{"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/object-detection-through-exploration-with-a","title":"Object Detection Through Exploration With A Foveated Visual Field","arxiv_id":"1408.0814","date":"2014-08-04","proceeding":null,"authors":["Emre Akbas","Miguel P. Eckstein"],"abstract":"We present a foveated object detector (FOD) as a biologically-inspired\nalternative to the sliding window (SW) approach which is the dominant method of\nsearch in computer vision object detection. Similar to the human visual system,\nthe FOD has higher resolution at the fovea and lower resolution at the visual\nperiphery. Consequently, more computational resources are allocated at the\nfovea and relatively fewer at the periphery. The FOD processes the entire\nscene, uses retino-specific object detection classifiers to guide eye\nmovements, aligns its fovea with regions of interest in the input image and\nintegrates observations across multiple fixations. Our approach combines modern\nobject detectors from computer vision with a recent model of peripheral pooling\nregions found at the V1 layer of the human visual system. We assessed various\neye movement strategies on the PASCAL VOC 2007 dataset and show that the FOD\nperforms on par with the SW detector while bringing significant computational\ncost savings.","url_abs":"http://arxiv.org/abs/1408.0814v2","url_pdf":"http://arxiv.org/pdf/1408.0814v2.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":[{"paper_slug":"object-detection-through-exploration-with-a","repo_url":"https://github.com/ArturoDeza/Piranhas","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1408.0814","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}