Fast reconstruction-based ROI triggering via anomaly detection in the CYGNO optical TPC
Abstract
Optical-readout Time Projection Chambers (TPCs) produce megapixel-scale images whose fine-grained topological information is essential for rare-event searches, but whose size challenges real-time data selection. We present an unsupervised, reconstruction-based anomaly-detection strategy for fast Region-of-Interest (ROI) extraction that operates directly on minimally processed camera frames. A convolutional autoencoder trained exclusively on pedestal images learns the detector noise morphology without labels, simulation, or fine-grained calibration. Applied to standard data-taking frames, localized reconstruction residuals identify particle-induced structures, from which compact ROIs are extracted via thresholding and spatial clustering. Using real data from the CYGNO optical TPC prototype, we compare two pedestal-trained autoencoder configurations that differ only in their training objective, enabling a controlled study of its impact. The best configuration retains (93.0 +/- 0.2)% of reconstructed signal intensity while discarding (97.8 +/- 0.1)% of the image area, with an inference time of approximately 25 ms per frame on a consumer GPU. The results demonstrate that careful design of the training objective is critical for effective reconstruction-based anomaly detection and that pedestal-trained autoencoders provide a transparent and detector-agnostic baseline for online data reduction in optical TPCs.
Keywords
Cite
@article{arxiv.2512.24290,
title = {Fast reconstruction-based ROI triggering via anomaly detection in the CYGNO optical TPC},
author = {F. D. Amaro and R. Antonietti and E. Baracchini and L. Benussi and C. Capoccia and M. Caponero and L. G. M. de Carvalho and G. Cavoto and I. A. Costa and A. Croce and M. D'Astolfo and G. D'Imperio and G. Dho and E. Di Marco and J. M. F. dos Santos and D. Fiorina and F. Iacoangeli and Z. Islam and E. Kemp and H. P. Lima and G. Maccarrone and R. D. P. Mano and D. J. G. Marques and G. Mazzitelli and P. Meloni and A. Messina and V. Monno and C. M. B. Monteiro and R. A. Nobrega and G. M. Oppedisano and I. F. Pains and E. Paoletti and F. Petrucci and S. Piacentini and D. Pierluigi and D. Pinci and F. Renga and A. Russo and G. Saviano and P. A. O. C. Silva and N. J. Spooner and R. Tesauro and S. Tomassini and D. Tozzi},
journal= {arXiv preprint arXiv:2512.24290},
year = {2026}
}
Comments
15 pages, 7 figures, Accepted for publication in IOP Machine Learning: Science and Technology