{"id":"W2081707527","doi":"10.1109/icip.2012.6466796","title":"Fast obstacle detection using targeted optical flow","year":2012,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Optical flow; Obstacle; Computer science; Benchmark (surveying); Computer vision; Optical imaging; Cluster analysis; Flow (mathematics); Artificial intelligence; Adaptive optics; Image (mathematics); Optics; Mathematics; Physics","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":[0.00009520794,0.00006464927,0.0000599274,0.00004639386,0.0001038174,0.00006017017,0.0001610357,0.00002188496,0.00004897332],"category_scores_gemma":[0.00003092327,0.00005484926,0.00002818313,0.0002064021,0.0000155887,0.00119215,0.000118973,0.00007242481,0.0001073346],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003463946,"about_ca_system_score_gemma":0.000008842795,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004537823,"about_ca_topic_score_gemma":6.998362e-7,"domain_scores_codex":[0.9993607,0.00001593109,0.00009448241,0.000135715,0.0001263039,0.0002668764],"domain_scores_gemma":[0.9996094,0.00002190386,0.00001923208,0.0001995979,0.00003061803,0.0001192228],"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":[0.000001744115,0.00004091039,0.0003900728,0.000002027271,0.000002848892,0.000001286848,0.0002073689,0.0005669449,0.08456135,0.00361383,0.00003403473,0.9105776],"study_design_scores_gemma":[0.00009591419,0.000009707507,0.001373187,0.000002940008,0.000001201936,0.00002448404,0.0000335549,0.8878539,0.1087642,0.0001915827,0.001558406,0.00009087268],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01560654,0.00005718212,0.9811867,0.00007766346,0.0005228364,0.00003701771,1.100577e-7,0.0001787064,0.002333246],"genre_scores_gemma":[0.5478938,5.615611e-7,0.4517861,0.0001683574,0.00005264916,5.756499e-7,1.374113e-7,0.000003084132,0.00009476589],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9104867,"threshold_uncertainty_score":0.2236688,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02319647619302572,"score_gpt":0.2821283495058046,"score_spread":0.2589318733127788,"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."}}