{"id":"W4206004579","doi":"10.1101/2022.01.14.476404","title":"Use of object detection in camera trap image identification: assessing a method to rapidly and accurately classify human and animal detections for research and application in recreation ecology","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Wildlife Ecology and Conservation","field":"Environmental Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Camera trap; Workflow; Bottleneck; Computer science; Artificial intelligence; Object detection; Process (computing); Trap (plumbing); Object (grammar); Image processing; Computer vision; Data mining; Wildlife; Pattern recognition (psychology); Image (mathematics); Ecology; Database; Environmental science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.004598329,0.0009230412,0.0007865304,0.002865065,0.0004919384,0.001803633,0.002060561,0.00120813,0.001266155],"category_scores_gemma":[0.008608875,0.0005865864,0.000807497,0.001457215,0.0004599724,0.001461321,0.001040235,0.0007042013,0.0008532502],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001350735,"about_ca_system_score_gemma":0.001338855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01952345,"about_ca_topic_score_gemma":0.03187487,"domain_scores_codex":[0.9982578,0.0003805143,0.0001098389,0.0005654541,0.0005525938,0.0001337493],"domain_scores_gemma":[0.9921238,0.003654556,0.0008464752,0.0008595737,0.002161526,0.00035411],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001539527,0.001188169,0.2200413,0.0007821854,0.0007092946,0.0003227895,0.0007211174,0.0693047,0.1271912,0.001066798,0.0108996,0.5662333],"study_design_scores_gemma":[0.00006011473,0.0003989556,0.05454952,0.00005534971,0.00009156772,0.0002768296,0.0002185542,0.8888721,0.05204718,0.0006035554,0.002736398,0.00008983426],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5716865,0.0005163525,0.4061098,0.0004132213,0.00009630179,0.000628341,0.002064106,0.01673846,0.001746798],"genre_scores_gemma":[0.5334369,0.0001405172,0.4632536,0.0001724053,0.00001923178,0.0002368553,0.001549536,0.0003653042,0.0008256651],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01952345,"threshold_uncertainty_score":0.03881961,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07961047643387786,"score_gpt":0.3546111961505415,"score_spread":0.2750007197166637,"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."}}