MFNet: Towards real-time semantic segmentation for autonomous vehicles with multi-spectral scenes
This work addresses the semantic segmentation of images of street scenes for autonomous vehicles based on a new RGB-Thermal dataset, which is also introduced in this paper. An increasing interest in self-driving vehicles has brought the adaptation of semantic segmentation to self-driving systems. However, recent research relating to semantic segmentation is mainly based on RGB images acquired during times of poor visibility at night and under adverse weather conditions. Furthermore, most of these methods only focused on improving performance while ignoring time consumption. The aforementioned problems prompted us to propose a new convolutional neural network architecture for multi-spectral image segmentation that enables the segmentation accuracy to be retained during real-time operation. We benchmarked our method by creating an RGB-Thermal dataset in which thermal and RGB images are combined. We showed that the segmentation accuracy was significantly increased by adding thermal infrared information.
PDF
PST900
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| Semantic Segmentation | GAMUS | MFNet | mIoU | 52.73 | # 6 | |
| Thermal Image Segmentation | KP day-night | MFNet | mIoU | 24.0 | # 5 | |
| Thermal Image Segmentation | MFN Dataset | MFNet | mIOU | 39.7 | # 47 | |
| Thermal Image Segmentation | Noisy RS RGB-T Dataset | MFNet | mIoU | 33.1 | # 6 | |
| Thermal Image Segmentation | PST900 | MFNet | mIoU | 57.0 | # 16 |
