{"id":"W3201731711","doi":"10.1016/j.jag.2021.102564","title":"Boundary-Aware graph Markov neural network for semiautomated object segmentation from point clouds","year":2021,"lang":"en","type":"article","venue":"International Journal of Applied Earth Observation and Geoinformation","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Science Foundation of Fujian Province; National Natural Science Foundation of China","keywords":"Point cloud; Segmentation; Computer science; Artificial intelligence; Markov random field; Boundary (topology); Conditional random field; Computer vision; Artificial neural network; Laser scanning; Pattern recognition (psychology); Representation (politics); Object (grammar); Image segmentation; Laser; Mathematics","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":[0.0005330388,0.0009144212,0.001100361,0.001140753,0.0005202891,0.0007333632,0.001755463,0.001676752,0.001636529],"category_scores_gemma":[0.001403907,0.0006779947,0.001171859,0.001065248,0.0006511429,0.001421048,0.001013065,0.001272145,0.0005134059],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001273393,"about_ca_system_score_gemma":0.001082586,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01960148,"about_ca_topic_score_gemma":0.01936075,"domain_scores_codex":[0.9996015,0.0000590968,0.00002019241,0.0001588747,0.00008818625,0.00007218228],"domain_scores_gemma":[0.9995754,0.0001909358,0.00006300599,0.00004517442,0.00009743514,0.00002789024],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002053037,0.00007497449,0.0009029852,0.00008917972,0.00005596874,0.0001066925,0.00008792539,0.7481394,0.009407667,0.002859199,0.001767018,0.2363037],"study_design_scores_gemma":[0.00000186449,0.000005269913,0.00005550694,0.000002215265,0.000002704654,0.000006073355,0.000002247939,0.9986993,0.0005454654,0.0006198433,0.00005708026,0.000002275632],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03090075,0.0004371596,0.9647917,0.0001504453,0.00004561274,0.00005529447,0.0001243801,0.002592595,0.0009020684],"genre_scores_gemma":[0.6670443,0.0003933328,0.3273024,0.0003082872,0.00007293611,0.0002102507,0.0009767966,0.0002992486,0.003392441],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01960148,"threshold_uncertainty_score":0.03897482,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009966155294219518,"score_gpt":0.2319204983916049,"score_spread":0.2219543430973854,"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."}}