{"id":"W2755209119","doi":"10.5194/isprs-archives-xlii-2-w7-285-2017","title":"A COMPARISON OF TREE SEGMENTATION METHODS USING VERY HIGHDENSITY AIRBORNE LASER SCANNER DATA","year":2017,"lang":"en","type":"article","venue":"˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Point cloud; Lidar; Segmentation; Tree (set theory); Range (aeronautics); Remote sensing; Computer science; Precision and recall; Kappa; Laser scanning; Statistics; Point (geometry); Mathematics; Scanner; Artificial intelligence; Laser; Optics; Geography; Geometry; Physics","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":["metaepi_narrow","sts"],"consensus_categories":["sts"],"category_scores_codex":[0.002105752,0.0004011173,0.000520995,0.0004881007,0.002303219,0.0007724643,0.002912021,0.0001029815,0.00001476375],"category_scores_gemma":[0.0009680981,0.0002642869,0.0002987687,0.0006252717,0.005122643,0.0008369494,0.002485144,0.0004138627,0.000004425701],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007847519,"about_ca_system_score_gemma":0.0001978694,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.8352845,"about_ca_topic_score_gemma":0.2381008,"domain_scores_codex":[0.9952698,0.0004077987,0.001532898,0.0005160501,0.001807726,0.0004656826],"domain_scores_gemma":[0.994727,0.0008829046,0.002838365,0.001209868,0.0001852502,0.0001566603],"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":[0.0001179132,0.00003286473,0.001488145,0.00002672057,0.00008056583,1.673148e-7,0.002754956,0.006379934,0.01120517,0.000002666136,0.00008369546,0.9778272],"study_design_scores_gemma":[0.0006094319,0.00008623903,0.01923682,0.0002221063,0.00008059363,0.00006481435,0.001538575,0.9432523,0.02946183,0.002749716,0.002420669,0.0002769531],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05118985,0.00001791802,0.9339652,0.002760046,0.001372908,0.0006244801,0.000129562,0.00003211791,0.009907936],"genre_scores_gemma":[0.9731712,0.00006171665,0.02605967,0.0004334201,0.0001076624,1.723013e-7,0.00005725004,0.00001239484,0.00009651269],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9775503,"threshold_uncertainty_score":0.9999809,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05085539840999888,"score_gpt":0.3453734259288619,"score_spread":0.2945180275188631,"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."}}