Home Publications Research Data Research Grants Equipment Inventions & Patents Awards Additional Research Activities Faculties & Institutions Research Areas

Hierarchical Filter Band Selection for Multispectral Object Classification

Kossira K, Seiler J, Kaup A (2026)

---

Publication Type: Conference contribution, Conference Contribution

Publication year: 2026

Event location: Tampere

DOI: 10.1109/ICIP61757.2026.11630382

Abstract

Multispectral camera arrays capture image data in various spectral bands, enabling image acquisition beyond human perception. These systems are widely used in medical, agricultural, environmental, and remote sensing applications. However, not all recorded bands are needed for classification tasks, thus reducing them can lower hardware complexity and cost. The conditional filter band selection algorithm addresses this by selecting low-noise, non-redundant bands to minimize the number of filters and cameras. This paper improves the approach by introducing a second classification stage that estimates object material in addition to the object label. This information is merged by a decision-tree based band selection strategy. The proposed method achieves a 28.9% relative reduction in classification error on the SMM50 dataset compared to the state-of-the-art. Moreover, for the same classification accuracy, the required number of cameras is reduced from 7 to 4, demonstrating that the proposed approach improves performance while significantly lowering hardware requirements.

Authors with CRIS profile

How to cite

APA:

Kossira, K., Seiler, J., & Kaup, A. (2026). Hierarchical Filter Band Selection for Multispectral Object Classification. In Proceedings of the International Conference on Image Processing (ICIP). Tampere, FI.

MLA:

Kossira, Katja, Jürgen Seiler, and André Kaup. "Hierarchical Filter Band Selection for Multispectral Object Classification." Proceedings of the International Conference on Image Processing (ICIP), Tampere 2026.

BibTeX: Download