{"id":"W1776642447","doi":"10.1007/978-3-319-23222-5_65","title":"Nonlinear Background Filter to Improve Pedestrian Detection","year":2015,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer vision; Computer science; Artificial intelligence; Filter (signal processing); Detector; Frame (networking); False positive paradox; Nonlinear system; Pedestrian detection; Pedestrian; Motion (physics); Image (mathematics); Frame rate; Motion detection; Physics; Geography; Telecommunications","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002430168,0.0005906204,0.0006115995,0.0008990331,0.0002297139,0.0008649149,0.003081978,0.0003876268,0.00001716842],"category_scores_gemma":[0.0001858878,0.0005435785,0.0001540144,0.0008877943,0.0002854376,0.0007258966,0.001354449,0.0008890372,0.0002163687],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005088071,"about_ca_system_score_gemma":0.0007427685,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006728104,"about_ca_topic_score_gemma":0.0003087501,"domain_scores_codex":[0.9954727,0.00008334179,0.0005673136,0.001912632,0.001157123,0.0008068661],"domain_scores_gemma":[0.9965545,0.0004512091,0.000251639,0.001861275,0.00048741,0.0003939462],"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":[0.00001147612,0.00002079212,0.00003215067,0.00002339817,0.000009416219,0.00006518552,0.0002867575,0.005026194,0.0005429209,0.0006914928,0.00002977132,0.9932604],"study_design_scores_gemma":[0.001586217,0.002257562,0.0008044098,0.0007000077,0.00003018934,0.0002800036,7.907695e-7,0.6391554,0.01934569,0.2807387,0.05142932,0.003671691],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003202867,0.0002021227,0.9909366,0.0006726869,0.004758744,0.0004652789,0.000008866959,0.0002284762,0.002406984],"genre_scores_gemma":[0.07630321,0.00001717202,0.9191433,0.001864478,0.001837892,0.00001761805,0.00000527462,0.00006310125,0.0007479902],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9895887,"threshold_uncertainty_score":0.9997016,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04950859430179317,"score_gpt":0.3082701536956525,"score_spread":0.2587615593938593,"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."}}