{"id":"W4320176508","doi":"10.1016/j.isprsjprs.2023.01.009","title":"Road object detection for HD map: Full-element survey, analysis and perspectives","year":2023,"lang":"en","type":"article","venue":"ISPRS Journal of Photogrammetry and Remote Sensing","topic":"Automated Road and Building Extraction","field":"Engineering","cited_by":20,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Computer science; Object (grammar); Object detection; Road surface; Road map; Construct (python library); Artificial intelligence; Computer vision; Key (lock); Segmentation; Geography; Cartography; Engineering; Computer security","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":[0.0003229225,0.0005208662,0.0003854368,0.001490861,0.0002067386,0.0008672671,0.0005217211,0.0005109673,0.005835049],"category_scores_gemma":[0.0005358699,0.0003476012,0.0003769901,0.001527686,0.0003086728,0.001271499,0.0004926024,0.0002499719,0.002670042],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002027475,"about_ca_system_score_gemma":0.0003483015,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004836822,"about_ca_topic_score_gemma":0.008054727,"domain_scores_codex":[0.9997554,0.00002697012,0.000007033898,0.00004738706,0.000119272,0.00004382026],"domain_scores_gemma":[0.9996327,0.00006556651,0.00001524958,0.00006861908,0.0002017425,0.00001613653],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003003653,0.0002051323,0.02653423,0.0005717612,0.00009552791,0.0002082689,0.0002740149,0.03939465,0.1586694,0.003819178,0.006203047,0.7637244],"study_design_scores_gemma":[0.00002372298,0.0002470759,0.1659346,0.0001148095,0.0001696232,0.001474211,0.001414697,0.6366031,0.1310253,0.01169553,0.05118597,0.000111402],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.2580767,0.002380667,0.7136584,0.0007137876,0.00009011477,0.0001147643,0.00462056,0.002903925,0.0174411],"genre_scores_gemma":[0.7583121,0.001561277,0.2257139,0.0001451541,0.00007029417,0.00004964507,0.00396441,0.0002906905,0.009892507],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.005835049,"threshold_uncertainty_score":0.01952022,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01726824336076558,"score_gpt":0.2594019683470514,"score_spread":0.2421337249862859,"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."}}