{"id":"W4319456044","doi":"10.1016/j.isprsjprs.2023.01.025","title":"From crowd to herd counting: How to precisely detect and count African mammals using aerial imagery and deep learning?","year":2023,"lang":"en","type":"article","venue":"ISPRS Journal of Photogrammetry and Remote Sensing","topic":"Identification and Quantification in Food","field":"Biochemistry, Genetics and Molecular Biology","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Université de Sherbrooke","funders":"Fonds pour la Formation à la Recherche dans l’Industrie et dans l’Agriculture; Fonds De La Recherche Scientifique - FNRS; European Commission","keywords":"Convolutional neural network; Artificial intelligence; Geography; Ovis; Livestock; Wildlife; Computer science; Deep learning; Cartography; Pattern recognition (psychology); Computer vision; Forestry; Ecology; Biology","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":[0.0006791915,0.0001550902,0.0002339233,0.0002332693,0.0002289534,0.0003189013,0.00007483829,0.0001184003,0.00000259815],"category_scores_gemma":[0.0005321082,0.0001483216,0.00005959769,0.0003182066,0.00009075891,0.000013853,0.00009121458,0.0001599058,0.000001889959],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001454026,"about_ca_system_score_gemma":0.00003423531,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001594008,"about_ca_topic_score_gemma":0.00005333939,"domain_scores_codex":[0.9988328,0.0001162681,0.0003227922,0.0003042597,0.000190571,0.0002333597],"domain_scores_gemma":[0.9990446,0.00006631971,0.000253005,0.0001473708,0.0002595848,0.0002291201],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001661952,0.000004395766,0.0001093819,0.00001631479,0.00005001879,0.00001362665,0.0003948192,0.00005251233,0.8717103,5.862892e-7,0.0001785605,0.1273033],"study_design_scores_gemma":[0.001263695,0.0005321972,0.00603352,0.0002442373,0.0001679941,0.0007326357,0.004109367,0.00914806,0.8997737,0.000142477,0.07723857,0.0006135965],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9498096,0.0005018178,0.04869528,0.0004080171,0.0003993993,0.0001406971,0.00000668685,0.00001268776,0.00002580436],"genre_scores_gemma":[0.980829,0.0003242153,0.01807538,0.0001561575,0.000462483,1.006999e-7,0.000008447898,0.00002562468,0.0001185682],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1266897,"threshold_uncertainty_score":0.604838,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0201759754059933,"score_gpt":0.2778167085148037,"score_spread":0.2576407331088104,"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."}}