{"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/person-in-wifi-fine-grained-person-perception","title":"Person-in-WiFi: Fine-grained Person Perception using WiFi","arxiv_id":"1904.00276","date":"2019-03-30","proceeding":"ICCV 2019 10","authors":["Fei Wang","Sanping Zhou","Stanislav Panev","Jinsong Han","Dong Huang"],"abstract":"Fine-grained person perception such as body segmentation and pose estimation\nhas been achieved with many 2D and 3D sensors such as RGB/depth cameras, radars\n(e.g., RF-Pose) and LiDARs. These sensors capture 2D pixels or 3D point clouds\nof person bodies with high spatial resolution, such that the existing\nConvolutional Neural Networks can be directly applied for perception. In this\npaper, we take one step forward to show that fine-grained person perception is\npossible even with 1D sensors: WiFi antennas. To our knowledge, this is the\nfirst work to perceive persons with pervasive WiFi devices, which is cheaper\nand power efficient than radars and LiDARs, invariant to illumination, and has\nlittle privacy concern comparing to cameras. We used two sets of off-the-shelf\nWiFi antennas to acquire signals, i.e., one transmitter set and one receiver\nset. Each set contains three antennas lined-up as a regular household WiFi\nrouter. The WiFi signal generated by a transmitter antenna, penetrates through\nand reflects on human bodies, furniture and walls, and then superposes at a\nreceiver antenna as a 1D signal sample (instead of 2D pixels or 3D point\nclouds). We developed a deep learning approach that uses annotations on 2D\nimages, takes the received 1D WiFi signals as inputs, and performs body\nsegmentation and pose estimation in an end-to-end manner. Experimental results\non over 100000 frames under 16 indoor scenes demonstrate that Person-in-WiFi\nachieved person perception comparable to approaches using 2D images.","url_abs":"http://arxiv.org/abs/1904.00276v1","url_pdf":"http://arxiv.org/pdf/1904.00276v1.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":"person-in-wifi-fine-grained-person-perception","repo_url":"https://github.com/geekfeiw/wifiperson","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"rf-based-pose-estimation","task_name":"RF-based Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1904.00276","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}