{"id":"W2600004689","doi":"10.1080/01431161.2017.1302107","title":"Segmentation parameter selection for object-based land-cover mapping from ultra high resolution spectral and elevation data","year":2017,"lang":"en","type":"article","venue":"International Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Segmentation; Computer science; Elevation (ballistics); Artificial intelligence; Image segmentation; Land cover; Scale-space segmentation; Segmentation-based object categorization; Minimum spanning tree-based segmentation; Pattern recognition (psychology); Aerial image; Computer vision; Object (grammar); Remote sensing; Image (mathematics); Mathematics; Geography; Land use","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":[0.000781918,0.0007259667,0.0008983355,0.00262598,0.0004573342,0.0008045718,0.0007068386,0.0008516309,0.0007587966],"category_scores_gemma":[0.001407011,0.0003170831,0.0006119778,0.001571662,0.0004869446,0.001066078,0.0005165297,0.0004917847,0.0005835129],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003729966,"about_ca_system_score_gemma":0.0006069295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002330446,"about_ca_topic_score_gemma":0.003356938,"domain_scores_codex":[0.999624,0.00008094359,0.00003280641,0.00009881389,0.0001165584,0.00004695162],"domain_scores_gemma":[0.9996595,0.0001311939,0.00005332452,0.00005148024,0.00008386213,0.00002059018],"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":[0.0003222564,0.0002526244,0.007486783,0.0002754193,0.000155855,0.0002329828,0.0003787986,0.08758622,0.1473884,0.002392237,0.002288997,0.7512395],"study_design_scores_gemma":[0.00002659949,0.00006265125,0.0105902,0.00002216593,0.00007571409,0.000234559,0.0002120378,0.9221205,0.06004312,0.003661579,0.002899514,0.00005137407],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07675165,0.0005341015,0.9199428,0.00008133135,0.00002083965,0.00009619232,0.0001119211,0.001640653,0.0008203826],"genre_scores_gemma":[0.420588,0.0004061229,0.5772845,0.00006444792,0.00002823453,0.0001264923,0.0006828103,0.0002295624,0.0005897481],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00262598,"threshold_uncertainty_score":0.004633725,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04155739075350304,"score_gpt":0.2877838556931378,"score_spread":0.2462264649396348,"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."}}