{"id":"W4402159185","doi":"10.1016/j.compag.2024.109333","title":"End-to-end stereo matching network with two-stage partition filtering for full-resolution depth estimation and precise localization of kiwifruit for robotic harvesting","year":2024,"lang":"en","type":"article","venue":"Computers and Electronics in Agriculture","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Key Research and Development Program of Zhejiang Province; Ministry of Agriculture and Rural Affairs of the People's Republic of China; Key Research and Development Projects of Shaanxi Province; National Aerospace Science Foundation of China; Ministry of Finance; Ministry of Science and Technology of the People's Republic of China; Overseas Expertise Introduction Project for Discipline Innovation; National Natural Science Foundation of China; Ontario Ministry of Agriculture, Food and Rural Affairs","keywords":"Partition (number theory); Artificial intelligence; Matching (statistics); Computer vision; Computer science; Stage (stratigraphy); End-to-end principle; Mathematics; Geology; Statistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001664871,0.000543472,0.0004929305,0.0005944301,0.0004593276,0.0003567385,0.001202911,0.0005847338,0.003651288],"category_scores_gemma":[0.0002660763,0.0003280703,0.0003506615,0.000667938,0.0001666274,0.0007190829,0.0007726284,0.0004644985,0.001246216],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004731294,"about_ca_system_score_gemma":0.001093448,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00870637,"about_ca_topic_score_gemma":0.01907888,"domain_scores_codex":[0.9997829,0.00001159018,0.00000668637,0.00005305382,0.0001015614,0.00004433996],"domain_scores_gemma":[0.9998863,0.0000131831,0.00001088757,0.00001811854,0.00006242083,0.000009143442],"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":[0.000470934,0.0002765425,0.001940679,0.00009205638,0.00007318644,0.0001236568,0.0001092929,0.03299625,0.2711898,0.002374261,0.006878172,0.6834752],"study_design_scores_gemma":[0.00002930342,0.0001813548,0.003066805,0.000009039874,0.00003847151,0.0001647105,0.00005387457,0.9066836,0.08448093,0.001496417,0.003767966,0.00002750416],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06554146,0.0001289571,0.9282302,0.0000855615,0.00007154223,0.00007249124,0.0003119222,0.00224492,0.003312943],"genre_scores_gemma":[0.5787072,0.0001572891,0.4086475,0.0002070727,0.00003881967,0.0001644207,0.001262436,0.000107283,0.01070784],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00870637,"threshold_uncertainty_score":0.01731139,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01477806599651151,"score_gpt":0.232506027830222,"score_spread":0.2177279618337105,"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."}}