HyMuDS: A Hybrid Multimodal Data Acquisition System

Abstract

This paper outlines an architectural perspective for a multimodal data acquisition to be implemented in order to monitor contamination in urban waterways. The purpose is to develop an approach to detect objects and anomalies in dynamic environmental conditions. For overcoming effects of environmental variations like high reflectivity, heat waves, fog and variable illumination, an implementation with multiple camera modalities including infrared, ultraviolet and visual spectrum is proposed. Detection of a micro-level parameters related with the environment and the water, analog sensing nodes connected to a wireless gateway are deployed. Main parameters under consideration include temperature, salinity, moisture and illumination. Software architecture for a data acquisition purpose is implemented in a C# .Net development environment. This software implementation allows parallel or concurrent data acquisition operate with a greater efficiency. Another important aspect of the software architecture implemented is to allow use of heterogeneous data for post-acquisition analysis. A problem specific data storage approach is proposed and implemented to improve availability and accessibility of the acquired data. Initial trials of this system clearly indicate merits of the system proposed. This approach has a strong capability to support capturing huge information of different scenarios and with a greater efficiency.