SiWiS: Fine-grained Human Detection Using Single WiFi Device
Open Access
- 4 December 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1439-1454
Abstract
Sub-6GHz radio sensing offers several compelling advantages, such as resilience to poor lighting conditions, privacy preservation, and the ability to see through walls. However, in indoor environments, the sub-6GHz ISM spectrum is heavily occupied by WiFi devices, leaving little available spectrum for sensing purposes. In this paper, we introduce SiWiS, a new approach to integrate radio sensing capabilities into individual WiFi devices for fine-grained human activity detection. SiWiS comprises two main components: (i) a new hardware component that can be easily installed on an off-the-shelf WiFi device, and (ii) a dual-branch deep neural network (DNN) optimized for concurrent human mask segmentation and pose estimation. We have built a prototype of SiWiS and installed it on a commercial WiFi router for evaluation. Extensive experimental results demonstrate a significant performance improvement over WiFi channel state information (CSI) based sensing methods. More importantly, zero-shot experiments confirm that SiWiS can be directly transferred to unseen real-world environments.Keywords
Funding Information
- NSF (National Science Foundation) (ECCS-2225337, CNS-2100112)
This publication has 59 references indexed in Scilit:
- A survey on application in RF signalMultimedia Tools and Applications, 2023
- RadSense: Enabling one hand and no hands interaction for sterile manipulation of medical images using Doppler radarSmart Health, 2020
- Respiration and Activity Detection Based on Passive Radio Sensing in Home EnvironmentsIEEE Access, 2020
- CornerNet: Detecting Objects as Paired Keypoints2018
- Simple Baselines for Human Pose Estimation and Tracking2018
- Towards Accurate Multi-person Pose Estimation in the Wild2017
- Deep Residual Learning for Image Recognition2016
- Fully convolutional networks for semantic segmentation2015
- DeepPose: Human Pose Estimation via Deep Neural Networks2014
- Interfacing human and computer with wireless body area sensor networks: the WiMoCA solutionMultimedia Tools and Applications, 2008