{"id":"W2911823924","doi":"10.1109/jsen.2019.2893892","title":"Outdoor Semantic Segmentation for UGVs Based on CNN and Fully Connected CRFs","year":2019,"lang":"en","type":"article","venue":"IEEE Sensors Journal","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"State Key Laboratory of Robotics; National Natural Science Foundation of China","keywords":"Artificial intelligence; RGB color model; Computer vision; Point cloud; Computer science; Segmentation; Image segmentation","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":[0.0002296957,0.0001099428,0.00011828,0.00005020584,0.0002062796,0.00007890991,0.00006990538,0.00005126583,0.0003456372],"category_scores_gemma":[0.00003025985,0.00009436539,0.00005658625,0.00009708605,0.00005452666,0.00007821953,0.000007432462,0.0001421234,0.0003884431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008091379,"about_ca_system_score_gemma":0.00001219128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002370939,"about_ca_topic_score_gemma":0.000008261523,"domain_scores_codex":[0.9991355,0.00005455405,0.0001842967,0.0002051568,0.0002197005,0.0002007983],"domain_scores_gemma":[0.999464,0.0001346523,0.0001167125,0.0001516207,0.0000198847,0.0001130823],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003687154,0.0002513878,0.02311543,0.00004453423,0.00005740252,0.00001884052,0.001206759,0.0770375,0.8399096,0.00006095216,0.023752,0.03417692],"study_design_scores_gemma":[0.006105638,0.001198682,0.1307318,0.0001555604,0.0001433554,0.000477527,0.0008493257,0.7354201,0.09930762,0.001186196,0.02350988,0.0009143348],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9904336,0.000004232352,0.005213649,0.0009338204,0.0002790455,0.0003347662,0.000005467889,0.00002535965,0.00277005],"genre_scores_gemma":[0.9931778,0.000005965801,0.004833259,0.0004660466,0.00009917469,0.000001334719,0.000004390131,0.00001723927,0.001394755],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.740602,"threshold_uncertainty_score":0.4992779,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009999586750758313,"score_gpt":0.2403084736392541,"score_spread":0.2303088868884958,"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."}}