{"id":"W3128639218","doi":"10.1109/lra.2021.3058909","title":"Learned Camera Gain and Exposure Control for Improved Visual Feature Detection and Matching","year":2021,"lang":"en","type":"article","venue":"IEEE Robotics and Automation Letters","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"Canada Research Chairs","keywords":"Artificial intelligence; Computer science; Feature (linguistics); Pipeline (software); Computer vision; Convolutional neural network; Visual odometry; Matching (statistics); Process (computing); Simultaneous localization and mapping; Odometry; Pattern recognition (psychology); Robot; Mathematics; Mobile robot","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"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":[0.000424617,0.0006463687,0.0003727837,0.0002588264,0.0001858556,0.0004715152,0.0009931215,0.000535127,0.001532769],"category_scores_gemma":[0.002025616,0.0003030422,0.0002836437,0.0002957766,0.0004297178,0.001066493,0.0009090417,0.001025891,0.0004141438],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005677163,"about_ca_system_score_gemma":0.0006538426,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003495734,"about_ca_topic_score_gemma":0.005822275,"domain_scores_codex":[0.9997169,0.00003320419,0.00001037391,0.0001183772,0.00007073493,0.0000503427],"domain_scores_gemma":[0.9995425,0.0001000737,0.00007582182,0.0001535501,0.0000987918,0.00002940777],"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":[0.0002381786,0.0002718861,0.003399191,0.0000752448,0.00007273514,0.00008991523,0.0001377464,0.4175676,0.1258844,0.004780167,0.002375596,0.4451073],"study_design_scores_gemma":[0.00001026436,0.00004985871,0.0009992191,0.000005125554,0.000008421051,0.00004636042,0.000007197455,0.9796436,0.01685337,0.001517811,0.0008503096,0.000008387758],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08365966,0.000152416,0.9125463,0.000116114,0.00004004948,0.00002596016,0.00006109379,0.001523164,0.001875255],"genre_scores_gemma":[0.9032135,0.00006096341,0.09450872,0.0001019794,0.00002131639,0.00002606991,0.0001213669,0.00009543965,0.001850702],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003495734,"threshold_uncertainty_score":0.006950736,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006078282824255606,"score_gpt":0.2118098342827624,"score_spread":0.2057315514585068,"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."}}