{"id":"W2807192771","doi":"10.5194/isprs-archives-xlii-2-15-2018","title":"UNDERWATER PHOTOGRAMMETRY IN VERY SHALLOW WATERS: MAIN CHALLENGES AND CAUSTICS EFFECT REMOVAL","year":2018,"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":"Image Enhancement Techniques","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; European Commission","keywords":"Underwater; Photogrammetry; Computer science; Caustic (mathematics); Robustness (evolution); Convolutional neural network; Artificial intelligence; Computer vision; Buoyancy; Object (grammar); Ground truth; Geology; Set (abstract data type); Neutral buoyancy; Marine engineering; Engineering; Mathematics; Geometry","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":[0.0005979358,0.0006146635,0.0004983242,0.0004830543,0.0003213921,0.0009839142,0.0005236948,0.001006572,0.001163202],"category_scores_gemma":[0.001633341,0.000393506,0.0003839378,0.0005583304,0.0006681118,0.001127416,0.001058509,0.00106599,0.0007780282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003568133,"about_ca_system_score_gemma":0.0005695769,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001696393,"about_ca_topic_score_gemma":0.002424267,"domain_scores_codex":[0.9993529,0.0001094308,0.0000314147,0.0001198592,0.000338585,0.00004775779],"domain_scores_gemma":[0.9992322,0.0002423961,0.00009531601,0.0002067321,0.0001905929,0.00003283843],"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":[0.0001305125,0.00005122377,0.005250507,0.0006025189,0.0001109677,0.0005741566,0.00057854,0.09008817,0.3268978,0.00521253,0.002530608,0.5679725],"study_design_scores_gemma":[0.0000239382,0.0002155899,0.01578689,0.0001790538,0.00008594496,0.002272938,0.0007402135,0.6636969,0.2717237,0.01826839,0.02689214,0.000114236],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07448553,0.001114018,0.9199693,0.0007100088,0.00008612221,0.00006941218,0.0001023022,0.0006442789,0.002819061],"genre_scores_gemma":[0.5020533,0.001766448,0.491508,0.0002261088,0.00006692744,0.00005263706,0.0003537727,0.0002310672,0.003741732],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001696393,"threshold_uncertainty_score":0.003891349,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01840285582556214,"score_gpt":0.2591163165649802,"score_spread":0.2407134607394181,"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."}}