Shailendra K. Bhonsle

A Binding Architecture for Multimedia Networks

An open architecture that achieves seamless binding between networking and multimedia devices is proposed. The building blocks of the binding architecture consist of a set of interfaces, methods and primitives. The former abstract the functionalities of multimedia networking devices and are organized into a binding interface base. The methods and primitives are invoked for implementing binding applications. The binding architecture is embedded into a reference model for multimedia networking architectures that supports a clean separation between binding interfaces and binding algorithms. Communication between the interfaces of the architecture is supported by CORBA. Public interfaces in the binding interface base are specified using CORBA IDL. The architecture is illustrated with a simple connection management algorithm and an example of computational binding.

Active Camera Networks and Semantic Event Databases for Intelligent Environments

In the future, intelligent rooms, with embedded multimodal sensory systems and semantic event databases, will support effective and efficient transactions of human activities and interactions. We are pursuing rigorous experimental investigations towards the development of such intelligent environments. In this paper we describe the overall system specification and general framework guiding our development. We also present details of the modules associated with the control and interpretation of video information acquired by a network of cameras and a novel semantic event database for characterization and recognition of activities. Evaluations of the system in a custom-built intelligent room are also presented.

Database-centered architecture for traffic incident detection, management, and analysis

This paper presents various issues related to the development of an integrated software architecture for a traffic incident monitoring, mitigation, and analysis system. The novel concept of using a set of distributed databases, having many different functions and types, is proposed for distributed coordination of sensing, control and analysis algorithms. This coordination paradigm using databases makes the whole architecture robust by providing means to efficiently manage current and past states of the monitored environment and the monitoring system. Use of a semantic event/activity database in the integrated architecture also provides high level abstractions through its query language to model traffic incidents and traffic behaviors. We also present experimental results of the use of a concrete database-centered architecture and algorithms in identifying important traffic flow events (such as tail-gating, exit from a ramp, etc.).

Database architecture for autonomous transportation agents for on-scene networked incident management (ATON)

A collection of distributed databases forms an important architectural component of the ATON project for networked incidence management of highway traffic. The database sub-architecture supports the architectural integration of many thematic areas of the ATON, and provides many high level abstractions that semantically correspond to traffic incidents. These databases are queried for the detection of local or distributed traffic incidents by many distributed control and analysis algorithms. The abstract database sub-architecture leads to many databases of different types having different functions. The semantic event/activity database is one of them. The distributed multi-sensory sub-architecture detects atomic semantic events that occur in the environment. The event/activity database stores them and their temporal structures. An activity is a temporal composition of atomic events. A specialized query language is used to flexibly define and detect activities of interest. The query language embodies high level semantic pattern matching abstractions. Preliminary results of using the event/activity database are also presented.

Complex Visual Activity Recognition Using a Temporally Ordered Database

We propose using a temporally ordered database for complex visual activity recognition. We use a temporal precedence relation together with the assumption of fixed bounded temporal uncertainty of occurrence time of an atomic activity and comparatively large temporal extent of the complex activity. Under these conditions we identify the temporal structure of complex activities as a semiorder and design a database that has semiorder as its data model. A query algebra is then defined for this data model.

Retargetable stub generator for a remote procedure call facility

Abstract A remote procedure call system to support calls from Lisp clients to C servers is extended by defining a language to specify how stub code is to be generated for a target language, and implementing a language-independent code generator to execute the stub generation specifications. Knowledge about a target language is therefore captured in a high level specification, yielding a retargetable design. This approach may be applied to handle other problems of heterogeneous computing environments.

Semiorder database for complex activity recognition in multi-sensory environments

A prototype semiorder database used for activity recognition in multi-sensory monitoring environments is described. Activities are spatio-temporal compositions of events, which are a type of atomic semantic units for such compositions. The focus is on the temporal composition of activities from events in the presence of bounded duration of temporal uncertainty in an event occurrence. Such temporal uncertainty forces the concurrency between event occurrences to be intransitive. Under certain assumptions, a subclass of partial orders, known as semiorders, models such intransitive concurrency appropriately. The semiorder database stores events and their semiorder temporal order of occurrences. A semiorder data model and the corresponding query language that embeds a semiorder pattern language are the main constituents of the semiorder database. We demonstrate this database and queries for activity recognition in a real time environment. The demonstration also includes a transducer subsystem for detection of events.