Abstract: An object trajectory prediction system of a vehicle includes: one or more sensors to generate sensory data corresponding to one or more objects within a range of the vehicle; one or more processors; and memory connected to the one or more processors and having instructions that, when executed by the one or more processors, cause the one or more processors to: identify a first person of interest (POI) from the sensory data; estimate a 3-dimensional (3D) pose of the first POI from the sensory data; calculate a trajectory of the first POI according to at least the 3D pose of the first POI; and determine a navigational path of the vehicle according to the trajectory of the first POI.

Abstract: An object trajectory prediction system of a vehicle includes: one or more sensors to generate sensory data corresponding to one or more objects within a range of the vehicle; one or more processors; and memory connected to the one or more processors and having instructions that, when executed by the one or more processors, cause the one or more processors to: identify a first person of interest (POI) from the sensory data; estimate a 3-dimensional (3D) pose of the first POI from the sensory data; calculate a trajectory of the first POI according to at least the 3D pose of the first POI; and determine a navigational path of the vehicle according to the trajectory of the first POI.

Abstract: Exemplary embodiments for visual communication between a first device and a second device, comprising: creating a 3D mesh model of a first device user; receiving sensor data from a sensor array during the visual communication session between the first device and the second device, wherein the image data includes motion of the first device user; determining 3D mesh model updates using the image data; transmitting the 3D mesh model updates to the second device for the second device to update display of the 3D mesh model of the first device user, wherein the update is represented as one or more of a blend shape and a relative vertex position change of the 3D mesh model.

Abstract: Exemplary embodiments for visual communication between a first device and a second device, comprising: creating a 3D mesh model of a first device user; receiving sensor data from a sensor array during the visual communication session between the first device and the second device, wherein the image data includes motion of the first device user; determining 3D mesh model updates using the image data; transmitting the 3D mesh model updates to the second device for the second device to update display of the 3D mesh model of the first device user, wherein the update is represented as one or more of a blend shape and a relative vertex position change of the 3D mesh model.

Abstract: Techniques for selecting a digital image are disclosed. The techniques may include receiving a first set of digital images, analyzing the first set of digital images to extract first image features from each of the first set of digital images, accessing a user profile, comparing the extracted first image features to a preset list of image features, ranking each digital image of the first set, selecting each digital image having a ranking that exceeds a threshold, assigning a category to each selected digital image based on a comparison of each selected digital image to a category database of digital image categories, displaying each selected digital image with the assigned category, receiving an input from the user in response to the displaying, updating the user profile and the category database based on the input, and selecting at least one subsequent digital image based on the updated user profile and category database.

Abstract: Exemplary embodiments for visual communication between a first device and a second device, comprising: creating a 3D mesh model of a first device user; receiving sensor data from a sensor array during the visual communication session between the first device and the second device, wherein the image data includes motion of the first device user; determining 3D mesh model updates using the image data; transmitting the 3D mesh model updates to the second device for the second device to update display of the 3D mesh model of the first device user, wherein the update is represented as one or more of a blend shape and a relative vertex position change of the 3D mesh model.

Abstract: Exemplary embodiments for visual communication between a first device and a second device, comprising: creating a 3D mesh model of a first device user; receiving sensor data from a sensor array during the visual communication session between the first device and the second device, wherein the image data includes motion of the first device user; determining 3D mesh model updates using the image data; transmitting the 3D mesh model updates to the second device for the second device to update display of the 3D mesh model of the first device user, wherein the update is represented as one or more of a blend shape and a relative vertex position change of the 3D mesh model.

Abstract: Exemplary embodiments for visual communication between a first device and a second device, comprising: using data from a camera system to create a 3D mesh model of a first device user, wherein the 3D mesh model is made available for storage on the second device for subsequent display on the second device; during the visual communication session between the first device and the second device, receiving sensor data from a sensor array, including image data capturing changing facial expressions and motion of the first device user; using the image data to determine 3D mesh model updates; transmitting the 3D mesh model updates to the second device for the second device to update display of the 3D mesh model of the first device user; and receiving from the second device for display on the first device at least one of a 2D video stream or updates to a 3D mesh model of a second device user.

Abstract: Techniques for selecting a digital image are disclosed. The techniques may include receiving a first set of digital images, analyzing the first set of digital images to extract first image features from each of the first set of digital images, accessing a user profile, comparing the extracted first image features to a preset list of image features, ranking each digital image of the first set, selecting each digital image having a ranking that exceeds a threshold, assigning a category to each selected digital image based on a comparison of each selected digital image to a category database of digital image categories, displaying each selected digital image with the assigned category, receiving an input from the user in response to the displaying, updating the user profile and the category database based on the input, and selecting at least one subsequent digital image based on the updated user profile and category database.

