{"id":"W2894165434","doi":"10.1109/mgrs.2018.2854840","title":"New Frontiers in Spectral-Spatial Hyperspectral Image Classification: The Latest Advances Based on Mathematical Morphology, Markov Random Fields, Segmentation, Sparse Representation, and Deep Learning","year":2018,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Magazine","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":323,"is_retracted":false,"has_abstract":true,"ca_institutions":"Foothills Medical Centre; University of Calgary","funders":"Department of Science, Information Technology and Innovation, Queensland Government; University of Houston; Università degli Studi di Pavia; European Commission; Department of Science and Technology, Ministry of Science and Technology, India; Purdue University","keywords":"Hyperspectral imaging; Remote sensing; Pattern recognition (psychology); Computer science; Artificial intelligence; Image resolution; Spatial analysis; Mathematical morphology; Markov chain; Segmentation; Land cover; Contextual image classification; Image processing; Geography; Image (mathematics); Machine learning; Land use; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004128516,0.0002036722,0.0002274767,0.0001803107,0.0002564461,0.0001672278,0.0001080966,0.00009008261,0.00001319131],"category_scores_gemma":[0.0002614046,0.0001637574,0.00003357324,0.0004345475,0.0005775803,0.0002610848,0.00001431381,0.0002894031,0.00002350719],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006274189,"about_ca_system_score_gemma":0.00003233969,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007248432,"about_ca_topic_score_gemma":0.0001260905,"domain_scores_codex":[0.9985643,0.0001160764,0.0003270787,0.0004335074,0.0002355548,0.0003235058],"domain_scores_gemma":[0.9992232,0.0002108183,0.0000925575,0.0002908286,0.00008181212,0.0001007933],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002451861,0.00002967331,0.000887807,0.00007374681,0.00002056806,0.00007111486,0.002294898,0.007852527,0.1779298,0.00002133222,0.002419217,0.8081541],"study_design_scores_gemma":[0.0009590641,0.00007728211,0.01578516,0.00007088221,0.00002227685,0.0001072539,0.0004794117,0.9743385,0.00651775,0.001206685,0.0002337365,0.0002019674],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1505298,0.0001625287,0.8439725,0.002534401,0.0006771619,0.0003045368,9.95782e-7,0.0001252918,0.001692788],"genre_scores_gemma":[0.6665315,0.0003937261,0.3322809,0.0001706647,0.0002979146,4.465924e-7,0.000008228296,0.00002817275,0.0002884131],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.966486,"threshold_uncertainty_score":0.6677834,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01177608000025162,"score_gpt":0.2451802987250059,"score_spread":0.2334042187247543,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}