{"id":"W3175466115","doi":"10.1109/tgrs.2021.3087159","title":"Building Instance Mapping From ALS Point Clouds Aided by Polygonal Maps","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University; University of Waterloo; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China","keywords":"Computer science; Point cloud; Polygon (computer graphics); Preprocessor; Segmentation; Footprint; Merge (version control); Roof; Artificial intelligence; Matching (statistics); Computer vision; Data mining; Geography; Information retrieval; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002291237,0.0002133785,0.0002029095,0.00005930787,0.0008759861,0.0001455193,0.0001304448,0.0001062776,0.00007788298],"category_scores_gemma":[0.00001413372,0.0002119888,0.00008858638,0.0006854274,0.0003917659,0.0002399373,0.000009602283,0.0003108777,0.00007585018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001301704,"about_ca_system_score_gemma":0.00004251622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002358554,"about_ca_topic_score_gemma":0.0002473027,"domain_scores_codex":[0.9980596,0.0000835207,0.0002896163,0.000742941,0.0004043278,0.0004200083],"domain_scores_gemma":[0.9991716,0.0001300384,0.00008541067,0.0003912348,0.00002352549,0.0001981812],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000007245807,0.00002757925,0.00000355418,0.000002629794,0.000008402129,0.00001591715,0.0003854691,0.0005162988,0.4343821,0.000007542206,0.0002539318,0.5643893],"study_design_scores_gemma":[0.001083269,0.00007943562,0.002038148,0.0004310769,0.00007802089,0.0005038314,0.001749469,0.2493381,0.7021392,0.007038118,0.03430218,0.001219216],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3568249,0.0000502439,0.6403098,0.001119946,0.0002868113,0.00008094314,0.0000276952,0.00006537265,0.001234355],"genre_scores_gemma":[0.7659608,0.0001361004,0.231898,0.0009251543,0.00004482828,9.592374e-8,0.000005161436,0.00001945899,0.001010333],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5631701,"threshold_uncertainty_score":0.8644652,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01127699819443388,"score_gpt":0.2284982804762981,"score_spread":0.2172212822818642,"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."}}