This paper presents a Decentralized Data Fusion (DDF) framework for micro-scale monitoring applications in urban environments using a mobile sensor network. Here nodes collect data along their routes and share them with other nodes in the network in an opportunistic manner. The DDF framework enables the nodes to fuse data that arrives delayed from other nodes and estimate the missing values in the time gaps. This allows the nodes to create an autonomous perception about the dynamics of the observed phenomenon. The performance of the proposed DDF framework is demonstrated in the context of an urban air pollution monitoring scenario. Simulation results show that the proposed framework is able to expand the estimated pollution data set at the expense of a slight decrease in its accuracy. The simulation results also evaluate the impact of population of nodes on the performance of the DDF framework.