Abstract: The present document is directed to automated and semi-automated surveillance and monitoring methods and systems that continuously record digital video, identify and characterize face tracks in the recorded digital video, store the face tracks in a face-track database, and provide query processing functionalities that allow particular face tracks to be quickly identified and used for a variety of surveillance and monitoring purposes. The currently disclosed methods and systems provide, for example, automated anomaly and threat detection, alarm generation, rapid identification of images of parameter-specified individuals within recorded digital video and mapping the parameter-specified individuals in time and space within monitored geographical areas or volumes, functionalities for facilitating human-witness identification of images of individuals within monitored geographical areas or volumes, and many additional functionalities.

Abstract: The present document is directed to automated and semi-automated surveillance and monitoring methods and systems that continuously record digital video, identify and characterize face tracks in the recorded digital video, store the face tracks in a face-track database, and provide query processing functionalities that allow particular face tracks to be quickly identified and used for a variety of surveillance and monitoring purposes. The currently disclosed methods and systems provide, for example, automated anomaly and threat detection, alarm generation, rapid identification of images of parameter-specified individuals within recorded digital video and mapping the parameter-specified individuals in time and space within monitored geographical areas or volumes, functionalities for facilitating human-witness identification of images of individuals within monitored geographical areas or volumes, and many additional functionalities.

Abstract: The present document is directed to methods and systems that identify and characterize face tracks in one or more videos that include frames that contain images of one or more human faces. In certain implementations, values for attributes, such as age, ethnicity, and gender, are assigned to face-containing subimages identified in frames of the image. The occurrence or presence of a face in a sequence of frames is identified, by comparing attributes and location and dimension parameters assigned to each occurrence of the face in a face-containing subimage within a frame, as a face track that represents a four-dimensional tube or cylinder in space time. Attributes are assigned to each face track based on attributes assigned to the occurrences of subimages of the face in frames within the face track.

Abstract: The present document is directed to methods and systems that identify and characterize subimages in images that each includes an image of a human face. In certain implementations, values for attributes, such as age, ethnicity, and gender, are assigned to face-containing subimages by the currently disclosed methods and systems. In these implementations, multiple feature-extractors output feature vectors that are distributed among attribute classifiers which consist of individual classifiers and, more often, multiple individual classifiers within aggregate classifiers. Attribute classifiers return indications of attribute values along with a probability value. Attribute classifiers are ordered with respect to reliability and applied in reliability order to generate attribute-assignment paths through a logical attribute-assignment tree, with uncertain attribute assignments generating multiple lower-level pathways.

Abstract: The present document is directed to methods and systems that identify and characterize face tracks in one or more videos that include frames that contain images of one or more human faces. In certain implementations, values for attributes, such as age, ethnicity, and gender, are assigned to face-containing subimages identified in frames of the image. The occurrence or presence of a face in a sequence of frames is identified, by comparing attributes and location and dimension parameters assigned to each occurrence of the face in a face-containing subimage within a frame, as a face track that represents a four-dimensional tube or cylinder in space time. Attributes are assigned to each face track based on attributes assigned to the occurrences of subimages of the face in frames within the face track.

Abstract: The present document is directed to methods and systems that identify and characterize subimages in images that each includes an image of a human face. In certain implementations, values for attributes, such as age, ethnicity, and gender, are assigned to face-containing subimages by the currently disclosed methods and systems. In these implementations, multiple feature-extractors output feature vectors that are distributed among attribute classifiers which consist of individual classifiers and, more often, multiple individual classifiers within aggregate classifiers. Attribute classifiers return indications of attribute values along with a probability value. Attribute classifiers are ordered with respect to reliability and applied in reliability order to generate attribute-assignment paths through a logical attribute-assignment tree, with uncertain attribute assignments generating multiple lower-level pathways.

Abstract: A distributed auction system allows remote bidders to interactively participate by computer in live auctions conducted on-site by an auctioneer. A client program that runs on the computers of the remote bidders displays real time auction status information extracted from status messages, and provides functionality of the remote bidders to submit live bids that are based on such status information. A network of nodes may be used to filter out invalid bids from the remote bidders so that such bids need not be processed by an auction server.

Abstract: A distributed auction system allows remote bidders to interactively participate by computer in live auctions conducted on-site by an auctioneer. A client program that runs on the computers of the remote bidders displays real time auction status information extracted from status messages, and provides functionality of the remote bidders to submit live bids that are based on such status information. A network of nodes may be used to filter out invalid bids from the remote bidders so that such bids need not be processed by an auction server.

Abstract: A distributed auction system allows remote bidders to interactively participate by computer in live auctions conducted on-site by an auctioneer. The system includes a console program that runs on a computer at a site of the auction. A human proxy that attends the live auction enters auction state information into an interface of the console program for real time dissemination to the remote bidders. The human proxy also receives via the interface information about valid bids placed by the remote bidders, and communicates such bids to the auctioneer. The auction state information is disseminated to the remote bidders via a set of nodes that are hierarchically connected such that different nodes are assigned to different sets of remote bidders. These nodes also filter out invalid bids received from the remote bidders, based on stored auction state information, to prevent such bids from unnecessarily being communicated to the human proxy.

Abstract: A distributed auction system allows remote bidders to interactively participate by computer in live auctions conducted on-site by an auctioneer. The system includes a console program that runs on a computer at a site of the auction. A human proxy that attends the live auction enters auction state information into an interface of the console program for real time dissemination to the remote bidders. The human proxy also receives via the interface information about valid bids placed by the remote bidders, and communicates such bids to the auctioneer. The auction state information is disseminated to the remote bidders via a set of nodes that are hierarchically connected such that different nodes are assigned to different sets of remote bidders. These nodes also filter out invalid bids received from the remote bidders, based on stored auction state information, to prevent such bids from unnecessarily being communicated to the human proxy.

Abstract: A method for distributing a live auction over the Internet to remote bidders. A human proxy attends the live auction in order to monitor the auction and compose status updates that are distributed to remote bidders via the Internet in real time to allow the remote bidders to follow the auction. Remote bidders may place bids for items that are transmitted via the Internet to the human proxy, who may then submit the bids to the auctioneer, components that facilitate distribution of the live auction over the Internet include: an auction console, an auction sever, collector/redistributor nodes, and client programs.