Abstract: Efficient image display on a display screen (e.g., in terms of number, space, resolution, and/or distortion) is facilitated by implementing one or more specialized select and pack routines for images. That is, representative images are selected from an image database, based on desired resolution and distortion, then resized and packed into a display arrangement that enhances use of display screen space. This allows, for example, images to be sent to a user from an image database more quickly, with more desirable resolution, and less distortion than traditional display techniques.

Abstract: Described herein is a method that includes receiving multiple requests for access to an exposed media object, wherein the exposed media object represents a live media stream that is being generated by a media source. The method also includes receiving data associated with each entity that provided a request, and determining, for each entity, whether the entities that provided the request are authorized to access the media stream based at least in part upon the received data and splitting the media stream into multiple media streams, wherein a number of media streams corresponds to a number of authorized entities. The method also includes automatically applying at least one policy to at least one of the split media streams based at least in part upon the received data.

Abstract: The mechanisms described herein are directed at hosting content of a web site on multiple computing devices. A relative importance for each file associated with the web site is calculated. This relative importance is used to calculate several subsets of the content which are distributed to several devices within a computer cluster, such as a server array, peer-to-peer network, and the like. The subsets may include coded messages created using an erasure coding scheme on packets containing portions of one or more files. Upon retrieving a file, a fixed number of distinct coded messages are retrieved from the devices based on the erasure coding scheme. The file is re-created with these distinct messages. Because multiple devices hold the content, the web site may be retrieved significantly faster and the reliability is increased without consuming a large amount of storage space or bandwidth of any one computing device.

Abstract: A “Classifier Trainer” trains a combination classifier for detecting specific objects in signals (e.g., faces in images, words in speech, patterns in signals, etc.). In one embodiment “multiple instance pruning” (MIP) is introduced for training weak classifiers or “features” of the combination classifier. Specifically, a trained combination classifier and associated final threshold for setting false positive/negative operating points are combined with learned intermediate rejection thresholds to construct the combination classifier. Rejection thresholds are learned using a pruning process which ensures that objects detected by the original combination classifier are also detected by the combination classifier, thereby guaranteeing the same detection rate on the training set after pruning. The only parameter required throughout training is a target detection rate for the final cascade system.

Abstract: A “Classifier Trainer” trains a combination classifier for detecting specific objects in signals (e.g., faces in images, words in speech, patterns in signals, etc.). In one embodiment “multiple instance pruning” (MIP) is introduced for training weak classifiers or “features” of the combination classifier. Specifically, a trained combination classifier and associated final threshold for setting false positive/negative operating points are combined with learned intermediate rejection thresholds to construct the combination classifier. Rejection thresholds are learned using a pruning process which ensures that objects detected by the original combination classifier are also detected by the combination classifier, thereby guaranteeing the same detection rate on the training set after pruning. The only parameter required throughout training is a target detection rate for the final cascade system.

Abstract: A “Classifier Trainer” trains a combination classifier for detecting specific objects in signals (e.g., faces in images, words in speech, patterns in signals, etc.). In one embodiment “multiple instance pruning” (MIP) is introduced for training weak classifiers or “features” of the combination classifier. Specifically, a trained combination classifier and associated final threshold for setting false positive/negative operating points are combined with learned intermediate rejection thresholds to construct the combination classifier. Rejection thresholds are learned using a pruning process which ensures that objects detected by the original combination classifier are also detected by the combination classifier, thereby guaranteeing the same detection rate on the training set after pruning. The only parameter required throughout training is a target detection rate for the final cascade system.

Abstract: A video noise reduction technique is presented. Generally, the technique involves first decomposing each frame of the video into low-pass and high-pass frequency components. Then, for each frame of the video after the first frame, an estimate of a noise variance in the high pass component is obtained. The noise in the high pass component of each pixel of each frame is reduced using the noise variance estimate obtained for the frame under consideration, whenever there has been no substantial motion exhibited by the pixel since the last previous frame. Evidence of motion is determined by analyzing the high and low pass components.

Abstract: Image enhancement techniques are described to enhance an image in accordance with a set of training images. In an implementation, an image color tone map is generated for a facial region included in an image. The image color tone map may be normalized to a color tone map for a set of training images so that the image color tone map matches the map for the training images. The normalized color tone map may be applied to the image to enhance the in-question image. In further implementations, the procedure may be updated when the average color intensity in non-facial regions differs from an accumulated mean by a threshold amount.

Abstract: A novel enhanced beamforming technique that improves beamforming operations by incorporating a model for the directional gains of the sensors, such as microphones, and provides means of estimating these gains. The technique forms estimates of the relative magnitude responses of the sensors (e.g., microphones) based on the data received at the array and includes those in the beamforming computations.

Abstract: A landmark detection technique that can quickly detect both objects of interest and landmarks within the objects in an image using regression methods. The present fast landmark detection scheme reuses existing feature values used for object detection (e.g., face detection) to find the landmarks in an object (e.g., the eyes and mouth of the face). Hence, the technique provides landmark detection functionality at almost no cost.

Abstract: A multi-sensor sound source localization (SSL) technique is presented which provides a true maximum likelihood (ML) treatment for microphone arrays having more than one pair of audio sensors. Generally, this is accomplished by selecting a sound source location that results in a time of propagation from the sound source to the audio sensors of the array, which maximizes a likelihood of simultaneously producing audio sensor output signals inputted from all the sensors in the array. The likelihood includes a unique term that estimates an unknown audio sensor response to the source signal for each of the sensors in the array.

