{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/multispecies-fruit-flower-detection-using-a","title":"Multispecies fruit flower detection using a refined semantic segmentation network","arxiv_id":"1809.10080","date":"2018-09-20","proceeding":null,"authors":["Dias Philipe A.","Tabb Amy","Medeiros Henry"],"abstract":"In fruit production, critical crop management decisions are guided by bloom\nintensity, i.e., the number of flowers present in an orchard. Despite its\nimportance, bloom intensity is still typically estimated by means of human\nvisual inspection. Existing automated computer vision systems for flower\nidentification are based on hand-engineered techniques that work only under\nspecific conditions and with limited performance. This work proposes an\nautomated technique for flower identification that is robust to uncontrolled\nenvironments and applicable to different flower species. Our method relies on\nan end-to-end residual convolutional neural network (CNN) that represents the\nstate-of-the-art in semantic segmentation. To enhance its sensitivity to\nflowers, we fine-tune this network using a single dataset of apple flower\nimages. Since CNNs tend to produce coarse segmentations, we employ a refinement\nmethod to better distinguish between individual flower instances. Without any\npre-processing or dataset-specific training, experimental results on images of\napple, peach and pear flowers, acquired under different conditions demonstrate\nthe robustness and broad applicability of our method.","url_abs":"http://arxiv.org/abs/1809.10080v1","url_pdf":"http://arxiv.org/pdf/1809.10080v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"management","task_name":"Management"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[{"slug":"multi-species-fruit-flower-detection-datasets","name":"Multi-species fruit flower detection datasets","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}