Event cameras are a new type of image sensor. The pixels of these sensors operate independently and asynchronously from each other. The sensor output is a variable rate data stream that spatio-temporally encodes the detection of brightness changes. This type of output and sensor operating paradigm poses processing challenges for computer vision applications, as frame-based methods are not natively applicable.

We provide the first systematic evaluation of different state-of-the-art deep learning based instance segmentation approaches in the context of event-based outdoor surveillance. For processing, we consider transforming the event output stream into representations of different dimensionalities, including point-, voxel-, and frame-based variants. We introduce a new dataset variant that provides annotations at the level of instances per output event, as well as a density-based preprocessing to generate regions of interest (RoI).

The achieved instance segmentation results show that the adaptation of existing algorithms for the event-based domain is a promising approach.