{"id":"W4205675430","doi":"10.1139/juvs-2021-0024","title":"Detection and tracking of belugas, kayaks and motorized boats in drone video using deep learning","year":2022,"lang":"en","type":"article","venue":"Drone Systems and Applications","topic":"Marine animal studies overview","field":"Environmental Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"Churchill Northern Studies Centre; Canada Excellence Research Chairs, Government of Canada","keywords":"Drone; Artificial intelligence; Computer science; Deep learning; Computer vision; Convolutional neural network; Video tracking; Tracking (education); Object detection; Object (grammar); Pattern recognition (psychology)","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"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":[0.000276176,0.00007408696,0.0001572349,0.00003021772,0.0003683463,0.0000162893,0.00004209947,0.00002060747,0.00003078684],"category_scores_gemma":[0.00000819911,0.00007958637,0.00001096079,0.0002003853,0.00006465529,0.00007482593,0.0002656631,0.0001076231,8.842044e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008363406,"about_ca_system_score_gemma":0.00000203847,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008181372,"about_ca_topic_score_gemma":0.0008775411,"domain_scores_codex":[0.999288,0.00005867198,0.0001994162,0.0002224654,0.0001192849,0.0001121964],"domain_scores_gemma":[0.9997357,0.00003600077,0.0001099426,0.00007797548,0.000004520494,0.00003587532],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000346609,0.0001520525,0.5971272,0.0003659663,0.00003466554,0.000002480762,0.002027214,0.00602563,0.1857271,0.0009867121,0.000008257423,0.207508],"study_design_scores_gemma":[0.001275989,0.0002482487,0.8472316,0.00005185857,0.00007218654,0.00009697532,0.004957011,0.08491463,0.0003467687,0.0003484136,0.06001798,0.0004383721],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9946105,0.001879223,0.002440287,0.00001869888,0.00001463904,0.0004949663,0.000003276406,0.00001327344,0.0005250808],"genre_scores_gemma":[0.9993398,0.000177419,0.000160437,0.000007198954,0.00001775342,0.000234441,0.000001469939,0.000007954673,0.00005355021],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2501044,"threshold_uncertainty_score":0.9984232,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01506454879873872,"score_gpt":0.2324818606906754,"score_spread":0.2174173118919366,"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."}}