Abstract: A “Video Browser” provides interactive browsing of unique events occurring within an overall video recording. In particular, the Video Browser processes the video to generate a set of video sprites representing unique events occurring within the overall period of the video. These unique events include, for example, motion events, security events, or other predefined event types, occurring within all or part of the total period covered by the video. Once the video has been processed to identify the sprites, the sprites are then arranged over a background image extracted from the video to create an interactive static video montage. The interactive video montage illustrates all events occurring within the video in a single static frame. User selection of sprites within the montage causes either playback of a portion of the video in which the selected sprites were identified, or concurrent playback of the selected sprites within a dynamic video montage.

Abstract: A “texture generator” uses an inverse texture synthesis solution that runs in the opposite direction to traditional forward synthesis techniques to construct 2D texture compactions for use by a graphics processing unit (GPU) of a computer system. These small 2D texture compactions generally summarize an original globally variant texture or image, and are used to reconstruct the original texture or image, or to re-synthesize new textures or images under user-supplied constraints. In various embodiments, the texture generator uses the texture compaction to provide real-time synthesis of globally variant textures on a GPU, where texture memory is generally too small for large textures. Further, the texture generator provides an optimization framework for inverse texture synthesis which ensures that each input region is properly encoded in the output compaction. In addition, the texture generator also computes orientation fields for anisotropic textures containing both low- and high-frequency regions.

Abstract: 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.

Abstract: A “Variable-Rate Perfect Hasher” maps sparse variable-rate data of one or more dimensions into a hash table using a perfect hash function. In various embodiments, perfect hash tables are populated by first computing offset table address for each data point of a domain of sparse variable-rate data elements. Offset vectors are then computed for each offset table address based in part on the size of each data element by evaluating offset vectors in order of a sum of the data point addresses mapping to each offset vector. These offset vectors are then stored in the offset table. For each data point, the corresponding offset vector is then used to compute a hash table address. Data elements are then perfectly hashed into the hash table using the computed hash table addresses. The resulting hash tables support efficient random access of the variable-sized data elements stored therein.

Abstract: A gigapixel image is generated from a set of images in raw format depicting different portions of a panoramic scene that has up to a full spherical field of view. Radiometric alignment of the images creates a set of images in radiance format. Geometric alignment of the radiance format images creates a set of true poses for the images in radiance format. A gigapixel image depicting the entire scene is assembled from the set of radiance format images and radiance format true poses for the images. The set of images in raw format is captured using a conventional digital camera, equipped with a telephoto lens, attached to a motorized head. The head is programmed to pan and tilt the camera in prescribed increments to individually capture the images at a plurality of exposures and with a prescribed overlap between images depicting adjacent portions of the scene.

Abstract: An audio user interface (UI) for comparing and selecting audio streams is presented. In general, the present invention allows a user to preview and navigate among multiple audio streams (audio sources) using three dimensional (3D) positional audio techniques to position the various sources in an audio field programmatically in such a way as to fool the brain into thinking the sound is located at a particular location in the space surrounding the user. When the user selects a preview mode, the various streams are placed in the space in a carousel-like manner. The user can move the sources forward or backward. As this is done, other audio streams can be added and dropped. Selecting a sound source will cause it to fill the audio field and the other sources will then cease to play.

Abstract: A location recognition technique that involves using a query image to identify a depicted location is presented. In addition to the query image, there is also a pre-constructed database of features which are associated with images of known locations. The technique matches features derived from the query image to the database features using a specialized vocabulary tree, which is referred to as an informative feature vocabulary tree. The informative feature vocabulary tree is specialized because it was generated using just those database features that have been deemed informative of known locations. The aforementioned matching features are used to identify a known location image that matches the query image. The location associated with that known location image is then deemed to be the location depicted in the query image.

Abstract: An interactive, multi-media presentation viewing system and process for viewing educational or business presentations integrating presentation graphics in the form of presentation slides, video, audio, text, and other streaming media into a powerfully coordinated viewing experience for the end user. The viewing system is an aggregate of synchronized presentation graphics, video, and text displays employing a graphical user interface that allows the user to control all aspects of media playback.

Abstract: A simplified general model and an associated estimation algorithm is provided for modeling visual data such as a video sequence. Specifically, images or frames in a video sequence are represented as collections of flat moving objects that change their appearance and shape over time, and can occlude each other over time. A statistical generative model is defined for generating such visual data where parameters such as appearance bit maps and noise, shape bit-maps and variability in shape, etc., are known. Further, when unknown, these parameters are estimated from visual data without prior pre-processing by using a maximization algorithm. By parameter estimation and inference in the model, visual data is segmented into components which facilitates sophisticated applications in video or image editing, such as, for example, object removal or insertion, tracking and visual surveillance, video browsing, photo organization, video compositing, etc.

Abstract: A focal length estimation technique is presented that estimates the focal length used to capture each of a pair of overlapping images taken by a camera rotating about its center. When it is known that the focal length is the same for both images, it is estimated using just two pairs of corresponding points between the images. When it is either unknown whether the focal lengths are the same or it is known that they vary, the focal length of each image is estimated using just three pairs of corresponding points between the images.

