{"id":"W2948612393","doi":"10.5194/isprs-archives-xlii-2-w13-475-2019","title":"RESNET-BASED TREE SPECIES CLASSIFICATION USING UAV IMAGES","year":2019,"lang":"en","type":"article","venue":"˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":94,"is_retracted":false,"has_abstract":true,"ca_institutions":"FPInnovations; York University","funders":"Natural Sciences and Engineering Research Council of Canada; FPInnovations; York University","keywords":"Artificial intelligence; Computer science; Tree (set theory); RGB color model; Pattern recognition (psychology); Artificial neural network; Set (abstract data type); Residual; Decision tree; Deep learning; Identification (biology); Data set; Residual neural network; Contextual image classification; Remote sensing; Computer vision; Image (mathematics); Geography; Mathematics; Ecology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002334537,0.0006604456,0.0003554613,0.001534351,0.0001857927,0.0003767578,0.0004728344,0.0004633808,0.001306022],"category_scores_gemma":[0.0004595098,0.0001566216,0.0004970164,0.000821773,0.0001658125,0.0004617315,0.0001988004,0.0003193619,0.00064869],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005193407,"about_ca_system_score_gemma":0.0002511202,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0104866,"about_ca_topic_score_gemma":0.01466741,"domain_scores_codex":[0.9998323,0.00001997026,0.000009916819,0.00005597894,0.00004506089,0.00003685944],"domain_scores_gemma":[0.9997846,0.0000393343,0.00004037784,0.00003325206,0.00008566498,0.00001667331],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008413002,0.0005004788,0.02425879,0.0004034663,0.0003226066,0.0008888851,0.0001594015,0.2757028,0.1206359,0.001137457,0.01498734,0.5601616],"study_design_scores_gemma":[0.00001408856,0.0001023156,0.02465236,0.00002794445,0.00003797474,0.0001321727,0.00008151155,0.9458457,0.02670283,0.000420085,0.001962852,0.00002024503],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9023115,0.001169479,0.0798045,0.0002979782,0.0003855338,0.0001437323,0.004415804,0.004372622,0.007098874],"genre_scores_gemma":[0.9359919,0.000216282,0.05651429,0.00007520853,0.00003047679,0.00003719626,0.004277678,0.00007610748,0.00278093],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0104866,"threshold_uncertainty_score":0.02085114,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0212369626610588,"score_gpt":0.2548592987036682,"score_spread":0.2336223360426094,"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."}}