Image Segmentation in Liquid Argon Time Projection Chamber Detector

TL;DR

This paper introduces a new supervised image segmentation method for Liquid Argon TPC detector images, enhancing particle track identification for neutrino research.

Contribution

It presents a novel pixel-wise feature descriptor and supervised classification approach tailored for LAr-TPC image segmentation.

Findings

Effective separation of particle tracks from noise.

Potential to improve reconstruction algorithms in neutrino detection.

Automates the segmentation process for LAr-TPC images.

Abstract

The Liquid Argon Time Projection Chamber (LAr-TPC) detectors provide excellent imaging and particle identification ability for studying neutrinos. An efficient and automatic reconstruction procedures are required to exploit potential of this imaging technology. Herein, a novel method for segmentation of images from LAr-TPC detectors is presented. The proposed approach computes a feature descriptor for each pixel in the image, which characterizes amplitude distribution in pixel and its neighbourhood. The supervised classifier is employed to distinguish between pixels representing particle's track and noise. The classifier is trained and evaluated on the hand-labeled dataset. The proposed approach can be a preprocessing step for reconstructing algorithms working directly on detector images.