{"id":"W2523745592","doi":"10.1007/978-3-319-50115-4_36","title":"Improving the Accuracy of Stereo Visual Odometry Using Visual Illumination Estimation","year":2017,"lang":"en","type":"book-chapter","venue":"Springer proceedings in advanced robotics","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Visual odometry; Artificial intelligence; Computer vision; Odometry; Computer science; Leverage (statistics); Convolutional neural network; Robot; Mobile robot","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":[0.0004265741,0.0008140641,0.000650606,0.0009233447,0.0002126461,0.001064165,0.001101977,0.0007625046,0.004042001],"category_scores_gemma":[0.002137874,0.0004760471,0.0005775052,0.001409594,0.000317392,0.001250752,0.001306245,0.0007599927,0.002917027],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003844416,"about_ca_system_score_gemma":0.0004541511,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003560942,"about_ca_topic_score_gemma":0.003693411,"domain_scores_codex":[0.9993723,0.00005220591,0.00002044538,0.0001093353,0.0003886826,0.00005697841],"domain_scores_gemma":[0.9994024,0.0001349004,0.00003684443,0.0001521265,0.0002584804,0.00001524163],"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":[0.00009643957,0.00003700474,0.0008867542,0.0001729925,0.00004689536,0.00003772999,0.00005637558,0.03392377,0.05700965,0.003006431,0.005520309,0.8992056],"study_design_scores_gemma":[0.00002614407,0.0001311681,0.004869789,0.00009625011,0.0000840909,0.0004030178,0.0000663817,0.8338258,0.1292534,0.008266168,0.02290776,0.00006991821],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01289754,0.001403402,0.9755428,0.0001153598,0.0002662882,0.00001871296,0.0001983725,0.00288555,0.006671929],"genre_scores_gemma":[0.3906657,0.002830566,0.5924016,0.0001824996,0.0002406868,0.00004175421,0.001145791,0.0006823303,0.01180909],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004042001,"threshold_uncertainty_score":0.01352185,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0178123412419293,"score_gpt":0.2704408692131051,"score_spread":0.2526285279711758,"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."}}