{"id":"W318364127","doi":"10.1016/j.isprsjprs.2015.04.010","title":"Scale parameter selection by spatial statistics for GeOBIA: Using mean-shift based multi-scale segmentation as an example","year":2015,"lang":"en","type":"article","venue":"ISPRS Journal of Photogrammetry and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":160,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Segmentation; Panchromatic film; Computer science; Spatial analysis; Scale-space segmentation; Scale (ratio); Image segmentation; Pattern recognition (psychology); Artificial intelligence; Histogram; Segmentation-based object categorization; Data mining; Image resolution; Computer vision; Remote sensing; Image (mathematics); Cartography; Geology; Geography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001159431,0.001003447,0.00115365,0.002566734,0.0006632952,0.00148945,0.0006407715,0.001229878,0.001265571],"category_scores_gemma":[0.002276249,0.0004122407,0.001147139,0.002233828,0.0004549233,0.0009189948,0.0005641666,0.000668001,0.0007347125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004007446,"about_ca_system_score_gemma":0.0008343383,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008222648,"about_ca_topic_score_gemma":0.01118076,"domain_scores_codex":[0.9996812,0.00009974108,0.00002172088,0.00008116459,0.00006048771,0.00005568097],"domain_scores_gemma":[0.9994142,0.000259883,0.00005119073,0.00008703412,0.0001591417,0.00002847178],"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":[0.0009385534,0.0002647745,0.01129472,0.0002868189,0.000253303,0.0006003694,0.000284131,0.3452687,0.07282051,0.008103245,0.004328435,0.5555564],"study_design_scores_gemma":[0.0000192961,0.00003641909,0.00397234,0.00001319627,0.00004167791,0.00008665902,0.00007199601,0.9828385,0.008446502,0.003130326,0.001320721,0.00002245961],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1377468,0.0006583103,0.8562139,0.000386527,0.00006694737,0.00007475354,0.0002874316,0.002205132,0.002360333],"genre_scores_gemma":[0.5716231,0.0004393377,0.4249051,0.00008948857,0.00005508191,0.00005313903,0.0006227659,0.0007163553,0.001495682],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008222648,"threshold_uncertainty_score":0.01634955,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04808426296852533,"score_gpt":0.2918447130145981,"score_spread":0.2437604500460728,"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."}}