{"id":"W4405194977","doi":"10.1016/j.compag.2024.109719","title":"Research on unmanned aerial vehicle (UAV) rice field weed sensing image segmentation method based on CNN-transformer","year":2024,"lang":"en","type":"article","venue":"Computers and Electronics in Agriculture","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":34,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ministry of Agriculture","funders":"","keywords":"Artificial intelligence; Aerial image; Computer vision; Drone; Aerial imagery; Aerial survey; Segmentation; Transformer; Image segmentation; Aerial photography; Computer science; Engineering; Remote sensing; Image (mathematics); Geography; Electrical engineering; Voltage","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":[0.0001706894,0.0004848006,0.0003605785,0.0005883474,0.0002163247,0.0004077985,0.0005740454,0.0003508163,0.001834142],"category_scores_gemma":[0.0002683774,0.0002602214,0.0004623358,0.0005268375,0.0001888977,0.0009386149,0.0002179869,0.0002880869,0.0003376981],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004432168,"about_ca_system_score_gemma":0.000718952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009525031,"about_ca_topic_score_gemma":0.009000349,"domain_scores_codex":[0.9998425,0.000008737791,0.0000070487,0.00005653523,0.00006420152,0.0000208472],"domain_scores_gemma":[0.9998977,0.00001574758,0.00001087372,0.000012052,0.00005451955,0.000009207495],"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":[0.0001793345,0.00008091592,0.004837019,0.0002727726,0.0001097719,0.0001771257,0.0001315777,0.04195003,0.2344776,0.004182576,0.003350575,0.7102507],"study_design_scores_gemma":[0.00001922432,0.0001483474,0.007076825,0.00002103384,0.00009988472,0.0004179285,0.0001045261,0.8842145,0.09847457,0.001559094,0.007836125,0.00002798985],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1348686,0.00159289,0.8535506,0.0002663198,0.0002289277,0.0001069023,0.0001836036,0.001730313,0.007471917],"genre_scores_gemma":[0.706867,0.002121301,0.2746624,0.0002199207,0.00009260239,0.00006851418,0.0007363467,0.0001855762,0.01504628],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009525031,"threshold_uncertainty_score":0.0189392,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0190702665722872,"score_gpt":0.3028685538742205,"score_spread":0.2837982873019332,"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."}}