Abstract: Exemplary embodiments for visual communication between a first device and a second device, comprising: using data from a camera system to create a 3D mesh model of a first device user, wherein the 3D mesh model is made available for storage on the second device for subsequent display on the second device; during the visual communication session between the first device and the second device, receiving sensor data from a sensor array, including image data capturing changing facial expressions and motion of the first device user; using the image data to determine 3D mesh model updates; transmitting the 3D mesh model updates to the second device for the second device to update display of the 3D mesh model of the first device user; and receiving from the second device for display on the first device at least one of a 2D video stream or updates to a 3D mesh model of a second device user.

Abstract: A method for automated content insertion into a video sequence. The video sequence comprising a sequence of frames is received. An automated determination is made of non-moving pixels in the sequence of frames. Thereafter, an automated identification is made of valid regions comprising the non-moving pixels which are suitable for unobtrusive content insertion. Other embodiments, aspects and features are also disclosed.

Abstract: One embodiment relates to an automated method for estimating motion of an image segment. An image frame is segmented into irregularly-shaped image segments. Motion vectors of blocks of pixels in the image frame are estimated. A determination is made as to the blocks which overlap a segment, and candidate motion vectors are determined from the motion vectors for those overlapping blocks. A motion vector for the segment is selected from amongst the candidate motion vectors. Other embodiments, aspects, and features are also disclosed.

Abstract: One embodiment relates to a computer-implemented method for the automated extraction of objects from a video stream. The method includes an automated procedure for creating a temporal graph, and an automated procedure for cutting the graph into graph partitions. The method further includes an automated procedure for mapping the graph partitions to pixels in frames of the video stream. Other features, aspects and embodiments are also disclosed.

Abstract: One embodiment relates to a computer-implemented method of image segmentation using automated saddle point detection. An edge map is created by edge detection, and a distance map is generated based on the edge map. Saddle points are detected using the distance map. Connector pixels are determined using the saddle points, and connector pixels forming valid connecting paths are marked as edge pixels. Finally, flood filling is performed within edges to designate image segments. Other features, aspects and embodiments are also disclosed.

Abstract: One embodiment relates to a computer-implemented method for automated object recognition and classification in scenes using segment-based object extraction. The method includes automated procedures for receiving video images, creating segmentation maps from said images, grouping segments so as to form extracted objects, extracting features from said extracted objects, classifying said extracted objects using said features. Other features, aspects and embodiments are also disclosed.

Abstract: One embodiment relates to a computer-implemented method of image segmentation using automated saddle point detection. An edge map is created by edge detection, and a distance map is generated based on the edge map. Saddle points are detected using the distance map. Connector pixels are determined using the saddle points, and connector pixels forming valid connecting paths are marked as edge pixels. Finally, flood filling is performed within edges to designate image segments. Other features, aspects and embodiments are also disclosed.

Abstract: One embodiment relates to a computer-implemented method for the automated extraction of objects from a video stream. The method includes an automated procedure for creating a temporal graph, and an automated procedure for cutting the graph into graph partitions. The method further includes an automated procedure for mapping the graph partitions to pixels in frames of the video stream. Other features, aspects and embodiments are also disclosed.

Abstract: An automated method for classifying an object in a sequence of video frames. The object is tracked in multiple frames of the sequence of video frame, and feature descriptors are determined for the object for each of the multiple frames. Multiple classification scores are computed by matching said feature descriptors for the object for each of the multiple frames with feature descriptors for a candidate class in a classification database. Said multiple classification scores are aggregated to generate an estimated probability that the object is a member of the candidate class. Other embodiments, aspects and features are also disclosed.

Abstract: A process and apparatus for allocating bits between the stages of a multi-stage digital image compression scheme with quantizer feedback is disclosed. The process selects a quantization schedule (from a finite number of possibilities) for all stages that minimizes an estimate of total distortion while keeping total bit demand below a constraint; uses said schedule to actually quantize one stage of the compression scheme; selects a new quantization schedule for the remaining stages using estimates for distortion and bit demand that are updated to reflect the quantization of the previous stage; actually quantizes the next stage according to the new quantization schedule; and continues recursively until it has chosen an actual quantization scale for every stage of the compression scheme.

Abstract: A process and apparatus for allocating bits between the stages of a multi-stage digital image compression scheme with quantizer feedback is disclosed. The process selects a quantization schedule (from a finite number of possibilities) for all stages that minimizes an estimate of total distortion while keeping total bit demand below a constraint; uses said schedule to actually quantize one stage of the compression scheme; selects a new quantization schedule for the remaining stages using estimates for distortion and bit demand that are updated to reflect the quantization of the previous stage; actually quantizes the next stage according to the new quantization schedule; and continues recursively until it has chosen an actual quantization scale for every stage of the compression scheme.