Abstract: Systems and methods for providing geometric interactions via three-dimensional mapping. A method includes determining a plurality of first descriptors for a plurality of key points in a plurality of first images, wherein each first image shows a portion of a 3D environment in which a robotic device and a visual sensor are deployed; generating a 3D map of the 3D environment based on the plurality of key points and the plurality of descriptors; determining a pose of the visual sensor based on at least one second descriptor and the plurality of first descriptors, wherein the second image is captured by the visual sensor; and determining a target action location based on at least one user input made with respect to a display of the second image and the pose of the visual sensor, wherein the target action location is a location within the 3D environment.

Abstract: Techniques for controlling a robotic device in motion using image synthesis are presented. A method includes determining local motion features based on image patches included in first and second input images captured by a camera installed on the robotic device; determining a camera motion based on the local motion features, wherein the camera motion indicates a movement of the camera between capture of the first input image and capture of the second input image; determining a scene geometry based on the camera motion, wherein the scene geometry is a set of three-dimensional coordinates corresponding to two-dimensional image coordinates of the image patches; generating a single perspective synthesized image based on the camera motion and the scene geometry; detecting a change between the first and second input images based on the synthesized image; and modifying motion of the robotic device based on the detected at least one change.

Abstract: Apparatuses, methods and storage media for providing a depth image of an object are described. In some embodiments, the apparatus may include a projector to project a light pattern on an object, and to move the projected light pattern over the object, to swipe the object with the light pattern, and a camera coupled with the projector. The camera may include a dynamic vision sensor (DVS) device, to capture changes in at least some image elements that correspond to an image of the object, during the swipe of the object with the light pattern. The apparatus may further include a processor coupled with the projector and the camera, to generate a depth image of the object, based at least in part on the changes in the at least some image elements. Other embodiments may be described and claimed.

Abstract: Apparatuses, methods and storage media for providing a depth image of an object are described. In some embodiments, the apparatus may include a projector to perform a controlled motion, to project a light pattern on different portions of the scene at different time instances, and an imaging device coupled with the projector, to generate pairs of images (a first image of a pair from a first perspective, and a second image of the pair from a second perspective), of different portions of the scene in response to the projection of the light pattern on respective portions. The apparatus may include a processor coupled with the projector and the imaging device, to control the motion of the projector, and generate the depth image of the object in the scene, based on processing of the generated pairs of images of the portions of the scene. Other embodiments may be described and claimed.

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed relating to micro-saccadic actuation for an event camera. An example event-based imaging device includes a sensor including a pixel array and an optical pathway modulator to move, via a micro-saccadic movement, one or more components of an optical pathway including the sensor to shift incident light on the pixel array to cause a change in light intensity on the pixel in at least one pixel of the pixel array.

Abstract: Methods and systems for eye tracking are disclosed. One such method obtains a plurality of images of the eye from an array camera and detects glint positions and a pupil edge of the eye in the plurality of the images. A distance from the array camera to the pupil edge may be estimated based on the glint positions. A pupil image may be generated based on selected ones of the plurality of images, the glint positions, and the estimated distance to the pupil edge. A pupil center position may be determined based on the pupil image and the glint positions.

Abstract: An illumination marker includes a light source and an optical attenuation cover coupled to the light source. The optical attenuation cover is configured to attenuate an intensity of light that passes through the optical attenuation cover based on a length of an optical path of the light through the optical attenuation cover. In some embodiments, the optical attenuation cover may be embodied as a physical barrier cover and include light-blocking structures. Additionally, in some embodiments, the illumination maker may include a diffusive or retro-reflective core rather than the light source.

Abstract: Systems, apparatuses and methods may provide for technology to detect a pose drift condition with respect to a head mounted display based on one or more first signals, to detect a reduced perception state with respect to the head mounted display based on one or more second signals, and to trigger a correction of the pose drift condition during the reduced perception state. Additionally, the reduced perception state may correspond to, for example, a blinking condition, a saccadic motion condition and/or an increased head rotation rate.

Abstract: Various embodiments may be generally directed to techniques for synchronizing operation of a flash light with operation of a camera using a rolling shutter for image capture. Various embodiments provide techniques for illuminating portions of a field of view of a camera substantially synchronously with portions of the field of view of the camera undergoing image capture. Various embodiments provide techniques for illuminating sequential sections of the camera field of view, rather than the entire field of view of the camera, at substantially the same time that a sensor of the camera performs image capture operations using corresponding portions of an image sensor, such as exposing the sensors to light from the image to be captured.

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed relating to micro-saccadic actuation for an event camera. An example event-based imaging device includes a sensor including a pixel array and an optical pathway modulator to move, via a micro-saccadic movement, one or more components of an optical pathway including the sensor to shift incident light on the pixel array to cause a change in light intensity on the pixel in at least one pixel of the pixel array.

Abstract: Technologies for camera and light source synchronization include an imaging device to detect a current location of an object in a captured image generated by the imaging device. The imaging device predicts a next location of the object in a next captured image, generated by the imaging device, based on the current location of the object. The imaging device determines an illumination interval defining a period of time during which a camera of the imaging device is to expose a set of sensor lines during the capturing of the next captured image and activates a light source of the imaging device to illuminate the object during the determined illumination interval. The set of sensor lines corresponds with the predicted next location of the object.

