Mobile Crowdsensing with Imagery Tasks

Abstract

The amount of gadgets connected to the internet has grown rapidly in the recent years. These human owned devices can potentially be used to gather sensor data without active involvement of their owners. One of the types of platforms that contribute to the utilisation of these devices are mobile crowdsensing systems. These systems can be used for different tasks including different types of community support. While these systems are quite widely used, yet little research has been done for integration of imagery data into them which require also human involvement. This paper considers a mobile crowdsensing system where gathering data from sensors is supported by crowdsourcing human intelligence for providing both textual and visual information. We also explore the best settings for such a system. Imagery processing is integrated into an already existing mobile crowdsensing platform CrowdS. The solution was evaluated both by a limited number of real life users and by conducting simulations. The simulations represent complex scenarios with multi-level variables. The results of simulation allow suggest an efficient configuration for the parameters and characteristics of the environment used in imagery integration.