{"id":"W4212931582","doi":"10.1109/iotm.001.2100088","title":"Unmanned Aerial Multi-Object Dynamic Frame Detection and Skipping Using Deep Learning on the Internet of Drones","year":2021,"lang":"en","type":"article","venue":"IEEE Internet of Things Magazine","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brandon University","funders":"","keywords":"Drone; Computer science; Frame (networking); Software deployment; Real-time computing; Deep learning; Artificial intelligence; The Internet; Process (computing); Object detection; Computer vision; Telecommunications; World Wide Web; Pattern recognition (psychology)","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":[0.0009641063,0.000191967,0.0003476235,0.0001414883,0.000055771,0.0001266442,0.0004809675,0.0001000601,0.00001453357],"category_scores_gemma":[0.0005873058,0.0001573627,0.0001159177,0.0002877969,0.0001063009,0.0003458066,0.0002689017,0.0003872451,0.00000711017],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000479327,"about_ca_system_score_gemma":0.00002671651,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002137083,"about_ca_topic_score_gemma":0.0001091526,"domain_scores_codex":[0.9982837,0.0003881038,0.000432253,0.0004064067,0.0002567589,0.0002327045],"domain_scores_gemma":[0.9986498,0.000468692,0.000312815,0.000351917,0.0001763648,0.00004035754],"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":[0.0001614611,0.0001717515,0.002921579,0.0002047549,0.0002336113,0.00005203596,0.00821531,0.003207239,0.87878,0.001113344,0.00001570884,0.1049232],"study_design_scores_gemma":[0.0004430978,0.000217394,0.004797062,0.000355428,0.00001679539,0.00007104258,0.00006207047,0.7316428,0.261579,0.0005130892,0.0001319481,0.0001702198],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.520066,0.00009851866,0.4789109,0.00009145859,0.0006523594,0.00005807295,2.927587e-7,0.00004162162,0.00008074941],"genre_scores_gemma":[0.9607407,0.00002233512,0.03883598,0.0001254141,0.00004742916,0.0000030668,0.000001056965,0.00001854171,0.0002054993],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7284356,"threshold_uncertainty_score":0.6417065,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02346996202038674,"score_gpt":0.283216060584466,"score_spread":0.2597460985640793,"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."}}