position of the focus lens has been controlled to the in-focus position, and resumes the focus control process when a change in scene has been detected when the focus control section is set to the standby state.