Investigation on Hyperspectral Augmentation to Construction Materials Classification |
|---|
| Zheng Liu, Patrick Hunhold, Ziran He, Galina Polte, Elske Linß, Janice Kielbassa, Maik Rosenberger, Gunther Notni |
- Abstract:
- The recycling of construction waste faces challenges in material identification due to class imbalance in hyperspectral datasets. To address this, we propose integrating a data augmentation module into the classification workflow for construction materials using short-wavelength infrared (SWIR) reflectance spectra. Experiments were conducted with Random Forest (RF) and 1D-CNN classifiers across multi-class and binary classification tasks, where the latter targeted classes commonly confused with minority categories. Various augmentation methods were tested, with the self-attention-based WGAN (SA-WGAN) showing the most notable improvement. It increased the recall of the minority class by up to 60 and 48 percentage points in the multi-class and binary classification tasks, respectively, while maintaining stable performance on the majority classes.
- Download:
- IMEKO-TC2-2025-008.pdf
- DOI:
- 10.21014/tc2-2025.008
- Event details
- IMEKO TC:
- TC2
- Event name:
- IMEKO TC2 PhotoMet 2025
- Title:
2025 IMEKO TC2 International Symposium on Modern Photonic Metrology
PhotoMet 2025 - Shaping the Future of Photonic Metrology
- Place:
- Modena, ITALY
- Time:
- 01 September 2025 - 03 September 2025