Various kinds of waste are generated in our daily life. The amount of waste disposal varies significantly in both spatial and temporal dimensions, Such fine-grained information on the spatio-temporal distributions of garbage disposal is expected to be utilized for novel applications in waste collection service, urban planing and garbage reduction. In this Pitch, we propose DeepCounter, an automotive sensing system mounted on garbage trucks where the videos of garbage collection are processed for detection of the category such like burnable or non-burnable and amount of collected garbage bags of the corresponding category. I would like to introduce the findings of this research, and contribute to the realization of 'Sustainable Cities and Communities', one of the goals of the SDGs