Our work aims to make opportunistic crowdsensing a reliable means of detecting urban phenomena, as a component of smart city development. We believe that the optimal method for achieving this is by enforcing the cost-effective collection of high quality data. We then investigate a supporting middleware solution that reduces both the network traffic and computation at the cloud. To this end, our research focuses on defining a set of protocols that together implement "context-aware in-network collaborative mobile crowdsensing" by combining: (i) The inference of the crowdsensors' physical context so as to characterize the gathered data; (ii) The context-aware grouping of crowdsensors to share the workload and filter out low quality data; and (iii) Data aggregation at the edge to enhance the knowledge transferred to the cloud.