2026-04-13T04:46:52Zhttps://recercat.cat/oai/request

oai:recercat.cat:2117/1924822026-02-02T09:21:00Zcom_2072_1033col_2072_452950

urn:hdl:2117/192482 Weakly supervised semantic segmentation for remote sensing hyperspectral imaging Moliner, Eloi Salgueiro Romero, Luis Fernando Vilaplana Besler, Verónica Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Radiocomunicació i exploració electromagnètica::Teledetecció Remote sensing Weakly-supervised segmentation Remote sensing Hyperspectral image Teledetecció This paper studies the problem of training a semantic segmentation neural network with weak annotations, in order to be applied in aerial vegetation images from Teide National Park. It proposes a Deep Seeded Region Growing system which consists on training a semantic segmentation network from a set of seeds generated by a Support Vector Machine. A region growing algorithm module is applied to the seeds to progressively increase the pixel-level supervision. The proposed method performs better than an SVM, which is one of the most popular segmentation tools in remote sensing image applications. Peer Reviewed Postprint (published version) 2020 Conference lecture https://ieeexplore.ieee.org/document/9053384 info:eu-repo/grantAgreement/EC/H2020/759764/EU/Accurate and Scalable Processing of Big Data in Earth Observation/BigEarth Restricted access - publisher's policy Institute of Electrical and Electronics Engineers (IEEE)