Real-time electron clustering in an event-driven hybrid pixel detector

Event-driven hybrid pixel detectors with nanosecond time resolution have opened up novel pathways in modern ultrafast electron microscopy, for example in hyperspectral electron-energy loss spectroscopy or free-electron quantum optics. However, the impinging electrons typically excite more than one pixel of the device, and an efficient algorithm is therefore needed to convert the measured pixel hits to real single-electron events. Here we present a robust clustering algorithm that is fast enough to find clusters in a continuous stream of raw data in real time. Each tuple of position and arrival time from the detector is continuously compared to a buffer of previous hits until the probability of a merger with an old event becomes irrelevant. In this way, the computation time becomes independent of the density of electron arrival and the algorithm does not break the operation chain. We showcase the performance of the algorithm with a 'timepix' camera in two regimes of electron microscopy, in continuous beam emission and laser-triggered femtosecond mode.

Automated summary

In this study, a robust clustering algorithm is proposed that can find clusters in a continuous stream of raw data in real time. This algorithm converts pixel hits measured by hybrid pixel detectors to real single-electron events. By continuously comparing with previous hits, the algorithm efficiently identifies the merging of new and old events.