Back to Search Start Over

A Performance Increment Strategy for Semantic Segmentation of Low-Resolution Images from Damaged Roads

Authors :
Toledo, Rafael S.
Oliveira, Cristiano S.
Oliveira, Vitor H. T.
Antonelo, Eric A.
von Wangenheim, Aldo
Publication Year :
2024

Abstract

Autonomous driving needs good roads, but 85% of Brazilian roads have damages that deep learning models may not regard as most semantic segmentation datasets for autonomous driving are high-resolution images of well-maintained urban roads. A representative dataset for emerging countries consists of low-resolution images of poorly maintained roads and includes labels of damage classes; in this scenario, three challenges arise: objects with few pixels, objects with undefined shapes, and highly underrepresented classes. To tackle these challenges, this work proposes the Performance Increment Strategy for Semantic Segmentation (PISSS) as a methodology of 14 training experiments to boost performance. With PISSS, we reached state-of-the-art results of 79.8 and 68.8 mIoU on the Road Traversing Knowledge (RTK) and Technik Autonomer Systeme 500 (TAS500) test sets, respectively. Furthermore, we also offer an analysis of DeepLabV3+ pitfalls for small object segmentation.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2411.16295
Document Type :
Working Paper