{"id":"W2033588814","doi":"10.3141/2299-13","title":"Automated Collection of Pedestrian Data through Computer Vision Techniques","year":2012,"lang":"en","type":"article","venue":"Transportation Research Record Journal of the Transportation Research Board","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal; Simon Fraser University; University of British Columbia","funders":"","keywords":"Pedestrian; Computer science; Data collection; Walkability; Automation; Data set; Set (abstract data type); Artificial intelligence; Transport engineering; Computer vision; Simulation; Data mining; Statistics; Engineering; Mathematics; Built environment","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01332212,0.0002193238,0.0004928163,0.0008396785,0.0005287812,0.0001563762,0.003109705,0.0002019331,0.00004413568],"category_scores_gemma":[0.000197024,0.0001626862,0.0002506817,0.003558174,0.0004336587,0.003145333,0.00004668632,0.001484758,0.000009198351],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001528036,"about_ca_system_score_gemma":0.0006355639,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004973007,"about_ca_topic_score_gemma":0.005102267,"domain_scores_codex":[0.9912065,0.002605036,0.001458078,0.0004353413,0.003371185,0.0009238845],"domain_scores_gemma":[0.9932982,0.001460481,0.000672154,0.001289785,0.002990989,0.0002884323],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001664721,0.001770677,0.7475916,0.0008913031,0.0004636388,0.0001118206,0.01050019,0.0006028581,0.01476144,0.009928733,0.04900432,0.1627087],"study_design_scores_gemma":[0.0009067585,0.0009409508,0.9635229,0.0003853387,0.00002883973,0.000002874522,0.0002253406,0.003822559,0.008992865,0.002820711,0.01814606,0.0002048747],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6958311,0.0004420074,0.2981947,0.002752705,0.001316141,0.001006093,0.00005604103,0.0001999503,0.0002013451],"genre_scores_gemma":[0.846108,0.0008371647,0.1526018,0.00003682009,0.0002794281,0.00001840081,0.00002295599,0.00002987233,0.00006563662],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2159313,"threshold_uncertainty_score":0.7517733,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1963894313795042,"score_gpt":0.471530019124502,"score_spread":0.2751405877449979,"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."}}