Abstract: Systems and methods for detecting people or speakers in an automated fashion are disclosed. A pool of features including more than one type of input (like audio input and video input) may be identified and used with a learning algorithm to generate a classifier that identifies people or speakers. The resulting classifier may be evaluated to detect people or speakers.

Abstract: Background blurring is an effective way to both preserve privacy and keep communication effective during video conferencing. The present image background blurring technique is a light weight real-time technique to perform background blurring using a fast background modeling procedure combined with an object (e.g., face) detector/tracker. A soft decision is made at each pixel whether it belongs to the foreground or the background based on multiple vision features. The classification results are mapped to a per-pixel blurring radius image to blur the background. In another embodiment, the image background blurring technique blurs the background of the image without using the object detector.

Abstract: A spatial-color Gaussian mixture model (SCGMM) image segmentation technique for segmenting images. The SCGMM image segmentation technique specifies foreground objects in the first frame of an image sequence, either manually or automatically. From the initial segmentation, the SCGMM segmentation system learns two spatial-color Gaussian mixture models (SCGMM) for the foreground and background objects. These models are built into a first-order Markov random field (MRF) energy function.

Abstract: A combined digital and mechanical tracking system and process for generating a video using a single digital video camera that tracks a person or object of interest moving in a scene is presented. This generally involves operating the camera at a higher resolution than is needed for the application, and cropping a sub-region out of the image captured that is output as the output video. The person or object being tracked is at least partially contained within the cropped sub-region. As the person or object moves within the field of view of the camera, the location of the cropped sub-region is also moved so as to keep the subject of interest within its boundaries. When the subject of interest moves to the boundary of the FOV of the camera, the camera is mechanically panned to keep the person or object inside its FOV.

Abstract: A computer network-based distributed presentation system and process is presented that controls the display of one or more video streams output by multiple video cameras located across multiple presentation sites on display screens located at each presentation site. The distributed presentation system and process provides the ability for a user at a site to customize the screen configuration (i.e., what video streams are display at any one time and in what format) for that site via a two-layer display director module. In the design layer of the module, a user interface is provided for a user to specify display priorities dictating what video streams are to be displayed on the screen over time. These display priorities are then provided to the execution layer of the module which translates them into probabilistic timed automata and uses the automata to control what is displayed on the display screen.

Abstract: Rebinning methods and arrangements are provided that significantly improve the 3D wavelet compression performance of the image based rendering data, such as, e.g., concentric mosaic image data. Through what is essentially a selective cutting and pasting process the image data is divided into stripes that are then used to form a set of multi-perspective panoramas. The rebinning process greatly improves the performance of the cross shot filtering, and thus improves the transform and coding efficiency of 3D wavelet codecs. While the region of support after rebinning may cease to be rectangular in some cases, a padding scheme and an arbitrary shape wavelet coder can be implemented to encode the result data volume of the smart rebinning. With an arbitrary shape wavelet codec, the rebinning outperforms MPEG-2 by 3.7 dB, outperforms direct 3D wavelet coder by 4.3 dB, and outperforms a reference block coder (RBC) by 3.2 dB on certain tested concentric mosaic image scenes.

Abstract: Rebinning methods and arrangements are provided that significantly improve the 3D wavelet compression performance of the image based rendering data, such as, e.g., concentric mosaic image data. Through what is essentially a selective cutting and pasting process the image data is divided into stripes that are then used to form a set of multi-perspective panoramas. The rebinning process greatly improves the performance of the cross shot filtering, and thus improves the transform and coding efficiency of 3D wavelet codecs. While the region of support after rebinning may cease to be rectangular in some cases, a padding scheme and an arbitrary shape wavelet coder can be implemented to encode the result data volume of the smart rebinning. With an arbitrary shape wavelet codec, the rebinning outperforms MPEG-2 by 3.7 dB, outperforms direct 3D wavelet coder by 4.3 dB, and outperforms a reference block coder (RBC) by 3.2 dB on certain tested concentric mosaic image scenes.

Abstract: Rebinning methods and arrangements are provided that significantly improve the 3D wavelet compression performance of the image based rendering data, such as, e.g., concentric mosaic image data. Through what is essentially a selective cutting and pasting process the image data is divided into stripes that are then used to form a set of multi-perspective panoramas. The rebinning process greatly improves the performance of the cross shot filtering, and thus improves the transform and coding efficiency of 3D wavelet codecs. While the region of support after rebinning may cease to be rectangular in some cases, a padding scheme and an arbitrary shape wavelet coder can be implemented to encode the result data volume of the smart rebinning. With an arbitrary shape wavelet codec, the rebinning outperforms MPEG-2 by 3.7 dB, outperforms direct 3D wavelet coder by 4.3 dB, and outperforms a reference block coder (RBC) by 3.2 dB on certain tested concentric mosaic image scenes.

Abstract: Methods and arrangements are provided for compressing, transporting and decompressing/rendering concentric mosaic image data. The methods and arrangements compress concentric mosaic image data using reference block coding (RBC) techniques. Such RBC techniques selectively divide each of the frames of the concentric mosaic image data into blocks, and then predictively encodes each of these blocks. Some of the blocks are independently encoded as anchor blocks. Each of the remaining blocks is encoded as a predicted block with motion compensation to the anchor frame. The resulting compressed data file includes indexing information that can be used to selectively, randomly access the compressed data during decompression/rendering. A bitstream can be selectively tailored to provide portions of the compressed data file, as needed, for example, during rendering of a particular user-selected view of the concentric mosaic image scene.