Title Challenges with image event processing : Poster

Multimedia Tools and Applications, 2010

This paper contains a survey on aspects of visual event computing. We start by presenting events and their classifications, and continue with discussing the problem of capturing events in terms of photographs, videos, etc, as well as the methodologies for event storing and retrieving. Later, we review an extensive set of papers taken from well-known conferences and journals in multiple disciplines. We analyze events, and summarize the procedure of visual event actions. We introduce each component of a visual event computing system, and its computational aspects, we discuss the progress of each component and review its overall status. Finally, we suggest future research trends in event computing and hope to introduce a comprehensive profile of visual event computing to readers.

Simulation Modelling Practice and Theory, 2023

The extensive deployment of the Internet of things (IoT) devices in urban areas enables smart city systems (e.g., urban traffic detection and air pollution monitoring) to use these devices to discover the affected regions by various events, particularly complex ones. A complex event is inferred from patterns of different individual primitive events according to their spatio-temporal information. Complex event processing (CEP) systems facilitate applications to define their reasoning rules based on event processing languages (EPL), similar to SQL. However, current languages and CEP engines do not efficiently support spatial data characteristics. Geospatial CEP is challenging since applications have diverse definitions for complex events (e.g., air quality index), IoT devices have heterogeneous specifications/capabilities, and complex events may happen concurrently. This paper proposes the Geo-Tesla language that enables smart city applications to define spatial attributes in complex event definitions and reasoning rules. Then, we devise the GeoT-Rex CEP engine that implements geospatial operations that compiles Geo-Tesla language and processes the spatial data. The integration of Geo-Tesla and GeoT-Rex enables applications to process complex events with spatial characteristics in their reasoning rules and identify boundaries of the detected complex event (event footprint). The evaluation results from the proof of concept implementation show that our proposed solution outperforms in identifying the footprint of complex events up to 44% in the largest network size. They also show that the detection percentage in the concurrent appearance of complex events is 40% more on average than a close state-of-the-art baseline.

Proceedings of the VLDB Endowment, 2021

Advances in Deep Neural Network (DNN) techniques have revolutionized video analytics and unlocked the potential for querying and mining video event patterns. This paper details GNOSIS, an event processing platform to perform near-real-time video event detection in a distributed setting. GNOSIS follows a serverless approach where its component acts as independent microservices and can be deployed at multiple nodes. GNOSIS uses a declarative query-driven approach where users can write customize queries for spatiotemporal video event reasoning. The system converts the incoming video streams into a continuous evolving graph stream using machine learning (ML) and DNN models pipeline and applies graph matching for video event pattern detection. GNOSIS can perform both stateful and stateless video event matching. To improve Quality of Service (QoS), recent work in GNOSIS incorporates optimization techniques like adaptive scheduling, energy efficiency, and content-driven windows. This paper...

Expert Systems with Applications, Volume 39, Issue 12, 15 September 2012, Pages 10408-10419, 2012

Complex Event Processing (CEP) is considered as a promising technology for enabling the evolution of service-oriented enterprise systems towards operational aware systems. CEP effectively supports the implementation of "sense and respond" behaviours, as it enables to extract meaningful events from raw data streams originated by sensing infrastructures, for enterprise processes and applications consumption. This paper proposes a novel CEP engine conceived with ease of use, extensibility, portability, and scalability requirements in mind. More specifically, we propose a Lightweight Stage-based Event Processor (LiSEP) based on a layered architectural design. Thanks to the adoption of Staged Event-Driven Architecture principles, core event processing logic is decoupled from low-level thread management issues. This results in an easy-to-understand and extensible implementation while testing results show performance scalability. We report on the carrying out of a case study on dangerous goods monitoring in maritime transport. The objective of the case study is to develop a Proof of Concept application leveraging on LiSEP capabilities in sensor and RFID events processing for monitoring and alerting purposes. © 2012 Elsevier Ltd. All rights reserved.

Procedia Computer Science, 2020

Throughout decades, many concepts to renovate cities have surfaced such as digital city, green city, smart cities and so forth, so that citizens can reach urban services and exercise their activities easily with respect to the environment's sustainability, by limiting energy waste, optimization of urban infrastructure costs, automation of many routines and efficient allocation of human resources. In effect, decision makers varying from government administrations to private sector have log started using information technology asa mean of to evolve cities, and maintain a consistent correlation between the population culture and the environment they live in, moreover, the solutions they came up with where specific to many problems but unique to each one,as efficient as it may seem to be. Moreover, the technology sector was long ago mature enough to turn inanimate objects into smart objects that interact with each other, and send data. As a result, these solutions make it possible to extract a great amount of data, which is used to turn future predictions more accurate. Nevertheless, the technical solutions are not designed to cover data from multiple sectors, and if so, they lack the possibility to be extended with new sector layers without going through a whole development processes that can turn the old system obsolete. Therefore, as a solution in this paper,to cover new aspects and facilitate addition of new layers of data types, we brought out an abstract layer to cover not only natural events (temperature,humidity, water level, noise) that occurs in the urban field of a city, but also,urban events for example: train arrivals, accidents (traffic, security infringements), population concentration variation, etc, we called it complex events.Furthermore, we also present the architecture of a system that is scalable and supports the variety of complex events, how it collects and broadcast it to external actors.

Sensors, 2019

Smart cities are urban environments where Internet of Things (IoT) devices provide a continuous source of data about urban phenomena such as traffic and air pollution. The exploitation of the spatial properties of data enables situation and context awareness. However, the integration and analysis of data from IoT sensing devices remain a crucial challenge for the development of IoT applications in smart cities. Existing approaches provide no or limited ability to perform spatial data analysis, even when spatial information plays a significant role in decision making across many disciplines. This work proposes a generic approach to enabling spatiotemporal capabilities in information services for smart cities. We adopted a multidisciplinary approach to achieving data integration and real-time processing, and developed a reference architecture for the development of event-driven applications. This type of applications seamlessly integrates IoT sensing devices, complex event processing,...

Proceedings 22nd International Conference on Distributed Computing Systems Workshops, 2002

There are many challenges in devising solutions for online content processing of live networked multimedia sessions. These include the computational complexity of feature extraction and high-level concept recognition, the massive amount of data to be analyzed under real-time requirements and the intricate correspondence between low-level features and high-level concepts. Our approach to these challenges is a distributed architecture consisting of interacting components encapsulating feature extraction and concept classifier algorithms. The purpose of the framework is to simplify the development of applications for the domain of on-line multimedia content processing.