Context-based scene recognition from visual data in smart homes: an Information Fusion approach

Abstract

Ambient Intelligence (AmI) aims at the development of computational systems that process data acquired by sensors embedded in the environment to support users in everyday tasks. Visual sensors, however, have been scarcely used in this kind of applications, even though they provide very valuable information about scene objects: position, speed, color, texture, etc. In this paper, we propose a cognitive framework for the implementation of AmI applications based on visual sensor networks. The framework, inspired by the Information Fusion paradigm, combines a priori context knowledge represented with ontologies with real time single camera data to support logic-based high-level local interpretation of the current situation. In addition, the system is able to automatically generate feedback recommendations to adjust data acquisition procedures. Information about recognized situations is eventually collected by a central node to obtain an overall description of the scene and consequently trigger AmI services. We show the extensible and adaptable nature of the approach with a prototype system in a smart home scenario.

Ontological representation of time-of-flight camera data to support vision-based AmI

“…The framework for computer vision representation presented in [5] is based on an ontological model for the representation of context and scene entities. This model is organized into several levels compliant with the Joint Directors of Laboratories (JDL) model [16].…”

“…The larger the number of levels in the model, the greater amount of data is inferred. More details and additional information about the data described in this section can be found in the authors' web page 5 .…”

“…This model is incorporated into a framework for contextual fusion of 2-D visual information previously proposed by our research group [5]. The ontologies of the initial framework have been extended to include ToF data, specifically:…”

Simulation environment for algorithms and agents evaluation.

“…The concept of SC or smart environments (Gómez-Romero et al, 2012) itself is still emerging. Making a city "smarter" is one of the main objectives of the researches as a strategy to reduce some problems caused by the rapid growth of the urban population.…”

A Data Fusion Perspective on Human Motion Analysis Including Multiple Camera Applications

“…The developments made during this period have enabled the creation of multiple systems. Automatic Surveillance [2], Ambient Intelligence [8] or Human Computer Interaction [5] are some of them. Abnormal behavior detection is employed in Video Surveillance Systems to detect suspicious behaviors that might be assessed as a thread.…”