{"id":"W2130626940","doi":"10.1109/crv.2012.52","title":"Robust Horizon Detection Using Segmentation for UAV Applications","year":2012,"lang":"en","type":"article","venue":"","topic":"Infrared Target Detection Methodologies","field":"Engineering","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Computer vision; Artificial intelligence; Horizon; Terrain; Sky; Segmentation; Obstacle; Image segmentation; Path (computing); Field (mathematics); Obstacle avoidance; Line (geometry); Remote sensing; Geology; Mathematics; Geography; Mobile robot; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002257783,0.00008093586,0.00006945733,0.00008958178,0.0001049496,0.000018088,0.0000382111,0.0000709712,0.00003883186],"category_scores_gemma":[0.00002916106,0.00008449352,0.00003747791,0.000149921,0.000009048421,0.0002954768,0.000006990778,0.00005720143,0.00002079065],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001259914,"about_ca_system_score_gemma":0.000003260018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004012955,"about_ca_topic_score_gemma":0.000002092823,"domain_scores_codex":[0.9995244,0.00002020452,0.0001290399,0.0000755312,0.00005529413,0.0001954921],"domain_scores_gemma":[0.9997145,0.00008745068,0.00002197059,0.0001034649,0.00003623359,0.00003638008],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000005556829,0.000008962469,0.0001481465,0.00005114798,0.00002139428,1.52916e-8,0.00009250658,0.1279103,0.8028782,0.0003212469,0.00005979199,0.0685027],"study_design_scores_gemma":[0.0001252879,0.00002246925,0.0002205802,0.000001610064,0.00002114209,0.000005482902,0.000293238,0.08182131,0.913965,0.0003527335,0.003040736,0.0001303754],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1087069,0.00008646304,0.8887182,0.000002957746,0.0006006399,0.0004059017,0.000004057013,0.0005731705,0.0009017257],"genre_scores_gemma":[0.3159713,0.000007570753,0.6832324,0.000009174071,0.0003581895,0.0003183338,0.00000739681,0.00002482964,0.00007080245],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2072644,"threshold_uncertainty_score":0.3445546,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1104226008409923,"score_gpt":0.3037034454608399,"score_spread":0.1932808446198476,"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."}}