{"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/comparing-apples-and-oranges-off-road","title":"Comparing Apples and Oranges: Off-Road Pedestrian Detection on the NREC Agricultural Person-Detection Dataset","arxiv_id":"1707.07169","date":"2017-07-22","proceeding":null,"authors":["Zachary Pezzementi","Trenton Tabor","Peiyun Hu","Jonathan K. Chang","Deva Ramanan","Carl Wellington","Benzun P. Wisely Babu","Herman Herman"],"abstract":"Person detection from vehicles has made rapid progress recently with the\nadvent of multiple highquality datasets of urban and highway driving, yet no\nlarge-scale benchmark is available for the same problem in off-road or\nagricultural environments. Here we present the NREC Agricultural\nPerson-Detection Dataset to spur research in these environments. It consists of\nlabeled stereo video of people in orange and apple orchards taken from two\nperception platforms (a tractor and a pickup truck), along with vehicle\nposition data from RTK GPS. We define a benchmark on part of the dataset that\ncombines a total of 76k labeled person images and 19k sampled person-free\nimages. The dataset highlights several key challenges of the domain, including\nvarying environment, substantial occlusion by vegetation, people in motion and\nin non-standard poses, and people seen from a variety of distances; meta-data\nare included to allow targeted evaluation of each of these effects. Finally, we\npresent baseline detection performance results for three leading approaches\nfrom urban pedestrian detection and our own convolutional neural network\napproach that benefits from the incorporation of additional image context. We\nshow that the success of existing approaches on urban data does not transfer\ndirectly to this domain.","url_abs":"http://arxiv.org/abs/1707.07169v2","url_pdf":"http://arxiv.org/pdf/1707.07169v2.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":"human-detection","task_name":"Human Detection"},{"task_slug":"pedestrian-detection","task_name":"Pedestrian Detection"}],"methods":[],"datasets_introduced":[{"slug":"nrec-agricultural-person-detection","name":"NREC Agricultural Person-Detection","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}