1,721,010 research outputs found
High-Level Surveillance Event Detection Using an Interval-Based Query Language
No full textWe propose a language based on relational algebra extended by intervals for detecting high-level surveillance events from a video stream. The operators we introduce for describing temporal constraints are based on the well-known Allen's interval relationships. The semantics of our language are clearly defined and we illustrate its usefulness by expressing typical events in it and showing the promising results of an experimental evaluation
High-Level Automatic Event Detection and User Classification in a Social Network Context
No full textWe present a framework for high-level automatic event detection and user classification in a social network context based on a novel temporal extension of relational algebra, which improves and extends our earlier work in the video surveillance context. By means of intuitive and interactive graphical user interfaces, a user is able to gain insights into the inner workings of the system as well as create new event models and user categories on the fly and track their processing through the system in both offline and online modes. Compared to an earlier version, we extended our relational algebra framework with operators suited for processing data from a social network context. As a proof-of-concept we have predefined events and user categories, such as spamming and fake users, on both a synthetic and a real data set containing data related to the interactions of users with Facebook over a 2-year period
An event detection framework supported by a smart graphical user interface
No full textWe develop a graphical user interface for defining events in a framework for detecting high-level surveillance events from a video stream, as the language used for the events may be too complex for an ordinary user. The language is based on relational algebra extended by intervals, introducing operators whose temporal constraints are described using the well-known Allen's interval relationships. The user interface captures intervals in a descriptive way, supporting the user in providing the missing parameters in a step-bystep manner. In the background, the system checks the user input for consistency and automatically transforms it into relational algebra expressions
A Framework for High-Level Event Detection in a Social Network Context Via an Extension of ISEQL
No full textWe develop a framework for the detection of high-level events in a social network context, allowing us to identify abnormal or malicious behavior such as spamming. Additionally, we can classify users by analyzing their typical behavior while logged into a social network site. The processing of (real-time) events in our framework is done via an event detection language called ISEQL, which we adapt and extend to fit the requirements of a social network setting. We evaluate our framework experimentally, showing its effectiveness and efficiency
An interval-based query language for high-level surveillance event detection
No full textWe propose a language based on relational algebra extended by intervals for detecting high-level surveillance events from a video stream. The operators we introduce for describing temporal constraints are based on the well-known Allen's interval relationships. The semantics of our language are clearly defined and we illustrate its usefulness by expressing typical events in it and showing the promising results of an experimental evaluation
An interactive framework for video surveillance event detection and modeling
No full textWe present a framework for high-level event detection in video streams based on a novel temporal extension of relational algebra. With the help of intuitive and interactive graphical user interfaces, a user can have a look at the different layers of our system to gain insights into the inner workings of the system, as well as create new events on the fly and track their processing through the system. As a proof-of-concept we have predefined events on three video surveillance data sets, but we also plan to run a demo with a live video stream generated by a local webcam
Labeling the Frames of a Video Stream with Interval Events
No full textWe propose a framework for detecting medium-level events referring to intervals of frames of a video stream. The detected events can serve as input for an earlier developed framework detecting high-level surveillance events. More specifically, we first define some specific image processing algorithms to effectively identify and track people and items in frames, and then exploit a previously-defined language based on relational algebra extended by intervals to develop both offline and online algorithms for labeling sequences of frames with descriptors such as 'person A has package X' or 'person B is in car C'. An experimental evaluation carried out on real-world data sets shows promising results in terms of both accuracy and performance
Itinerary planning with category constraints using a probabilistic approach
No full textWe propose a probabilistic approach for finding approximate solutions to rooted orienteering problems with category constraints. The basic idea is to select nodes from the input graph according to a probability distribution considering properties such as the reward of a node, the attractiveness of its neighborhood, its visiting time, and its proximity to the direct route from source to destination. In this way, we reduce the size of the input considerably, resulting in a much faster execution time. Surprisingly, the quality of the generated solutions does not suffer significantly compared to the optimal ones. We illustrate the effectiveness of our approach with an experimental evaluation also including real-world data sets
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
- …
