Healthy.io Ltd

Amazon Technologies, Inc.

Nathaniel Bubis

Yonatan Adiri

Ido Omer

Ron Zohar

Ilya Vladimirovich Brailovskiy

Noam Sorek

Ilia Vitsnudel

Matthew Alan Townsend

William Christopher Banta

Paul Alioshin

Philip James Taylor

Dmitry Svetlov

Benjamin Robert Hirsch

Matan Ronen

Nitai Fine

Systems and methods for image processing of a skin feature may include receiving from at least one image sensor associated with a mobile communications device a first and a second images of a skin feature. The skin feature has multiple segments of differing colors and differing sizes, and the second image is captured at least a day after the first image is captured. The method may further include analyzing data associated with the first and second images to determine a condition of the skin feature based on changes over time of the multiple segments. The method may also include determining, based on the determined condition of the skin feature, a medical action for treating the skin feature during a time period. Then, the method may include causing a mobile communications device to display information indicative of the determined medical action.

Image processing systems and methods for caring for skin features

A non-transitory computer readable medium storing data and computer implementable instructions that, when executed by at least one processor, cause the at least one processor to perform operations for generating cross section views of a wound, the operations including receiving 3D information of a wound based on information captured using an image sensor associated with an image plane substantially parallel to the wound; generating a cross section view of the wound by analyzing the 3D information; and providing data configured to cause a presentation of the generated cross section view of the wound.

Cross section views of wounds

In some embodiments, an example method or system consistent with the present disclosure may: obtain a desired property of a simulated trajectory of a virtual camera; receive a first video of a wound captured by a moving camera, the first video including a plurality of frames; use the desired property of the simulated trajectory of the virtual camera to analyze the first video to select at least two frames of the plurality of frames corresponding to the simulated trajectory of the virtual camera; use the desired property of the simulated trajectory of the virtual camera to select an order for the selected at least two frames; and rearrange the at least two frames based on the selected order to create a new video of the wound that represents the simulated trajectory of the virtual camera.

Rearranging and selecting frames of medical videos

In one embodiment of the present disclosure, an example system may receive a plurality of frames from at least one image sensor associated with a mobile device, at least one of the plurality of frames containing an image of a wound; display a real time video including at least a portion of the plurality of frames and a visual overlay indicating a desired position of the wound; detect, based on at least part of the plurality of frames, that the wound is in the desired position; display an indication to move the mobile device in a desired direction; receive motion data from at least one motion sensor associated with the mobile device; detect that the mobile device has moved in the desired direction; and display an additional indication on the mobile device.

Providing guidance for wound image capturing

Disclosed are processes including receiving at least a first and a second image data record corresponding to a first and a second point in time and including a first and a second one or more images of a wound; obtaining an image of the wound from a particular point of view corresponding to the first point in time by analyzing the first image data record; generating a simulated image of the wound from the particular point of view corresponding to the second point in time by analyzing the second image data record; and generating a visual time series view of the wound including at least the image of the wound from the particular point of view corresponding to the first point in time and the simulated image of the wound from the particular point of view corresponding to the second point in time.

Visual time series view of a wound with image correction

Various examples are directed to systems and methods for formatting stitched panoramic frames for transmission to a remote image processing system, the method comprising. A control circuit of a panoramic camera may receive first and second frames captured by first and second image sensors having partially overlapping fields-of-view. The control circuit may identify a first overlap region of the first frame and a second overlap region of the second frame. The first and second overlap region may comprise pixel values from portions of the fields-of-view of the image sensors that overlap. The control circuit may generate a panoramic frame from based at least in part on the first and second frames. The control circuit may generate a transmission frame comprising the panoramic frame, the first overlap region and the second overlap region.

Formatting stitched panoramic frames for transmission

Various examples are directed to a panoramic camera system comprising a first image sensor, a second image sensor and an enclosure. The first image sensor may have a first in-air field-of-view and the second image sensor may have a second in-air field-of-view. The first in-air field-of-view may overlap the second in-air field-of-view by greater than a threshold amount. The enclosure may comprise a curved outer surface. An alternate medium field-of-view of the first image sensor may overlap an alternate medium field-of-view of the second image sensor by greater than the threshold amount. The panoramic camera system may also comprise an image processor that is programmed to determine that the first image sensor and the second image sensor are within the enclosure. The panoramic camera system may stitch frames captured by the first and second image sensors considering an alternate medium stitching parameter.

Panoramic camera enclosure

Various examples are directed to systems, devices, and methods effective to generate updated pixel values in a stitched image. A processor may be programmed to identify a first block of pixels located in a region of a stitched image. The region may include pixels representing parallax views of a portion of a physical environment. The processor may determine a first average pixel value of pixels of the first block. The processor may identify a second block of pixels in the region. The processor may determine a second average pixel value of pixels of the second block. The processor may generate an updated pixel value for a pixel location of the first block or the second block. The updated pixel value may be based at least in part on the first average pixel value and the second average pixel value.

Growing community of inventors

Tel Aviv, Israel

Nathaniel Bubis