Microsoft Technology Licensing, LLC

Given Imaging Ltd.

Avishai Adler

Sagi Katz

Giora Yahav

Guy Gilboa

John Allen Tardif

Shlomo Felzenshtein

David Cohen

Dori Peleg

Tal Davidson

Eli Larry

Moran Horesh

Iddo Ambor

Eshel Hason

Avishag Spillinger

Alexandra Gilinsky

Laurence Keselbrener

Roni Keynan

Giovanni Di Napoli

Systems, devices, methods for capsule endoscopy procedures are disclosed. A system for a capsule endoscopy procedure includes a capsule device configured to capture in-vivo images over time of at least a portion of a gastrointestinal tract (GIT) of a person, a wearable device configured to be secured to the person where the wearable device is configured to receive at least some of the in-vivo images from the capsule device and to communicate at least some of the received images to a communication device at a same location as the wearable device, and a storage medium storing machine-executable instructions configured to execute on a computing system remote from the location of the wearable device. The instructions, when executed, cause the computing system to receive communicated images from the communication device, perform processing of the communicated images received from the communication device, and communicate with at least one healthcare provider device.

Systems, devices, apps, and methods for capsule endoscopy procedures

A method for image classification includes accessing a plurality of images of at least a portion of a gastrointestinal tract (GIT) captured by a capsule endoscopy device and for each image of the plurality of images: providing a classification score for each segment of a plurality of consecutive segments of the GIT by a deep learning neural network, and providing a classification probability for each segment of the plurality of consecutive segments of the GIT based on the classification scores by a classical machine learning classifier. The method further includes determining a classification for each image to one segment of the plurality of consecutive segments of the GIT based on processing a signal corresponding to the classification probabilities of the plurality of images.

Systems and methods for image classification and stream of images segmentation

A 3D imager comprising two cameras having fixed wide-angle and narrow angle FOVs respectively that overlap to provide an active space for the imager and a controller that determines distances to features in the active space responsive to distances provided by the cameras and a division of the active space into near, intermediate, and far zones.

3D zoom imager

A system for controlling infrared (IR) enabled devices by projecting coded IR pulses from an active illumination depth camera is described. In some embodiments, a gesture recognition system includes an active illumination depth camera such as a depth camera that utilizes time-of-flight (TOF) or structured light techniques for obtaining depth information. The gesture recognition system may detect the performance of a particular gesture associated with a particular electronic device, determine a set of device instructions in response to detecting the particular gesture, and transmit the set of device instructions to the particular electronic device utilizing coded IR pulses. The coded IR pulses may imitate the IR pulses associated with a remote control protocol. In some cases, the coded IR pulses transmitted may also be used by the active illumination depth camera for determining depth information.

Methods for controlling electronic devices using gestures

Techniques are provided for determining depth to objects. A depth image may be determined based on two light intensity images. This technique may compensate for differences in reflectivity of objects in the field of view. However, there may be some misalignment between pixels in the two light intensity images. An iterative process may be used to relax a requirement for an exact match between the light intensity images. The iterative process may involve modifying one of the light intensity images based on a smoothed version of a depth image that is generated from the two light intensity images. Then, new values may be determined for the depth image based on the modified image and the other light intensity image. Thus, pixel misalignment between the two light intensity images may be compensated.

Time-of-flight depth imaging

A depth-mapping method comprises exposing first and second detectors oriented along different optical axes to light dispersed from a scene, and furnishing an output responsive to a depth coordinate of a locus of the scene. The output increases with an increasing first amount of light received by the first detector during a first period, and decreases with an increasing second amount of light received by the second detector during a second period different than the first.

Plural detector time-of-flight depth mapping

Compatibility between a depth image consumer and a plurality of different depth image producers is provided by receiving a native depth image having unsupported depth camera parameters that are not compatible with a depth image consumer, and converting the native depth image to a virtual depth image having supported virtual depth camera parameters that are compatible with the depth image consumer. This virtual depth image is then output to the depth image consumer.

Depth camera compatibility

A video projector device includes a visible light projector to project an image on a surface or object, and a visible light sensor, which can be used to obtain depth data regarding the object using a time-of-flight principle. The sensor can be a charge-coupled device which obtains color images as well as obtaining depth data. The projected light can be provided in successive frames. A frame can include a gated sub-frame of pulsed light followed by continuous light, while the sensor is gated, to obtain time of flight data, an ungated sub-frame of pulsed light followed by continuous light, while the sensor is ungated, to obtain reflectivity data and a background sub-frame of no light followed by continuous light, while the sensor is gated, to determine a level of background light. A color sub-frame projects continuous light, while the sensor is active.

Integrated low power depth camera and projection device

Systems and methods for increasing the resolution of a depth map by identifying and updating false depth pixels are described. In some embodiments, a depth pixel of the depth map is initially assigned a confidence value based on curvature values and localized contrast information. The curvature values may be generated by applying a Laplacian filter or other edge detection filter to the depth pixel and its neighboring pixels. The localized contrast information may be generated by determining a difference between the maximum and minimum depth values associated with the depth pixel and its neighboring pixels. A false depth pixel may be identified by comparing a confidence value associated with the false depth pixel with a particular threshold. The false depth pixel may be updated by assigning a new depth value based on an extrapolation of depth values associated with neighboring pixel locations.

Combined depth filtering and super resolution

Compatibility between a depth image consumer and a depth image producer is provided by receiving a native depth image having an unsupported type that is not supported by a depth image consumer, and processing the native depth image into an emulation depth image having a supported type that is supported by the depth image consumer. This emulation depth image is then output to the depth image consumer.

Techniques are provided for de-aliasing depth images. The depth image may have been generated based on phase differences between a transmitted and received modulated light beam. A method may include accessing a depth image that has a depth value for a plurality of locations in the depth image. Each location has one or more neighbor locations. Potential depth values are determined for each of the plurality of locations based on the depth value in the depth image for the location and potential aliasing in the depth image. A cost function is determined based on differences between the potential depth values of each location and its neighboring locations. Determining the cost function includes assigning a higher cost for greater differences in potential depth values between neighboring locations. The cost function is substantially minimized to select one of the potential depth values for each of the locations.

Growing community of inventors

Haifa, Israel

Avishai Adler