{"corpus_id":3824984,"paper_sha":"0ce55b631203a2aaaa506dbc20d0b91ea1bd5485","doi":"10.3390/rs10020285","arxiv_id":null,"pmid":null,"pmcid":null,"mag_id":2790858865,"dblp_id":"journals/remotesensing/CastroTPJCL18","acl_id":null,"title":"An Automatic Random Forest-OBIA Algorithm for Early Weed Mapping between and within Crop Rows Using UAV Imagery","year":2018,"publication_date":"2018-02-12","venue":"Remote Sensing","journal":{"name":"Remote. Sens.","pages":"285","volume":"10"},"journal_issn":null,"journal_title":null,"publication_types":["JournalArticle"],"pubmed_pub_types":null,"s2_fields_of_study":["Agricultural and Food Sciences","Computer Science","Engineering","Geology","Environmental Science"],"reference_count":63,"citation_count":249,"influential_citation_count":4,"is_open_access":true,"arxiv_categories":null,"arxiv_license":null,"arxiv_journal_ref":null,"mesh_headings":null,"chemicals":null,"comments_corrections":null,"source_flags":1,"s2_open_access_pdf_url":"https://www.mdpi.com/2072-4292/10/2/285/pdf?version=1518430558","s2_open_access_landing_url":"https://www.semanticscholar.org/paper/0ce55b631203a2aaaa506dbc20d0b91ea1bd5485","s2_open_access_license":"CCBY","s2_open_access_status":"GOLD","pmc_open_access_pdf_url":null,"pmc_open_access_landing_url":null,"pmc_open_access_license":null,"pmc_open_access_status":null,"unpaywall_open_access_pdf_url":null,"unpaywall_open_access_landing_url":null,"unpaywall_open_access_license":null,"unpaywall_open_access_status":null,"abstract":"Accurate and timely detection of weeds between and within crop rows in the early growth stage is considered one of the main challenges in site-specific weed management (SSWM). In this context, a robust and innovative automatic object-based image analysis (OBIA) algorithm was developed on Unmanned Aerial Vehicle (UAV) images to design early post-emergence prescription maps. This novel algorithm makes the major contribution. The OBIA algorithm combined Digital Surface Models (DSMs), orthomosaics and machine learning techniques (Random Forest, RF). OBIA-based plant heights were accurately estimated and used as a feature in the automatic sample selection by the RF classifier; this was the second research contribution. RF randomly selected a class balanced training set, obtained the optimum features values and classified the image, requiring no manual training, making this procedure time-efficient and more accurate, since it removes errors due to a subjective manual task. The ability to discriminate weeds was significantly affected by the imagery spatial resolution and weed density, making the use of higher spatial resolution images more suitable. Finally, prescription maps for in-season post-emergence SSWM were created based on the weed maps—the third research contribution—which could help farmers in decision-making to optimize crop management by rationalization of the herbicide application. The short time involved in the process (image capture and analysis) would allow timely weed control during critical periods, crucial for preventing yield loss.","claims":[{"public_id":"cl_874b3ac40c9aa3d1e85351905dcff187","status":"active","text":"A robust automatic object-based image analysis algorithm was developed for early post-emergence weed mapping between and within crop rows from UAV imagery.","confidence":0.97,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_874b3ac40c9aa3d1e85351905dcff187"},{"public_id":"cl_146d6d10504873ff0f9084c66cec866f","status":"active","text":"OBIA-based plant heights were accurately estimated and used as a feature for automatic sample selection by the Random Forest classifier.","confidence":0.95,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_146d6d10504873ff0f9084c66cec866f"},{"public_id":"cl_5fa019dfb066194c9e294922debb76ac","status":"active","text":"Prescription maps for in-season post-emergence site-specific weed management were created from the weed maps to support herbicide optimization and timely weed control.","confidence":0.96,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_5fa019dfb066194c9e294922debb76ac"},{"public_id":"cl_7863dd44c1f49df77ef5c83b97a041d0","status":"active","text":"The Random Forest procedure required no manual training, used class-balanced training sets, and reduced subjective errors while improving time efficiency and accuracy.","confidence":0.93,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_7863dd44c1f49df77ef5c83b97a041d0"},{"public_id":"cl_5c3f95f50d2c723650278c24955089a3","status":"active","text":"Weed discrimination was significantly affected by imagery spatial resolution and weed density, with higher spatial resolution images being more suitable.","confidence":0.92,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_5c3f95f50d2c723650278c24955089a3"}],"concepts":[{"public_id":"co_004c7fabd85d83235ee97fc3b38e50d5","status":"active","name":"imagery spatial resolution","description":"The ground sampling detail of the imagery, affecting the ability to separate objects.","types":["image property"],"aliases":["spatial resolution"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_004c7fabd85d83235ee97fc3b38e50d5"},{"public_id":"co_2cd9d50b0cc3221cc88ea3cb24881e4a","status":"active","name":"weed discrimination","description":"The ability to distinguish weeds from other image objects or crop plants.","types":["task"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_2cd9d50b0cc3221cc88ea3cb24881e4a"},{"public_id":"co_38dfdbe8188d1f1a8e465d4a9dbd0639","status":"active","name":"Random Forest classifier","description":"A machine learning classifier that uses an ensemble of decision trees for classification.","types":["machine