Patent application number | Description | Published |
20080260274 | LOCAL IMAGE DESCRIPTORS - A local image descriptor generation technique that produces a descriptor for an image patch is presented. The technique generally involves smoothing the pixels of the image patch, followed by employing a transformation to produce a transform vector for each of a set of sample points spaced across the image patch. The transform vectors are weighted and spatially accumulated to produce a prescribed number of linearly summed vectors. The linearly summed vectors are concatenated to form a raw local image descriptor, which is normalized to produce a finalized descriptor for the image patch. | 10-23-2008 |
20080267506 | INTEREST POINT DETECTION - An interest point detection technique is presented. More particularly, for each of possibly multiple image pyramid resolutions, a cornerness image is generated. One or more potential interest point locations are identified in the cornerness image. This involves finding locations associated with a pixel that exhibits a higher corner strength value than pixels in a prescribed-sized surrounding pixel neighborhood. The potential interest point locations are then clustered to identify groups that likely derive from a same 2D structure. Potential interest point locations in one or more of the identified groups are respectively combined to produce a single location that represents the combined group. The representative location of each group having one is then designated as an interest point. An optional location refinement can also be implemented. | 10-30-2008 |
20090252428 | IMAGE DESCRIPTOR QUANTIZATION - Image descriptor quantization technique embodiments are presented which quantize an image descriptor defined by a vector of number elements. This is generally accomplished by lowering the number of bits per number element to a prescribed degree. The resulting quantized image descriptor exhibits minimal loss of matching reliability while at the same time reducing the amount of storage space needed to store the descriptor in a database. Lowering the number of bits per number element also allows for increased matching speed. | 10-08-2009 |
20090310888 | MULTI-PASS IMAGE RESAMPLING - Multi-pass image resampling technique embodiments are presented that employ a series of one-dimensional filtering, resampling, and shearing stages to achieve good efficiency while maintaining high visual fidelity. In one embodiment, high-quality (multi-tap) image filtering is used inside each one-dimensional resampling stage. Because each stage only uses one-dimensional filtering, the overall computation efficiency is very good and amenable to graphics processing unit (GPU) implementation using pixel shaders. This embodiment also upsamples the image before shearing steps in a direction orthogonal to the shearing to prevent aliasing, and then downsamples the image to its final size with high-quality low-pass filtering. This ensures that none of the stages causes excessive blurring or aliasing. | 12-17-2009 |
20120114037 | COMPRESSING AND DECOMPRESSING MULTIPLE, LAYERED, VIDEO STREAMS EMPLOYING MULTI-DIRECTIONAL SPATIAL ENCODING - A process for compressing and decompressing non-keyframes in sequential sets of contemporaneous video frames making up multiple video streams where the video frames in a set depict substantially the same scene from different viewpoints. Each set of contemporaneous video frames has a plurality frames designated as keyframes with the remaining being non-keyframes. In one embodiment, the non-keyframes are compressed using a multi-directional spatial prediction technique. In another embodiment, the non-keyframes of each set of contemporaneous video frames are compressed using a combined chaining and spatial prediction compression technique. The spatial prediction compression technique employed can be a single direction technique where just one reference frame, and so one chain, is used to predict each non-keyframe, or it can be a multi-directional technique where two or more reference frames, and so chains, are used to predict each non-keyframe. | 05-10-2012 |
20120237134 | IMAGE DESCRIPTOR QUANTIZATION - Image descriptor quantization technique embodiments are presented which quantize an image descriptor defined by a vector of number elements. This is generally accomplished by lowering the number of bits per number element to a prescribed degree. The resulting quantized image descriptor exhibits minimal loss of matching reliability while at the same time reducing the amount of storage space needed to store the descriptor in a database. Lowering the number of bits per number element also allows for increased matching speed. | 09-20-2012 |
20130095920 | GENERATING FREE VIEWPOINT VIDEO USING STEREO IMAGING - Methods and systems for generating free viewpoint video using an active infrared (IR) stereo module are provided. The method includes computing a depth map for a scene using an active IR stereo module. The depth map may be computed by projecting an IR dot pattern onto the scene, capturing stereo images from each of two or more synchronized IR cameras, detecting dots within the stereo images, computing feature descriptors corresponding to the dots in the stereo images, computing a disparity map between the stereo images, and generating the depth map using the disparity map. The method also includes generating a point cloud for the scene using the depth map, generating a mesh of the point cloud, and generating a projective texture map for the scene from the mesh of the point cloud. The method further includes generating the video for the scene using the projective texture map. | 04-18-2013 |
20130100256 | GENERATING A DEPTH MAP - Methods and systems for generating a depth map are provided. The method includes projecting an infrared (IR) dot pattern onto a scene. The method also includes capturing stereo images from each of two or more synchronized IR cameras, detecting a number of dots within the stereo images, computing a number of feature descriptors for the dots in the stereo images, and computing a disparity map between the stereo images. The method further includes generating a depth map for the scene using the disparity map. | 04-25-2013 |
