{"id":"W2967154765","doi":"10.1007/s11042-019-08047-5","title":"A motion and lightness saliency approach for forest smoke segmentation and detection","year":2019,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Computer vision; Background subtraction; Smoke; Pattern recognition (psychology); Motion detection; Segmentation; Feature (linguistics); Motion (physics); Pixel","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":[0.0003168686,0.0007378735,0.0009653553,0.002324614,0.0004633837,0.0006665565,0.0009805262,0.0006248141,0.002292328],"category_scores_gemma":[0.0005960776,0.0003860182,0.001001431,0.0009821628,0.0002936482,0.0006296356,0.0008572469,0.0004772013,0.0004887115],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004906043,"about_ca_system_score_gemma":0.000816393,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00792638,"about_ca_topic_score_gemma":0.01554084,"domain_scores_codex":[0.9998071,0.00001638434,0.000007723517,0.0000500784,0.00007726601,0.00004146438],"domain_scores_gemma":[0.9997697,0.00004332217,0.00002205496,0.00002223506,0.0001087669,0.00003379564],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000535982,0.0003470893,0.001791382,0.0002272577,0.0001677668,0.0002452322,0.0001422317,0.03067142,0.268948,0.004270188,0.002806971,0.6898465],"study_design_scores_gemma":[0.00003579868,0.0002479091,0.005734014,0.000020858,0.0001313126,0.0003031057,0.00005684692,0.9440095,0.04184039,0.003301541,0.004284356,0.00003438647],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.049224,0.0008010654,0.9458913,0.0001377803,0.0001090992,0.0001761561,0.0001536751,0.001067538,0.002439302],"genre_scores_gemma":[0.4991724,0.0007385663,0.4936323,0.0001962132,0.0002565184,0.0001189164,0.0005353025,0.0002491106,0.005100522],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00792638,"threshold_uncertainty_score":0.01576048,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0135402977045221,"score_gpt":0.2172110601723635,"score_spread":0.2036707624678414,"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."}}