2026-10-10T14:42:11Zhttps://www.radar-service.eu/oai/OAIHandler

10.35097/aj4ve1c03pkan0dr2026-10-09T10:42:40Zradar4kit

https://dx.doi.org/10.35097/aj4ve1c03pkan0dr Bihler, Manuel WoodVIT_V1 Bihler, Manuel 2026 Engineering dataset Dataset info:eu-repo/semantics/openAccess https://creativecommons.org/licenses/by/4.0/legalcode Roming, Lukas Aderhold, Jochen Čibiraitė-Lukenskienė, Dovilė Schlüter, Friedrich This deep learning dataset is designed for image classification and segmentation of bulky waste. It contains 22,659 patches with dimensions of 50 × 50 × 717 px. The dataset provides both patch-wise and pixel-wise annotations, with labels categorized into two main classes and 16 subclasses. The data was acquired using a multi-sensor imaging system comprising a high-resolution VIS/RGB camera, a hyperspectral NIR camera, a thermographic camera, and a THz scanner. Multi-sensor, multispectral, multimodal, hyperspectral, image data, image classification, annotation, patch-wise, pixel-wise, ground truth, bulky waste, artificial intelligence, image processing, VIS, NIR, IR, THz, segmentation, thermographic, hyperspectral imaging, dataset, deep learning, bulky waste, wood extraction, material recovery Roming, Lukas Aderhold, Jochen Čibiraitė-Lukenskienė, Dovilė Schlüter, Friedrich eng 10.35097/yhanb6twk8t9pqku https://ror.org/0137dsz97 application/x-tar