{"id":"W3130613393","doi":"10.1109/tits.2021.3055366","title":"BoundaryNet: Extraction and Completion of Road Boundaries With Deep Learning Using Mobile Laser Scanning Point Clouds and Satellite Imagery","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Intelligent Transportation Systems","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University; University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Point cloud; Convolutional neural network; Boundary (topology); Computer science; Deep learning; Artificial intelligence; Satellite; Computer vision; Feature extraction; Remote sensing; Satellite imagery; Laser scanning; Geography; Engineering; Mathematics; Laser","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":[0.0005404603,0.001137246,0.0006892206,0.001086795,0.0003491669,0.0006321507,0.001437749,0.0009810686,0.001282066],"category_scores_gemma":[0.001224815,0.0004710416,0.0007372845,0.0006215972,0.0005522354,0.001983988,0.001410062,0.001193664,0.0008589476],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005861053,"about_ca_system_score_gemma":0.0009195462,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01063199,"about_ca_topic_score_gemma":0.01278399,"domain_scores_codex":[0.9996381,0.00003594035,0.00001369996,0.0001408968,0.0001053172,0.00006607972],"domain_scores_gemma":[0.999693,0.00004975462,0.0000481746,0.00008241078,0.00009995079,0.00002666454],"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":[0.0002347583,0.0001906801,0.003562811,0.0001389704,0.00009425543,0.0002290376,0.0001649768,0.4273606,0.02989175,0.004452254,0.007795959,0.5258839],"study_design_scores_gemma":[0.000006767118,0.00003351473,0.0005910902,0.000008881434,0.000008249413,0.00004861803,0.00002382866,0.9901512,0.006500536,0.00153574,0.001082767,0.000008832419],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07546025,0.0003758127,0.9163562,0.0001603732,0.00008138052,0.0001215305,0.0004028657,0.004995091,0.002046384],"genre_scores_gemma":[0.5620747,0.0002970567,0.4280384,0.0002017989,0.00006193384,0.0001350906,0.003917783,0.0004207175,0.004852618],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01063199,"threshold_uncertainty_score":0.02114016,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01418125388484954,"score_gpt":0.2477063963741264,"score_spread":0.2335251424892769,"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."}}