20130321396 | MULTI-INPUT FREE VIEWPOINT VIDEO PROCESSING PIPELINE - Free viewpoint video of a scene is generated and presented to a user. An arrangement of sensors generates streams of sensor data each of which represents the scene from a different geometric perspective. The sensor data streams are calibrated. A scene proxy is generated from the calibrated sensor data streams. The scene proxy geometrically describes the scene as a function of time and includes one or more types of geometric proxy data which is matched to a first set of current pipeline conditions in order to maximize the photo-realism of the free viewpoint video resulting from the scene proxy at each point in time. A current synthetic viewpoint of the scene is generated from the scene proxy. This viewpoint generation maximizes the photo-realism of the current synthetic viewpoint based upon a second set of current pipeline conditions. The current synthetic viewpoint is displayed. | 12-05-2013 |
20130321586 | CLOUD BASED FREE VIEWPOINT VIDEO STREAMING - Cloud based FVV streaming technique embodiments presented herein generally employ a cloud based FVV pipeline to create, render and transmit FVV frames depicting a captured scene as would be viewed from a current synthetic viewpoint selected by an end user and received from a client computing device. The FVV frames use a similar level of bandwidth as a conventional streaming movie would consume. To change viewpoints, a new viewpoint is sent from the client to the cloud, and a new streaming movie is initiated from the new viewpoint. Frames associated with that viewpoint are created, rendered and transmitted to the client until a new viewpoint request is received. | 12-05-2013 |
Patent application number | Description | Published |
20090091802 | Local Image Descriptors Using Linear Discriminant Embedding - To render the comparison of image patches more efficient, the data of an image patch can be projected into a smaller-dimensioned subspace, resulting in a descriptor of the image patch. The projection into the descriptor subspace is known as a linear discriminant embedding, and can be performed with reference to a linear discriminant embedding matrix. The linear discriminant embedding matrix can be constructed from projection vectors that maximize those elements that are shared by matching image patches or that are used to distinguish non-matching image patches, while also minimizing those elements that are common to non-matching image patches or that distinguish matching image patches. The determination of such projection vectors can be limited such that only orthogonal vectors comprise the linear discriminant embedding matrix. The determination of the linear discriminant embedding matrix can likewise be constrained to avoid overfitting to training data. | 04-09-2009 |
20090154795 | INTERACTIVE CONCEPT LEARNING IN IMAGE SEARCH - An interactive concept learning image search technique that allows end-users to quickly create their own rules for re-ranking images based on the image characteristics of the images. The image characteristics can include visual characteristics as well as semantic features or characteristics, or may include a combination of both. End-users can then rank or re-rank any current or future image search results according to their rule or rules. End-users provide examples of images each rule should match and examples of images the rule should reject. The technique learns the common image characteristics of the examples, and any current or future image search results can then be ranked or re-ranked according to the learned rules. | 06-18-2009 |
20100246969 | COMPUTATIONALLY EFFICIENT LOCAL IMAGE DESCRIPTORS - Described is a technology in which an image (or image patch) is processed into a highly discriminative and computationally efficient image descriptor that has a low storage footprint. Feature vectors are generated from an image (or image patch), and further processed via a polar Gaussian pooling approach (a DAISY configuration) into a descriptor. The descriptor is normalized, and processed with a dimension reduction component and a quantization component (based upon dynamic range reduction) into a finalized descriptor, which may be further compressed. The resulting descriptors have significantly reduced error rates and significantly smaller sizes than other image descriptors (such as SIFT-based descriptors). | 09-30-2010 |
20120183206 | INTERACTIVE CONCEPT LEARNING IN IMAGE SEARCH - An interactive concept learning image search technique that allows end-users to quickly create their own rules for re-ranking images based on the image characteristics of the images. The image characteristics can include visual characteristics as well as semantic features or characteristics, or may include a combination of both. End-users can then rank or re-rank any current or future image search results according to their rule or rules. End-users provide examples of images each rule should match and examples of images the rule should reject. The technique learns the common image characteristics of the examples, and any current or future image search results can then be ranked or re-ranked according to the learned rules. | 07-19-2012 |
20130151210 | SURFACE NORMAL COMPUTATION ON NOISY SAMPLE OF POINTS - Various technologies described herein pertain to computing surface normals for points in a point cloud. The point cloud is representative of a measured surface of a physical object. A point in the point cloud can be set as a point of origin, and points in the point cloud can be modeled as electrostatic point charges. Moreover, a point of least electrostatic potential on a sphere centered at the point of origin can be computed as a function of the electrostatic point charges. Further, unit vector with a direction from the point of origin to the point of least electrostatic potential on the sphere can be assigned as a normal for the point of origin. | 06-13-2013 |
20130321393 | SMOOTHING AND ROBUST NORMAL ESTIMATION FOR 3D POINT CLOUDS - A “Point Cloud Smoother” provides various techniques for refining a 3D point cloud or other 3D input model to generate a smoothed and denoised 3D output model. Smoothing and denoising is achieved, in part, by robustly fitting planes to a neighborhood of points around each point of the input model and using those planes to estimate new points and corresponding normals of the 3D output model. These techniques are useful for a number of purposes, including, but not limited to, free viewpoint video (FVV), which, when combined with the smoothing techniques enabled by the Point Cloud Smoother, allows 3D data of videos or images to be denoised and then rendered and viewed from any desired viewpoint that is supported by the input data. | 12-05-2013 |