A Performance Increment Strategy for Semantic Segmentation of Low-Resolution Images from Damaged Roads
This addresses the problem of autonomous driving in emerging countries where roads are often damaged, though it is incremental as it builds on existing methods.
The paper tackled semantic segmentation of low-resolution images from damaged roads, achieving state-of-the-art results of 79.8 and 68.8 mIoU on RTK and TAS500 test sets using a Performance Increment Strategy for Semantic Segmentation (PISSS).
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.