Koninklijke Philips Corporation N.v.

Koninklijke Philips Electronics N.v.

Philips Intellectual Property & Standards Gmbh

Christiaan Varekamp

Bart Kroon

Patrick Luc Els Vandewalle

Wilhelmus Hendrikus Alfonsus Bruls

Reinier Bernardus Maria Klein Gunnewiek

Philip Steven Newton

Wiebe De Haan

Arnoldus Werner Johannes Oomen

Johan Cornelis Talstra

Jeroen Gerardus Henricus Koppens

Vasanth Philomin

Nathan Souviraa-Labastie

Fabian Edgar Ernst

Christian Benien

Marc Helbing

Patrick Luc E Vandewalle

Bartholomeus Wilhelmus Damianus Van Geest

Georgios Parlantzas

Bernardus Hendrikus Wilhelmus Hendriks

Mark Jozef Willem Mertens

Reinhold Wimberger-Friedl

Pieter Jan Van Der Zaag

Abraham Karel Riemens

Peter-Andre Redert

Erno Hermanus Antonius Langendijk

Karel Johannes Gerhardus Hinnen

Bart Gerard Bernard Barenbrug

Marc Joseph Rita Op De Beeck

Robert-Paul Mario Berretty

Ralph Braspenning

Eric Peter Funke

Gerardus Wilhelmus Theodorus Van Der Heijden

Bart G B Barenbrug

Reinier B M Klein Gunnewiek

Om Prakash Gangwal

Fons Bruls

Ralph Antonius Cornelius Braspenning

Gerardus W T Van Der Heijden

David Halter

Wilhelmus H A Bruls

John Arthur Pedersen

Wilhelmus Hendricus Alfonsus Bruls

Geradus Wilhelmus Theodorus Van Der Heijden

Bartolomeus W D Sonneveldt

Mickael Stephane Bernard George Bouvier

Patrick Fernandes Machado

Matthijs Carolus Piek

Andy Willems

Bartolomeus Wilhelmus Damianus Sonneveldt

Bartholomeus Wilhelmus Sonneveldt

Nathan SouviraÀ-Labastie

John Pedersen

Patrick F Machado

Patrick L E Vandewalle

Om P Gangwal

Eric P Funke

Mickael S B G Bouvier

A method for processing multi-view image data. The method comprises obtaining source view data from a plurality of sensors, the source view data containing source texture data and source depth data of a scene with one or more objects. The positions of one or more of the objects in the scene are obtained and a stack of layers is generated in a virtual scene for at least one of the objects, wherein the position of a stack of layers in the virtual scene is based on the position of the corresponding object in the scene. Generating a stack of layers comprises generating a plurality of layers, wherein each layer comprises texture data and transparency data for the corresponding object.

Multi object surface image (MOSI) format

A method for calibrating a camera pose in a hybrid camera array comprising two or more color sensors and one or more depth sensors. The method comprises obtaining a depth map for each of the depth sensors, obtaining a set of images from the color sensors and generating up to scale camera poses for the color sensors and an up to scale point cloud using the set of images. A scaling of the up to scale camera poses and up to scale point cloud is then estimated using the one or more depth maps.

Self-calibration for hybrid camera arrays

A method of depth segmentation for the generation of a multi-view video data. The method comprises obtaining a plurality of source view images and source view depth maps representative of a 3D scene from a plurality of sensors. Foreground objects in the 3D scene are segmented from the source view images and/or the source view depth maps. One or more patches are then generated for each source view image and source view depth map containing at least one foreground object, wherein each patch corresponds to a foreground object and wherein generating a patch comprises generating a patch texture image, a patch depth map and a patch transparency map based on the source view images and the source view depth maps.

Depth segmentation in multi-view videos

Presented are concepts for generating an input image dataset that may be used for training the alignment of multiple synthesized images. Such concepts may be based on an idea to generate an input image dataset from copies of an arbitrary reference image that are shifted in various directions. In this way, a single arbitrary image may be used to create an artificial misaligned input image input sample (i.e. input image dataset) that can be used to train a neural network.

Training alignment of a plurality of images

A method for transmitting multi-view image frame data. The method comprises obtaining multi-view components representative of a scene generated from a plurality of sensors, wherein each multi-view component corresponds to a sensor and wherein at least one of the multi-view components includes a depth component and at least one of the multi-view components does not include a depth component. A virtual sensor pose is obtained for each sensor in a virtual scene, wherein the virtual scene is a virtual representation of the scene and wherein the virtual sensor pose is a virtual representation of the pose of the sensor in the scene when generating the corresponding multi-view component. Sensor parameter metadata is generated for the multi-view components, wherein the sensor parameter metadata contains extrinsic parameters for the multi-view components and the extrinsic parameters contain at least the virtual sensor pose of a sensor for each of the corresponding multi-view components. The extrinsic parameters enable the generation of additional depth components by warping the depth components based on their corresponding virtual sensor pose and a target position in the virtual scene. The multi-view components and the sensor parameter metadata is thus transmitted.

Coding hybrid multi-view sensor configurations

An apparatus comprises a receiver () receiving an image signal representing a scene. The image signal includes image data comprising a number of images where each image comprises pixels that represent an image property of the scene along a ray having a ray direction from a ray origin. The ray origins are different positions for at least some pixels. The image signal further comprises a plurality of parameters describing a variation of the ray origins and/or the ray directions for pixels as a function of pixel image positions. A renderer () renders images from the number of images based on the plurality of parameters.

