A method of processing first video data of a region from incoming video data collected by a camera. The method includes subscribing, by a first subscriber, to an endpoint at which the first video data is published after the first video data is preprocessed according to preprocessing parameters defined within a runtime configuration file. The preprocessing includes formatting the incoming video data to create the first video data of the first region of interest with a second field of view that is less than the first field of view. The method further includes processing, by a computer processor, the first video data to determine at least one output that is indicative of a first inference dependent upon the first video data. The preprocessing parameters that format incoming video data to create the first video data are dependent upon the processing to be performed on the first video data.