learning model"],"aliases":["RF classifier"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_38dfdbe8188d1f1a8e465d4a9dbd0639"},{"public_id":"co_3c32d6267697cd20531b9989170975f9","status":"active","name":"Random Forest","description":"An ensemble learning method based on many decision trees.","types":["machine learning method"],"aliases":["RF"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_3c32d6267697cd20531b9989170975f9"},{"public_id":"co_47a262574d30ba264bc81ca7de6219d5","status":"active","name":"class balanced training set","description":"A training sample set constructed to contain balanced representation across classes.","types":["training data"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_47a262574d30ba264bc81ca7de6219d5"},{"public_id":"co_56cae4d61d0b0da9a078ad22e8b50480","status":"active","name":"weed density","description":"The amount of weed presence within the observed crop area.","types":["scene characteristic"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_56cae4d61d0b0da9a078ad22e8b50480"},{"public_id":"co_6c60948a6c3064fda368a77d05e29105","status":"active","name":"weed maps","description":"Spatial maps showing the distribution of weeds in the field.","types":["map"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_6c60948a6c3064fda368a77d05e29105"},{"public_id":"co_6c6bc4c0cd3079428248b3a1c184616d","status":"active","name":"manual training","description":"Human-guided training of the classifier using manually selected samples.","types":["procedure"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_6c6bc4c0cd3079428248b3a1c184616d"},{"public_id":"co_77139e09207ec02e207782440ba0507e","status":"active","name":"site-specific weed management","description":"A weed management approach that targets interventions to specific field locations.","types":["management approach"],"aliases":["SSWM"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_77139e09207ec02e207782440ba0507e"},{"public_id":"co_99987ecf3de6561d51d745e4cea3a9aa","status":"active","name":"early post-emergence weed mapping","description":"The spatial identification and mapping of weeds soon after crop and weed emergence.","types":["task"],"aliases":["early weed mapping"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_99987ecf3de6561d51d745e4cea3a9aa"},{"public_id":"co_b4deff8c43b41856b3767508404c85ae","status":"active","name":"automatic object-based image analysis algorithm","description":"An automated object-based image analysis workflow used to process UAV imagery for weed mapping.","types":["method"],"aliases":["automatic OBIA algorithm","OBIA algorithm"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_b4deff8c43b41856b3767508404c85ae"},{"public_id":"co_ce2919983326dc1bd28f7b78d2095734","status":"active","name":"UAV imagery","description":"Aerial images acquired from an unmanned aerial vehicle and used as the input data source.","types":["data source"],"aliases":["Unmanned Aerial Vehicle imagery"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_ce2919983326dc1bd28f7b78d2095734"},{"public_id":"co_d9a1bdd789dc6484baf2d0da05851854","status":"active","name":"prescription maps","description":"Application maps that specify where and how much treatment should be applied in the field.","types":["map"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_d9a1bdd789dc6484baf2d0da05851854"},{"public_id":"co_fbd195d203959017002a8afcd976ff7a","status":"active","name":"automatic sample selection","description":"A process for selecting training samples automatically for classifier learning.","types":["procedure"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_fbd195d203959017002a8afcd976ff7a"},{"public_id":"co_fc847b538ad6a2e859da4b43b0ed2bad","status":"active","name":"OBIA-based plant heights","description":"Plant height estimates derived from object-based image analysis features.","types":["feature"],"aliases":["plant heights"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_fc847b538ad6a2e859da4b43b0ed2bad"}],"external_ids":{"DOI":"10.3390/rs10020285","ArXiv":null,"PubMed":null,"PubMedCentral":null,"MAG":2790858865,"DBLP":"journals/remotesensing/CastroTPJCL18","ACL":null},"open_access":{"is_open_access":true,"pdf_url":"https://www.mdpi.com/2072-4292/10/2/285/pdf?version=1518430558","landing_url":"https://www.semanticscholar.org/paper/0ce55b631203a2aaaa506dbc20d0b91ea1bd5485","source":"semantic_scholar","pdf_url_source":"semantic_scholar_open_access_pdf","license":"CCBY","status":"GOLD","reason":null},"reference_availability":{"status":"available","references_indexed":true,"full_text_available":false,"full_text_source":null,"count_basis":"semantic_scholar_metadata","extraction_status":"not_applicable","reason":null},"source":{"provider":"episteme2","base_corpus":"semantic_scholar_dump","freshness_mode":"unknown","basis":["semantic_scholar_metadata","postgres_metadata"],"limits":["paper metadata is based on indexed upstream scholarly datasets","claims and concepts are available only for extracted papers","absence of claims or concepts means no extracted graph data is available in this response"],"status":"available","degraded":false,"degraded_reasons":[],"diagnostics":{"status":"available","degraded":false,"degraded_reasons":[],"metadata_status":"available","graph_status":"available","abstract_status":"available"},"source_flags":1},"paper_id":631292,"paper_uid":"de32b4ca-a6eb-414f-8cad-4398b415ff6b","canonical_identity":{"paper_id":631292,"paper_uid":"de32b4ca-a6eb-414f-8cad-4398b415ff6b","identity_status":"available","lookup_basis":"semantic_scholar_external_id","compatibility_path":"corpus_id"},"url":"https://sah.borca.ai/papers/3824984"}