{"id":"W2944536024","doi":"10.1117/12.2518879","title":"Challenges in object detection in above-water imagery","year":2019,"lang":"en","type":"article","venue":"","topic":"Infrared Target Detection Methodologies","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Defence Research and Development Canada","funders":"","keywords":"Computer science; Background subtraction; Thresholding; Object detection; Artificial intelligence; Pixel; Computer vision; Object (grammar); Image (mathematics); 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":[0.0004670202,0.0001059308,0.0001515454,0.0003264307,0.000007049708,0.00001234828,0.00006374616,0.0001109342,0.0002558933],"category_scores_gemma":[0.00004317575,0.00008785676,0.00002962282,0.0001243543,0.000007225036,0.000201599,0.00002066274,0.0002186449,0.0004414899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001001025,"about_ca_system_score_gemma":0.000002890113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002514703,"about_ca_topic_score_gemma":0.0002706058,"domain_scores_codex":[0.9992704,0.00007178519,0.0001786717,0.0001592873,0.00007018795,0.0002496426],"domain_scores_gemma":[0.9996988,0.00009477197,0.000007206448,0.0001740706,0.00001051054,0.00001462954],"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":[0.00002666421,0.00001308728,0.002094944,0.0001309056,0.00001041543,0.00001540781,0.001019975,0.03953423,0.8708623,0.00006407444,0.00001439622,0.08621358],"study_design_scores_gemma":[0.0002830366,0.00002682017,0.03120357,0.0000129441,8.587489e-7,0.000008153545,0.0005143301,0.007148466,0.959062,0.0009658881,0.0006042039,0.0001697319],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9470207,0.0003572133,0.001382094,0.00003599621,0.0008166664,0.0001483829,2.809541e-7,0.0003913324,0.04984733],"genre_scores_gemma":[0.9937342,0.0002748859,0.005655093,0.00001613673,0.00003392325,0.00002641961,5.898609e-7,0.00002218094,0.0002365792],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08819968,"threshold_uncertainty_score":0.5674607,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04709904588476035,"score_gpt":0.2556165749408598,"score_spread":0.2085175290560994,"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."}}