Abstract: A method of deriving one or more individual thoracic parameters of a subject. The method comprises instructing a subject to perform a thoracic volume manipulation, receiving a plurality of measurements of a plurality of EM signals from a thoracic intrabody area of lungs of the subject during the thoracic volume manipulation, deriving a plurality of thoracic volume values at a plurality of different intervals during the thoracic volume manipulation so that each the thoracic volume value correspond with another of a plurality of estimated thoracic volumes achieved during the thoracic volume manipulation, and calculating at least one individual thoracic parameter of the subject by combining between the plurality of measurements and the plurality of thoracic volume values.

Abstract: An odometric image capture system includes an image acquisition device that provides an image to exposure determination circuitry and motion prediction circuitry at current time=t1. One or more odometric sensors provide data representative of a first pose and movement or displacement of the odometric image capture system through a three-dimensional space. The motion prediction circuitry predicts a second pose and/or location of the odometric image capture system at a future time=t2 and also provides a prospective second image based on the second pose and/or location to the exposure determination circuitry. The exposure determination circuitry determines one or more exposure parameters using the prospective second image and communicates the exposure parameters to the image acquisition device prior to future time=t2.

Abstract: Systems, apparatuses and methods may provide for technology to detect a pose drift condition with respect to a head mounted display based on one or more first signals, to detect a reduced perception state with respect to the head mounted display based on one or more second signals, and to trigger a correction of the pose drift condition during the reduced perception state. Additionally, the reduced perception state may correspond to, for example, a blinking condition, a saccadic motion condition and/or an increased head rotation rate.

Abstract: A method of deriving one or more individual thoracic parameters of a subject. The method comprises instructing a subject to perform a thoracic volume manipulation, receiving a plurality of measurements of a plurality of EM signals from a thoracic intrabody area of lungs of the subject during the thoracic volume manipulation, deriving a plurality of thoracic volume values at a plurality of different intervals during the thoracic volume manipulation so that each the thoracic volume value correspond with another of a plurality of estimated thoracic volumes achieved during the thoracic volume manipulation, and calculating at least one individual thoracic parameter of the subject by combining between the plurality of measurements and the plurality of thoracic volume values.

Abstract: Generally, this disclosure provides systems, devices, methods and computer readable media for calibration of an eye tracking system. In some embodiments, the method may include analyzing a video stream received from a scene facing camera to detect moving objects and estimate angular locations of the moving objects. The method may also include receiving images from an eye tracking camera and estimating gaze angles of a user's eye, based on the images. The method may further include computing, for each of the moving objects, a first distance measure between the object angular locations and the gaze angles; accepting or rejecting each of the moving objects for use in calibration based on a comparison of the first distance measure to a threshold; and estimating an eye tracking calibration angle based on a minimization of a second distance measure computed between the angular locations of the accepted moving objects and the gaze angles.

Abstract: Technologies for adjusting a perspective of a captured image for display on a mobile computing device include capturing a first image of a user by a first camera and a second image of a real-world environment by a second camera. The mobile computing device determines a position of an eye of the user relative to the mobile computing device based on the first captured image and a distance of an object in the real-world environment from the mobile computing device based on the second captured image. The mobile computing device generates a back projection of the real-world environment captured by the second camera to the display based on the determined distance of the object in the real-world environment relative to the mobile computing device, the determined position of the user's eye relative to the mobile computing device, and at least one device parameter of the mobile computing device.

Abstract: Apparatuses, methods and storage media for providing a depth image of an object are described. In some embodiments, the apparatus may include a projector to perform a controlled motion, to project a light pattern on different portions of the scene at different time instances, and an imaging device coupled with the projector, to generate pairs of images (a first image of a pair from a first perspective, and a second image of the pair from a second perspective), of different portions of the scene in response to the projection of the light pattern on respective portions. The apparatus may include a processor coupled with the projector and the imaging device, to control the motion of the projector, and generate the depth image of the object in the scene, based on processing of the generated pairs of images of the portions of the scene. Other embodiments may be described and claimed.

Abstract: Apparatuses, methods and storage media for providing a depth image of an object are described. In some embodiments, the apparatus may include a projector to project a light pattern on an object, and to move the projected light pattern over the object, to swipe the object with the light pattern, and a camera coupled with the projector. The camera may include a dynamic vision sensor (DVS) device, to capture changes in at least some image elements that correspond to an image of the object, during the swipe of the object with the light pattern. The apparatus may further include a processor coupled with the projector and the camera, to generate a depth image of the object, based at least in part on the changes in the at least some image elements. Other embodiments may be described and claimed.

Abstract: A mechanism is described for facilitating eye torsion-based accurate eye tracking on computing devices according to one embodiment. A method of embodiments, as described herein, includes determining a head pose representing a tilt of a head of a person in an image captured by a capturing device of one or more capturing/sensing device. The image may illustrate one or more eyes of the person. The method may further include estimating a gravity vector relating to an eye of the one or more eyes based on data relating to the image and sensed by a sensing device of the one or more capturing/sensing devices, computing a total torsion angle based on one or more of the head pose and the gravity vector, and estimating a gaze vector associated with eye to facilitate tracking of the eye. The tracking may include positions or movements of the eye based on the gaze vector.