Endoscope with images optimized based on depth map derived from structured light images
Inventors
Wang, Kang-Huai • Wilson, Gordon C.
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-10624533-B2
Publication Date
2020-04-21
Expiration Date
Abstract
A method and apparatus for processing gastrointestinal (GI) images are disclosed. According to this method, a regular image is received, where the regular image is captured using an imaging apparatus by projecting non-structured light onto a body lumen when the imaging apparatus is in the body lumen. One or more structured-light images captured using the imaging apparatus by projecting the body lumen with structured light are received. A target distance for a target region in the regular image is derived based on said one or more structured-light images. A filter is determined based on the target distance and camera parameters associated with the imaging apparatus. A first processed target region is generated by applying the filter to the target region to improve sharpness of the target region. A first processed regular image comprising the first processed target region is provided.
Core Innovation
The invention processes gastrointestinal (GI) images by receiving one or more structured-light images captured by projecting structured light onto a body lumen using an imaging apparatus in the body lumen, and also receiving a regular image captured by projecting non-structured light onto the body lumen with the same imaging apparatus. Using the structured-light images, it derives a target distance for a target region in the regular image.
Based on the derived target distance and camera parameters associated with the imaging apparatus, the invention determines a filter and generates a first processed target region by applying the filter to the target region to improve sharpness of the target region. The invention then provides a first processed regular image comprising the first processed target region.
Embodiments include depth-map-to-PSF/kernel computation and depth-map-guided variable-kernel sharpening, including deconvolution kernels such as Wiener filters using point spread function (PSF) and noise. The invention also describes imaging models, frequency-domain sharpening, and partitioning the regular image into regions with different distances and corresponding filters.
Claims Coverage
The partial content provides two independent claims. Both claims cover deriving target distance from structured-light for a target region and using that distance with camera parameters to determine a filter that improves sharpness in a processed regular image.
Structured-light depth to target distance for a regular-image target region
Receiving one or more structured-light images captured by projecting structured light onto a body lumen when the imaging apparatus is in the body lumen; receiving a regular image captured by projecting non-structured light onto the body lumen when the imaging apparatus is in the body lumen; deriving a target distance for a target region in the regular image based on said one or more structured-light images.
Target-distance and camera-parameter-based filter for sharpened target region
Determining a filter based on the target distance and camera parameters associated with the imaging apparatus; generating a first processed target region by applying the filter to the target region to improve sharpness of the target region; and providing a first processed regular image comprising the first processed target region.
Across the independent claims, the inventive coverage centers on using structured-light images to derive a target distance for a target region within a regular (non-structured light) GI image, and then selecting or determining a filter based on that target distance together with camera parameters to generate a sharpened processed target region that is included in a processed regular image.
Stated Advantages
Improve sharpness of the target region.
Documented Applications
Processing gastrointestinal (GI) images using an imaging apparatus in a body lumen, including capsule endoscopes and traditional flexible-tube endoscopes.
Using a panoramic capsule camera for GI imaging with depth-map-guided variable-kernel sharpening.
Interested in licensing this patent?