Abstract: A graph layout technique that creates a layered graph layout with a given aspect ratio. The present layered graph layout technique better utilizes the available space and, at the same time, creates an aesthetically pleasing drawing of a directed graph. In one embodiment it determines the layout of the new graph based on a modified Sugiyama technique combined with a modified Coffman-Graham scheduling algorithm. Given a directed graph and a desired aspect ratio, it uses a binary search and the Coffman-Graham scheduling algorithm to find a layout of the graph that has an aspect ratio that matches the given aspect ratio of the available space.

Abstract: An energy based technique to estimate the positions of people speaking from an ad hoc network of microphones. The present technique does not require accurate synchronization of the microphones. In addition, a technique to normalize the gains of the microphones based on people's speech is presented, which allows aggregation of various audio channels from the ad hoc microphone network into a single stream for audio conferencing. The technique is invariant of the speaker's volumes thus making the system easy to deploy in practice.

Abstract: An echo cancellation technique that can process multi-input microphone signals with only a small increase in the overall CPU consumption compared to implementing the algorithm for a single channel microphone signal. Furthermore, the invention provides an architecture that provides for echo cancellation for multiple applications in parallel with only a small increase in CPU consumption compared to a single instance of echo cancellation with a single microphone input and multi-output channel playback.

Abstract: A system and process for broadcast and communication with bi-level or sketch video at extremely low bandwidths is described. Essentially, bi-level and sketch video presents the outlines of the objects in a scene being depicted. Bi-level and sketch video provides a clearer shape, smoother motion, shorter initial latency and cheaper computational cost than do conventional DCT-based video compression methods. This is accomplished by converting each color or gray-scale image frame to bi-level or sketch image frame using adaptive thresholding method, compressing bi-level or sketch image frames into bi-level or sketch video using adaptive context-based arithmetic coding method. Bi-level or sketch video is particularly suitable to such small devices as Pocket PCs and mobile phones that possess small display screen, low bandwidth connection, and light computational power.

Abstract: A “speech onset detector” provides a variable length frame buffer in combination with either variable transmission rate or temporal speech compression for buffered signal frames. The variable length buffer buffers frames that are not clearly identified as either speech or non-speech frames during an initial analysis. Buffering of signal frames continues until a current frame is identified as either speech or non-speech. If the current frame is identified as non-speech, buffered frames are encoded as non-speech frames. However, if the current frame is identified as a speech frame, buffered frames are searched for the actual onset point of the speech. Once that onset point is identified, the signal is either transmitted in a burst, or a time-scale modification of the buffered signal is applied for compressing buffered frames beginning with the frame in which onset point is detected. The compressed frames are then encoded as one or more speech frames.

Abstract: The concurrent presentation technique provides information about content related to a source media currently being presented to a user in a fashion that allows the user to keep viewing the source media while either interactively or non-interactively perusing a list of related content. Thus, the user can see a list of related content without interrupting the presentation experience, and if desired, the user can choose to interact with the list to obtain further information about available related content.

Abstract: A “Joint Bilateral Upsampler” uses a high-resolution input signal to guide the interpolation of a low-resolution solution set (derived from a downsampled version of the input signal) from low-to high-resolution. The resulting high-resolution solution set is then saved or applied to the original input signal to produce a high-resolution output signal. The high-resolution solution set is close to what would be produced directly from the input signal without downsampling. However, since the high-resolution solution set is constructed in part from a downsampled version of the input signal, it is computed using significantly less computational overhead and memory than a solution set computed directly from a high-resolution signal. Consequently, the Joint Bilateral Upsampler is advantageous for use in near real-time operations, in applications where user wait times are important, and in systems where computational costs and available memory are limited.

Abstract: Images are automatically annotated using semantic distance learning. Training images are manually annotated and partitioned into semantic clusters. Semantic distance functions (SDFs) are learned for the clusters. The SDF for each cluster is used to compute semantic distance scores between a new image and each image in the cluster. The scores for each cluster are used to generate a ranking list which ranks each image in the cluster according to its semantic distance from the new image. An association probability is estimated for each cluster which specifies the probability of the new image being semantically associated with the cluster. Cluster-specific probabilistic annotations for the new image are generated from the manual annotations for the images in each cluster. The association probabilities and cluster-specific probabilistic annotations for all the clusters are used to generate final annotations for the new image.

Abstract: A photo illumination technology that facilitates user selectable illumination of an existing photo ranging from full artificial flash illumination to ambient light illumination and every gradation between. The technology in one embodiment employs a digital camera feature that captures two photos hundredths of a second apart where one photo is captured in concert with a flash and one is captured with no flash. Compensations are made to reconcile any movement of the subject matter that may have occurred between the two photos and the user is presented with the infinite gradations of illumination on the subject matter when selecting a photo for display or printing.