Image signal representing a scene

A distribution system comprises an audio server () for receiving incoming audio from remote clients () and for transmitting audio derived from the incoming audio to the remote clients (). An audio apparatus comprises an audio a receiver () which receives data comprising: audio data for a plurality of audio components representing audio from a remote client of the plurality of remote clients; and proximity data for at least one of the audio components. The proximity data is indicative of proximity between remote clients. A generator () of the apparatus generates an audio mix from the audio components in response to the proximity data. For example, an audio component indicated to be proximal to a remote client may be excluded from an audio mix for that remote client.

Audio apparatus, audio distribution system and method of operation therefor

A method for calibrating at least one of the six-degrees-of-freedom of all or part of cameras in a formation positioned for scene capturing, the method comprising a step of initial calibration before the scene capturing. The step comprises creating a reference video frame which comprises a reference image of a stationary reference object. During scene capturing the method further comprises a step of further calibration wherein the position of the reference image of the stationary reference object within a captured scene video frame is compared to the position of the reference image of the stationary reference object within the reference video frame, and a step adapting the at least one of the six-degrees-of-freedom of a multiple cameras of the formation if needed in order to get an improved scene capturing after the further calibration.

Method of calibrating cameras

A method is provided for selecting a transparency setting and color values of pixels in a virtual image. The virtual image can be formed by combining reference images taken at different angles to produce the virtual image that views an object at a new, uncaptured angle. The method includes determining for each pixel of the virtual image, what information it carries from the reference view images. The information of the pixel is used to define a pixel category, and the category is used to select, based on logical conditions, what information will be displayed by the pixel and to set the color of the pixels.

Image processing method for setting transparency values and color values of pixels in a virtual image

An apparatus where a vertical image position of the scene point may depend on the horizontal image position. A mapper generates a modified image having a modified projection by applying a mapping to the first wide angle image corresponding to a mapping from the first projection to a perspective projection followed by a non-linear vertical mapping from the perspective projection to a modified vertical projection of the modified projection and a non-linear horizontal mapping from the perspective projection to a modified horizontal projection of the modified projection. Then a disparity estimator generates disparities for the modified image relative to a second image and representing a different view point than the first wide angle image.

Disparity estimation from a wide angle image

An image synthesis apparatus comprises a receiver () for receiving image parts and associated depth data of images representing a scene from different view poses from an image source. A store () stores a depth transition metric for each image part of a set of image parts where the depth transition metric for an image part is indicative of a direction of a depth transition in the image part. A determiner () determines a rendering view pose and an image synthesizer () synthesizes at least one image from received image part. A selector is arranged to select a first image part of the set of image parts in response to the depth transition metric and a retriever () retrieves the first image part from the image source. The synthesis of an image part for the rendering view pose is based on the first image part.

Image synthesis

The invention refers to a system () for affecting a subject and a method for operating the system comprising a medical device like a biopsy gun () set in a first state in which it is not able to affect the subject based on a trigger signal or in a second state in which it is able to affect the subject based on the trigger signal, wherein the state is set based on a provided location of the medical device, i.e., for instance, is set based on the distance of the medical device to a target region. The location of the medical device is provided by a location providing unit () comprising, for instance, an imaging unit like an ultrasound system (). Thus, unintended, possible dangerous injuries of the patient are prevented and the safety of the patient during the interventional procedure is increased.

System for affecting a subject

A method of processing depth maps comprises receiving () images and corresponding depth maps. The depth values of a first depth map of the corresponding depth maps are updated () based on depth values of at least a second depth map of the corresponding depth maps. The updating is based on a weighted combination of candidate depth values determined from other maps. A weight for a candidate depth value from the second depth map is determined based on the similarity between a pixel value in the first image corresponding to the depth being updated and a pixel value in a third image at a position determined by projecting the position of the depth value being updated to the third image using the candidate depth value. More consistent depth maps may be generated in this way.

Processing of depth maps for images

An apparatus for evaluating a quality for image capture comprises a stored () for storing a model of a scene and a capture circuit () for generating virtual captured images for a camera configuration by rendering from the model. A depth generation circuit () generates model depth data from the model and a depth estimation circuit () generates estimated depth data from the virtual captured images. A first synthesis circuit () and a second synthesis circuit () generates first and second view images for test poses by processing the virtual captured images based on the model depth data or estimated depth data respectively. A reference circuit () generates reference images for the f test poses by rendering based on the model. A quality circuit () generates a quality metric based on a comparison of the first view images, the second view images, and the reference images.

Apparatus and method for evaluating a quality of image capture of a scene

An image synthesis system comprises receivers () receiving scene data describing at least part of a scene; object data describing a 3D object from a viewing zone having a relative pose with respect to the object, and a view pose in the scene. A pose determiner circuit () determines an object pose for the object in the scene in response to the scene data and the view pose; and a view synthesis circuit () generates a view image of the object from the object data, the object pose, and the view pose. A circuit () determines a viewing region in the scene which corresponds to the viewing zone for the object being at the object pose. The pose determiner circuit () determines a distance measure for the view pose relative to the viewing region and changes the object pose if the distance measure meets a criterion including a requirement that a distance between the view pose and a pose of the viewing region exceeds a threshold.

Image synthesis system and method therefor

Growing community of inventors

Eindhoven, Netherlands

Christiaan Varekamp