{"id":"W3043718939","doi":"10.1007/s43154-020-00011-8","title":"Using Deep Learning to Find Victims in Unknown Cluttered Urban Search and Rescue Environments","year":2020,"lang":"en","type":"article","venue":"Current Robotics Reports","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Artificial intelligence; Computer science; Computer vision; RGB color model; Detector; Deep learning; Feature (linguistics); Pyramid (geometry); Urban search and rescue; Feature extraction; Identification (biology); Single shot; Rescue robot; Mobile robot; Pattern recognition (psychology); Robot; Mathematics","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":[0.000557513,0.0008467141,0.0006779397,0.001008546,0.0004467138,0.0008155541,0.001324746,0.001281032,0.0009098679],"category_scores_gemma":[0.001781779,0.0005723365,0.000481031,0.0007677111,0.0006207627,0.001350929,0.001316248,0.001031308,0.0003416302],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006238278,"about_ca_system_score_gemma":0.0007744698,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01216404,"about_ca_topic_score_gemma":0.01318702,"domain_scores_codex":[0.9997132,0.0000385309,0.0000114476,0.00007582516,0.00006376301,0.00009722281],"domain_scores_gemma":[0.9992924,0.0002954033,0.00008566241,0.00007963998,0.0001776169,0.00006924093],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002905373,0.0004094333,0.00787016,0.00007886113,0.0001291839,0.000185982,0.0001612133,0.6730213,0.01243314,0.001562231,0.003081253,0.3007768],"study_design_scores_gemma":[0.000003558805,0.00002073119,0.0003804418,0.000002855993,0.000005303894,0.00001138727,0.00001662014,0.9978638,0.0007820268,0.0008226411,0.00008774544,0.000002819115],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4400692,0.0007054657,0.5528719,0.0005328683,0.0001668976,0.00006251036,0.0002619221,0.001524066,0.003805217],"genre_scores_gemma":[0.9481702,0.0001695873,0.04830385,0.0001551481,0.00005121935,0.00001923296,0.0003287313,0.00005439163,0.002747701],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01216404,"threshold_uncertainty_score":0.02418643,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09172285302467226,"score_gpt":0.3419341077514897,"score_spread":0.2502112547268174,"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."}}