{"id":"W2902218628","doi":"10.1016/j.isprsjprs.2018.10.007","title":"A deep learning framework for road marking extraction, classification and completion from mobile laser scanning point clouds","year":2018,"lang":"en","type":"article","venue":"ISPRS Journal of Photogrammetry and Remote Sensing","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":151,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Point cloud; Computer science; Artificial intelligence; Road surface; Cluster analysis; Deep learning; Context (archaeology); Convolutional neural network; Laser scanning; Road traffic safety; Artificial neural network; Computer vision; Data mining; Pattern recognition (psychology); Transport engineering; Road traffic; Engineering; Geography","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":[],"consensus_categories":[],"category_scores_codex":[0.0006819546,0.000150821,0.0002272919,0.00009218285,0.0006051424,0.0001380374,0.00006425483,0.0001388747,0.00002976803],"category_scores_gemma":[0.0002068729,0.0001381396,0.000080737,0.0002526602,0.0002816147,0.0001668308,0.00004226543,0.0003860508,0.000005675985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008295882,"about_ca_system_score_gemma":0.000009468933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009689272,"about_ca_topic_score_gemma":0.0001087628,"domain_scores_codex":[0.9987574,0.0001138948,0.0004046784,0.0002710427,0.0002213077,0.0002317191],"domain_scores_gemma":[0.9988582,0.0002940054,0.0004699092,0.0001412783,0.00008874948,0.0001478428],"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":[0.00008957572,0.00001657722,0.0008258068,0.000006964223,0.00002645654,0.000003475871,0.001099159,0.0002385036,0.08299931,0.000006889259,0.00004543263,0.9146419],"study_design_scores_gemma":[0.0009790558,0.0005323108,0.05532003,0.0005245777,0.000201522,0.0007871772,0.005424548,0.8758093,0.01864512,0.01004791,0.03124863,0.0004798775],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5182341,0.0001225746,0.481011,0.0001079823,0.0001609762,0.0001151983,6.24783e-7,0.00001510714,0.0002323595],"genre_scores_gemma":[0.7806192,0.0001042043,0.2187593,0.00009754172,0.0003793476,7.111042e-8,0.000003959527,0.00001815775,0.00001821543],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.914162,"threshold_uncertainty_score":0.5633169,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01650638479196665,"score_gpt":0.2831513596821171,"score_spread":0.2666449748901504,"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."}}