3D Tracking and Classification System Using a Monocular Camera

This paper details a 3D tracking and recognition system using a single camera. The system is able to track and classify targets in outdoors and indoors scenarios, as long as they move (at least approximately) on a plane. The system first detects and validates targets and then tracks them in a state-space employing cylindrical models (horizontal and vertical position on the ground, their radius and height) utilising Particle Filters. The tracker fuses visual measurements that utilise the targets’ foreground and colour models. Finally the system classifies the tracked objects based on the visual metrics extracted by our algorithm. We have tested our model in an outdoor setting using humans and automobiles passing through the field of view of the camera at various speeds and distances. The results presented in this paper show the validity our approach.     

eWALL: An Open-Source Cloud-Based eHealth Platform for Creating Home Caring Environments for Older Adults Living with Chronic Diseases or Frailty

Independent living of older adults is one of the main challenges linked to the ageing population. Especially those living with diseases like COPD, MCI or frailty, need more support in everyday life and this is by itself a big societal challenge with impact in multiple sectors. In this paper we present eWALL, an innovative open-source eHealth platform that aims to address these challenges by means of an advanced cloud-based infrastructure. eWALL is designed in an innovative manner and achieved technical breakthroughs in eHealth platforms, while prioritizing user and market needs that are often abandoned and are the major reason for technically sound solutions that fail. We consider this as an opportunity and we aim to change the eHealth systems’ experience for older adults and break the barriers for the penetration of ICT solutions.     

Improved Gaussian Mixture Models for Adaptive Foreground Segmentation

Adaptive foreground segmentation is traditionally performed using Stauffer and Grimson’s algorithm that models every pixel of the frame by a mixture of Gaussian distributions with continuously adapted parameters. In this paper we provide an enhancement of the algorithm by adding two important dynamic elements to the baseline algorithm: The learning rate can change across space and time, while the Gaussian distributions can be merged together if they become similar due to their adaptation process. We quantify the importance of our enhancements and the effect of parameter tuning using an annotated outdoors sequence.     

Audio-visual active speaker tracking in cluttered indoors environments

We propose a system for detecting the active speaker in cluttered and reverberant environments where more than one person speaks and moves. Rather than using only audio information, the system utilizes audiovisual information from multiple acoustic and video sensors that feed separate audio and video tracking modules. The audio module operates using a particle filter (PF) and an information-theoretic framework to provide accurate acoustic source location under reverberant conditions. The video subsystem combines in 3-D a number of 2-D trackers based on a variation of Stauffer's adaptive background algorithm with spatiotemporal adaptation of the learning parameters and a Kalman tracker in a feedback configuration. Extensive experiments show that gains are to be expected when fusion of the separate modalities is performed to detect the active speaker.     

Subclass linear discriminant analysis for video-based face recognition

We present a novel subclass Linear Discriminant Analysis algorithm for feature extraction that copes with the severe pose, expression and illumination changes present in faces extracted from far-field video streams with subjects unconstrained in their motion and uncooperative to the system. Our novelty lies on the efficient automatic generation of subclasses from the gallery faces, by exploiting their different visual appearance and not constrained by their numbers per class. The proposed feature extraction algorithm is integrated in our complete face recognition system, with modules for preprocessing, classification, and decision fusion. We demonstrate the capability of the new algorithm to automatically generate discriminable subclasses and the resulting improved classification accuracy on a challenging video-based dataset, comprising low quality and resolution faces, as well as large variations in visual appearance. Our results indicate superior recognition rate compared to any systems in the CLEAR 2007 evaluation, running on that dataset.     

Visual Detection of Events of Interest from Urban Activity

Learning patterns of human-related activities in outdoor urban spaces, and utilising them to detect activity outliers that represent events of interest, can have important applications in automatic news generation and security. This paper addresses the problem of detecting both expected and unexpected activities in the visual domain. We use a foreground extraction method to mark people and vehicles in videos from city surveillance cameras as foreground blobs. The extracted foreground blobs are then converted to an activity measure to indicate how crowded the scene is at any given video frame. The activity measure, collected over the period of a day, is used to build an activity feature vector describing that day. Day activity vectors are then clustered into different patterns of activities. Common patterns in the data are not considered important as they represent the everyday norm of urban life in that location. Outliers, on the other hand, are detected and reported as events of interest.     

Hierarchical Tree Alternative Path (HTAP) algorithm for congestion control in wireless sensor networks

Recent advances in wireless sensor networks (WSNs) have lead to applications with increased traffic demands. Research is evolving from applications where performance is not considered as a crucial factor, to applications where performance is a critical factor. There are many cases in the fields of automation, health monitoring, and disaster response that demand wireless sensor networks where performance assurances are vital, especially for parameters like power, delay, and reliability. Due to the nature of these networks the higher amount of traffic is observed when the monitored event takes place. Exactly at this instance, there is a higher probability of congestion appearance in the network. Congestion in WSNs is tackled by the employment of two methods: either by reducing the load (“traffic control”), or by increasing the resources (“resource control”). In this paper we present the Hierarchical Tree Alternative Path (HTAP) algorithm, a “resource control” algorithm that attempts, through simple steps and minor computations, to mitigate congestion in wireless sensor networks by creating dynamic alternative paths to the sink. HTAP is evaluated in several scenarios in comparison with another “resource control” algorithm (TARA), as well as with a “traffic control” algorithm (SenTCP), and also the case where no congestion control exists in the network (“no CC”). Results show that HTAP is a simple and efficient algorithm capable of dealing successfully with congestion in WSNs, while preserving the performance characteristics of the network.     

Combination of Multiple Measurement Cues for Visual Face Tracking

Visual face tracking is an important building block for all intelligent living and working spaces, as it is able to locate persons without any human intervention or the need for the users to carry sensors on themselves. In this paper we present a novel face tracking system built on a particle filtering framework that facilitates the use of non-linear visual measurements on the facial area. We concentrate on three different such non-linear visual measurement cues, namely object detection, foreground segmentation and colour matching. We derive robust measurement likelihoods under a unified representation scheme and fuse them into our face tracking algorithm. This algorithm is complemented with optimum selection of the particle filter’s object model and a target handling scheme. The resulting face tracking system is extensively evaluated and compared to baseline ones.