About
21
Publications
6,111
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
126
Citations
Introduction
Human Action Recognition, Pose Estimation, Self-driving cars, Autonomous Vehicles
Publications
Publications (21)
The task of human action recognition (HAR) can be found in many computer vision practical applications. Various data modalities have been considered for solving this task, including joint-based skeletal representations which are suitable for real-time applications on platforms with limited computational resources. We propose a spatio-temporal neura...
Space Surveillance and Tracking is a task that requires the development of systems that can accurately discriminate between natural and man-made objects that orbit around Earth. To manage the discrimination between these objects, it is required to analyze a large amount of partially annotated astronomical images collected using a network of on-grou...
Action recognition plays an important role in various applications such as video monitoring, automatic video indexing, crowd analysis, human-machine interaction, smart homes and personal assistive robotics. In this paper, we propose improvements to some methods for human action recognition from videos that work with data represented in the form of...
Robust action recognition methods lie at the cornerstone of Ambient Assisted Living (AAL) systems employing optical devices. Using 3D skeleton joints extracted from depth images taken with time-of-flight (ToF) cameras has been a popular solution for accomplishing these tasks. Though seemingly scarce in terms of information availability compared to...
Context-awareness is central to many applications in Ambient Intelligence. The paper presents the functionality of a context reasoning engine, called CONSERT, for developing ambient intelligence applications, which builds on semantic complex event processing. The implementation of core rule processing using the DROOLS Fusion framework and the advan...
The field of assistive robotics is gaining traction in both research as well as industry communities. However, capabilities of existing robotic platforms still require improvements in order to implement meaningful human-robot interactions. We report on the design and implementation of an external system that significantly augments the person detect...
This paper proposes a new algorithm for object recognition with high precision and an efficient execution time using the Kinect sensor. The proposed algorithm is based on geometric hashing and provides a more detailed geometric description of objects that can be further used to identify object parts or other information localized on the object's su...
The main components of a supervising system is detecting and tracking of the supervised person in an intelligent room. This paper presents architecture for a non-intrusive multi-agent system for person detection and tracking. The main objective of this system is to offer continuity over the user’s movement, as it can be controlled in such a way so...
This work studies the problem of the emergence of norms in multi-agent systems. Based on a socially interactive game environment for the "rules of the road" problem, of choosing a side of the road to drive on, a series of simulations are run in order to highlight the importance of the topology of the network underlying the multi-agent system and th...
Activity recognition is an important component for the ambient assisted living systems which perform home monitoring and assistance for elderly people or patients with risk factors. This paper presents a prototype system for activity recognition using information provided by four Kinects. First the posture of the supervised person is detected using...
This article studies the problem of norm emergence in the context of multi-agent systems (MAS). The agents of a certain MAS repeatedly play the Ultimatum game, by means of individual social interactions. The simulations are run and, afterwards, studied, for different learning strategies (a normative advisor model and a social model), and for differ...
In this paper we propose an approach for the experimental analysis of the classical problem of the Tragedy of the Commons. This approach revolves around norms within multi-agent systems, without regimenting them. The proposed model allows norms to emerge between selfish agents that compete for the same resource. The paper shows how the emerging nor...
Norms establish many aspects of human behavior. While most of them are considered to be optional, some are used to create laws that govern our lives. In multi-agent systems (MAS), norms are very useful in establishing and sustaining a social order for the general behavior of the agents, while increasing cooperation and coordination, and reducing co...