{"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/deep-fruit-detection-in-orchards","title":"Deep Fruit Detection in Orchards","arxiv_id":"1610.03677","date":"2016-10-12","proceeding":null,"authors":["Suchet Bargoti","James Underwood"],"abstract":"An accurate and reliable image based fruit detection system is critical for\nsupporting higher level agriculture tasks such as yield mapping and robotic\nharvesting. This paper presents the use of a state-of-the-art object detection\nframework, Faster R-CNN, in the context of fruit detection in orchards,\nincluding mangoes, almonds and apples. Ablation studies are presented to better\nunderstand the practical deployment of the detection network, including how\nmuch training data is required to capture variability in the dataset. Data\naugmentation techniques are shown to yield significant performance gains,\nresulting in a greater than two-fold reduction in the number of training images\nrequired. In contrast, transferring knowledge between orchards contributed to\nnegligible performance gain over initialising the Deep Convolutional Neural\nNetwork directly from ImageNet features. Finally, to operate over orchard data\ncontaining between 100-1000 fruit per image, a tiling approach is introduced\nfor the Faster R-CNN framework. The study has resulted in the best yet\ndetection performance for these orchards relative to previous works, with an\nF1-score of >0.9 achieved for apples and mangoes.","url_abs":"http://arxiv.org/abs/1610.03677v2","url_pdf":"http://arxiv.org/pdf/1610.03677v2.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":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"faster-r-cnn","method_name":"Faster R-CNN"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"roipool","method_name":"RoIPool"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[{"slug":"acfr-orchard-fruit-dataset","name":"ACFR Orchard Fruit Dataset","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}