{"id":"W2887452256","doi":"10.1139/juvs-2017-0022","title":"Pixel- and object-based multispectral classification of forest tree species from small unmanned aerial vehicles","year":2018,"lang":"en","type":"article","venue":"Journal of Unmanned Vehicle Systems","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"Trent University","funders":"","keywords":"Multispectral image; Forest inventory; Tree (set theory); Geomatics; Context (archaeology); Computer science; Remote sensing; Segmentation; Identification (biology); Artificial intelligence; Multispectral pattern recognition; Image segmentation; Pixel; Crown (dentistry); Pattern recognition (psychology); Geography; Forest management; Forestry; Ecology; Mathematics; Biology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":true,"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":[0.000434796,0.0002588844,0.0001970991,0.0009912433,0.0001959889,0.0006072061,0.0002603445,0.0001983508,0.0007348144],"category_scores_gemma":[0.0007200461,0.00009672759,0.0001967232,0.0005402865,0.000221523,0.0006260238,0.0002083055,0.0001639875,0.0002684109],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003115703,"about_ca_system_score_gemma":0.0002151908,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006451644,"about_ca_topic_score_gemma":0.02124116,"domain_scores_codex":[0.9998021,0.00003500048,0.00001010074,0.00004262673,0.00008769691,0.00002251502],"domain_scores_gemma":[0.9995837,0.0001241687,0.00006421141,0.00004943995,0.0001572,0.00002132059],"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":[0.0002649328,0.0001665679,0.1213661,0.0002431364,0.0001406795,0.00007723775,0.0004164179,0.01690362,0.2283577,0.0008728906,0.0008076361,0.630383],"study_design_scores_gemma":[0.00001862539,0.0003484671,0.6177067,0.0000690697,0.0001344683,0.0004432356,0.001249913,0.2819541,0.0907562,0.001433137,0.005825189,0.00006088948],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8497071,0.0006320001,0.144571,0.0001026713,0.00002987614,0.00008465815,0.0003727284,0.0004636162,0.004036331],"genre_scores_gemma":[0.8867813,0.000327588,0.111402,0.00003908405,0.00001171223,0.0000269487,0.0004339071,0.00003232419,0.0009452272],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006451644,"threshold_uncertainty_score":0.01282817,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02193049257349221,"score_gpt":0.2309889361799982,"score_spread":0.209058443606506,"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."}}