One of the main benefits of mobile participatory sensing becoming a reality is the increased knowledge it will provide about the real world, as it is expected to rely on a large number of smart and mobile devices. Nowadays, those devices have the ability to host different types of sensors that will be incorporated in every aspect of our daily lives. However, given the constantly increasing number of capable mobile devices, any participatory sensing approach should be, first and foremost, scalable. To address this challenge, we present an approach to decrease the participation of devices (in sensing tasks) in a manner that does not compromise the accuracy of the real-world information while increasing the efficiency of the overall system. To reduce the number of the devices involved, we present a probabilistic registration approach enabling only a subset of devices to register their services while still providing adequate coverage of the deployment area. Our techniques, based on a re- alistic human mobility model, allow devices to decide whether or not to register their sensing services depending on the probability of other, equivalent devices being present at the locations of their expected path. We present the design and implementation of a registration middleware based on our techniques, using which mobile devices can base their registration decision. Through experiments performed on real and simulated datasets, we show that our approach scales, while not sacrificing significant amounts of sensing coverage.