{"id":"W4311681015","doi":"10.22215/etd/2022-15218","title":"Near Infrared Imaging and Image Pre-Processing to Improve the Automatic Detection of Canada Geese","year":2022,"lang":"en","type":"dissertation","venue":"","topic":"Advanced Measurement and Detection Methods","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Vegetation (pathology); Convolutional neural network; Remote sensing; Object detection; Contrast (vision); Population; Computer science; Artificial intelligence; Geography; Computer vision; Environmental science; Cartography; Pattern recognition (psychology)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002443375,0.0001804015,0.0001863222,0.00008494678,0.0002321155,0.00005617679,0.00009746394,0.00003942277,0.00009827887],"category_scores_gemma":[0.0001181798,0.000153919,0.00003109386,0.0002389993,0.00001119631,0.0001299446,0.00001807134,0.0002608759,2.972997e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001903678,"about_ca_system_score_gemma":0.0001641916,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01059443,"about_ca_topic_score_gemma":0.07496195,"domain_scores_codex":[0.9990513,0.00003497062,0.0002781869,0.0001696547,0.0002904388,0.0001754592],"domain_scores_gemma":[0.9995505,0.00004827352,0.0000886428,0.0001733176,0.00008289357,0.00005639484],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003686014,0.000004486135,0.00001781245,0.001030614,0.0000398692,0.000001945543,0.001634378,0.006998967,0.4482867,0.000002244214,0.0003220359,0.5416241],"study_design_scores_gemma":[0.0004386029,0.00006291229,0.006342382,0.0001468805,0.0001351973,0.000008317382,0.008499659,0.4961348,0.4802619,0.0004255041,0.006844195,0.0006996074],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7639084,0.003632694,0.1971802,0.00004711958,0.004424131,0.001768472,0.0000318585,0.0008344138,0.02817275],"genre_scores_gemma":[0.9518934,0.00003170749,0.03934509,0.00008443991,0.0001240585,0.0003439902,0.0000435035,0.0001584084,0.007975341],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5409244,"threshold_uncertainty_score":0.9959941,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004877550192078797,"score_gpt":0.2486468693647294,"score_spread":0.2437693191726506,"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."}}