# Low-Light Image Segmentation on Edge Computing System

## TL;DR

This paper presents a three-step algorithm for segmenting low-light images using brightness enhancement and a U-Net model, suitable for real-time edge computing.

## Contribution

A novel low-light image segmentation algorithm combining enhancement and U-Net for real-time edge computing is proposed.

## Key findings

- The proposed algorithm outperforms baseline models in segmentation accuracy.
- Implementation on edge computing platforms achieves real-time performance.
- Brightness and contrast enhancement improves segmentation effectiveness.

## Abstract

Segmenting low-light images, such as images showing cracks on tunnel walls, is challenging due to limited visibility. Hence, we need to combine image brightness enhancement and a segmentation algorithm. We introduce essential preliminaries, specifically highlighting deep learning-based low-light image enhancement methods and the pixel-level image segmentation algorithm. After that, we provide a three-step low-light image segmentation algorithm. The proposed algorithm begins with brightness and contrast enhancement of low-light images, followed by accurate segmentation using a U-Net model. By various experimental results, we show the performance metrics of the proposed low-light image segmentation algorithm and compare the proposed algorithm’s performance against several baseline models. Furthermore, we demonstrate the implementation of the proposed low-light image segmentation pipeline on an edge computing platform. The implementation results show that the proposed algorithm is sufficiently fast for real-time processing.