http://cvssp-data.eps.surrey.ac.uk/Personal/AdrianHilton/Publications_files/survey_techrep.pdf

A survey of advances in vision-based human motion capture and analysis

We constructed a corpus of digitized texts containing about 4% of all books ever printed. Analysis of this corpus enables us to investigate cultural trends quantitatively. We survey the vast terrain of 'culturomics,' focusing on linguistic and cultural phenomena that were reflected in the English language between 1800 and 2000. We show how this approach can provide insights about fields as diverse as lexicography, the evolution of grammar, collective memory, the adoption of technology, the pursuit of fame, censorship, and historical epidemiology. Culturomics extends the boundaries of rigorous quantitative inquiry to a wide array of new phenomena spanning the social sciences and the humanities.

/pdf/quantitative-analysis-of-culture-using-millions-of-digitized-1p7ygzqdx7.pdf

Quantitative analysis of culture using millions of digitized books

One of the aims of the standardization committee has been the development of Part I, which could be used on a royalty- and fee-free basis. This is important for the standard to become widely accepted. The standardization process, which is coordinated by the JTCI/SC29/WG1 of the ISO/IEC has already produced the international standard (IS) for Part I. In this article the structure of Part I of the JPFG 2000 standard is presented and performance comparisons with established standards are reported. This article is intended to serve as a tutorial for the JPEG 2000 standard. The main application areas and their requirements are given. The architecture of the standard follows with the description of the tiling, multicomponent transformations, wavelet transforms, quantization and entropy coding. Some of the most significant features of the standard are presented, such as region-of-interest coding, scalability, visual weighting, error resilience and file format aspects. Finally, some comparative results are reported and the future parts of the standard are discussed.

/pdf/the-jpeg-2000-still-image-compression-standard-2dd3aimci6.pdf

The JPEG 2000 still image compression standard

ALVINN (Autonomous Land Vehicle In a Neural Network) is a 3-layer back-propagation network designed for the task of road following. Currently ALVINN takes images from a camera and a laser range finder as input and produces as output the direction the vehicle should travel in order to follow the road. Training has been conducted using simulated road images. Successful tests on the Carnegie Mellon autonomous navigation test vehicle indicate that the network can effectively follow real roads under certain field conditions. The representation developed to perform the task differs dramatically when the network is trained under various conditions, suggesting the possibility of a novel adaptive autonomous navigation system capable of tailoring its processing to the conditions at hand.

/pdf/alvinn-an-autonomous-land-vehicle-in-a-neural-network-1s0w97pkpv.pdf

ALVINN: An Autonomous Land Vehicle in a Neural Network

This paper presents a technique for motion detection that incorporates several innovative mechanisms. For example, our proposed technique stores, for each pixel, a set of values taken in the past at the same location or in the neighborhood. It then compares this set to the current pixel value in order to determine whether that pixel belongs to the background, and adapts the model by choosing randomly which values to substitute from the background model. This approach differs from those based upon the classical belief that the oldest values should be replaced first. Finally, when the pixel is found to be part of the background, its value is propagated into the background model of a neighboring pixel. We describe our method in full details (including pseudo-code and the parameter values used) and compare it to other background subtraction techniques. Efficiency figures show that our method outperforms recent and proven state-of-the-art methods in terms of both computation speed and detection rate. We also analyze the performance of a downscaled version of our algorithm to the absolute minimum of one comparison and one byte of memory per pixel. It appears that even such a simplified version of our algorithm performs better than mainstream techniques.

/pdf/vibe-a-universal-background-subtraction-algorithm-for-video-3hbi5ckurx.pdf

ViBe: A Universal Background Subtraction Algorithm for Video Sequences

Adaptive Gaussian mixtures have been used for modeling nonstationary temporal distributions of pixels in video surveillance applications. However, a common problem for this approach is balancing between model convergence speed and stability. This paper proposes an effective scheme to improve the convergence rate without compromising model stability. This is achieved by replacing the global, static retention factor with an adaptive learning rate calculated for each Gaussian at every frame. Significant improvements are shown on both synthetic and real video data. Incorporating this algorithm into a statistical framework for background subtraction leads to an improved segmentation performance compared to a standard method.

Effective Gaussian mixture learning for video background subtraction

A meeting recorder captures multimodal information of a meeting. Subsequent analysis of the information produces scores indicative of visually and aurally significant events that can help identify significant segments of the meeting recording. Textual analysis can enhance searching for significant meeting segments and otherwise enhance the presentation of the meeting segments.

Multimodal access of meeting recordings

A M ixed M edia R eality (MMR) system and associated techniques are disclosed. The MMR system provides mechanisms for forming a mixed media document that includes media of at least two types (e.g., printed paper as a first medium and digital content and/or web link as a second medium). In one particular embodiment, the MMR system includes an action processor and method, and MMR documents with an associated action. The MMR document structure is particularly advantageous because the ability to specify different actions for different MMR documents, combined with the ability to create any number of MMR documents for a particular location on any media, allows the MMR architecture to serve as a universal trigger or initiator for additional processing. In other words, addition processing or actions can be triggered or initiated based on MMR recognition. The action processor receives the output of the MMR recognition process which yields an MMR document including at least one action. The action processor executes that action which includes various commands to the MMR system or other systems coupled to the MMR system. The MMR system architecture is advantageous because an action can be executed by pointing the capture device at a block of text, and the action is performed. Example actions include retrieving the text in electronic form to the capture device, retrieving the specification for the action, inserting data to a MMR document, transferring data between documents, purchasing items, authoring actions or reviewing historical information about actions. The MMR system includes a variety of user applications (one or more actions) initiated by the MMR recognition of a text patch such as information retrieval for a travel guide book, stock listings or advertisements; information capture such as recording content from a conference, recording and storing multimedia associated with the document, capturing information for a calendar and on the fly authoring; purchasing media files for storage on any part of an MMR document.

Triggering applications based on a captured text in a mixed media environment

A Mixed Media Reality (MMR) system and associated techniques are disclosed. The MMR system of the present invention provides mechanisms for forming a mixed media document that includes media of at least two types, such as printed paper as a first medium and a digital photograph, digital movie, digital audio file, or web link as a second medium. Furthermore, the MMR system of the present invention facilitates business methods that take advantage of the combination of a portable electronic device, such as a cellular camera phone, and a paper document.

System And Methods For Creation And Use Of A Mixed Media Environment

An apparatus and method for determining if a query document matches one or more of a plurality of documents in a database. In a coarse matching stage, a compressed file or other query document is scanned to produce a bit profile. Global statistics such as line spacing and text height are calculated from the bit profile and used to narrow the field of documents to be searched in an image database. The bit profile is cross-correlated with bit profiles of documents in the search space to identify candidates for a detailed matching stage. If multiple candidates are generated in the coarse matching stage, a set of endpoint features is extracted from the query document for detailed matching in the detailed matching stage. Endpoint features contain sufficient information for various levels of processing, including page skew and orientation estimation. In addition, endpoint features are stable, symmetric and easily computable from commonly used compressed files including, but not limited to, CCITT Group 4 compressed files. Endpoint features extracted in the detailed matching stage are used to correctly identify a matching document in a high percentage of cases.

Dar-Shyang Lee

Papers

Effective Gaussian mixture learning for video background subtraction

Multimodal access of meeting recordings

Triggering applications based on a captured text in a mixed media environment

System And Methods For Creation And Use Of A Mixed Media Environment

Compressed document matching