{"id":"W2164554221","doi":"10.1109/tce.2012.6227462","title":"Robust video stabilization based on particle filtering with weighted feature points","year":2012,"lang":"en","type":"article","venue":"IEEE Transactions on Consumer Electronics","topic":"Image and Video Stabilization","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"RANSAC; Motion estimation; Artificial intelligence; Robustness (evolution); Computer vision; Feature (linguistics); Kalman filter; Computer science; Motion field; Particle filter; Image stabilization; Quarter-pixel motion; Mathematics; Pattern recognition (psychology); Image (mathematics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005564908,0.0006891461,0.0008500622,0.0006933077,0.000398724,0.0004813468,0.0007610041,0.0007403479,0.0005834508],"category_scores_gemma":[0.001598503,0.0003273938,0.0005724983,0.000716174,0.0003562807,0.0008258657,0.0005769292,0.0006307031,0.0002796884],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004303558,"about_ca_system_score_gemma":0.0004138089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003007798,"about_ca_topic_score_gemma":0.001797052,"domain_scores_codex":[0.9994158,0.00008744834,0.0000296775,0.0001529155,0.0002850895,0.00002913476],"domain_scores_gemma":[0.9995832,0.0001247348,0.00008462818,0.00005996117,0.0001348657,0.00001258269],"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":[0.0003558391,0.00009086363,0.00126808,0.0001841067,0.0001332817,0.0002150759,0.0002451856,0.293127,0.1226659,0.01072959,0.00205867,0.5689264],"study_design_scores_gemma":[0.00001756752,0.00008592142,0.0004393565,0.000007306602,0.00001757352,0.00005415999,0.000009635769,0.983354,0.01332164,0.001208799,0.001465837,0.00001828982],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005813675,0.0001516721,0.9932808,0.00003226568,0.00003548474,0.00001914236,0.000007327565,0.0002741354,0.0003854748],"genre_scores_gemma":[0.4578405,0.0005061718,0.5386807,0.00006498609,0.0001045408,0.0001605525,0.0001234249,0.00008089731,0.002438327],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003007798,"threshold_uncertainty_score":0.005980611,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01752601709365206,"score_gpt":0.2260306476612334,"score_spread":0.2085046305675813,"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."}}