# An Optimized Instance Segmentation of Underlying Surface in Low-Altitude TIR Sensing Images for Enhancing the Calculation of LSTs

## TL;DR

This paper introduces a deep learning method to improve the segmentation of surfaces in low-altitude thermal infrared images, enhancing the accuracy of land surface temperature calculations.

## Contribution

A novel deep learning approach for instance segmentation of underlying surfaces in TIR images is proposed and optimized.

## Key findings

- The optimized algorithm outperformed existing methods across four evaluation indicators.
- High-quality segmented masks were generated for 150 new TIR images.
- Pixel-level classification improved the accuracy of land surface temperature calculations.

## Abstract

The calculation of land surface temperatures (LSTs) via low-altitude thermal infrared remote (TIR) sensing images at a block scale is gaining attention. However, the accurate calculation of LSTs requires a precise determination of the range of various underlying surfaces in the TIR images, and existing approaches face challenges in effectively segmenting the underlying surfaces in the TIR images. To address this challenge, this study proposes a deep learning (DL) methodology to complete the instance segmentation and quantification of underlying surfaces through the low-altitude TIR image dataset. Mask region-based convolutional neural networks were utilized for pixel-level classification and segmentation with an image dataset of 1350 annotated TIR images of an urban rail transit hub with a complex distribution of underlying surfaces. Subsequently, the hyper-parameters and architecture were optimized for the precise classification of the underlying surfaces. The algorithms were validated using 150 new TIR images, and four evaluation indictors demonstrated that the optimized algorithm outperformed the other algorithms. High-quality segmented masks of the underlying surfaces were generated, and the area of each instance was obtained by counting the true-positive pixels with values of 1. This research promotes the accurate calculation of LSTs based on the low-altitude TIR sensing images.