Skip to main navigation Skip to search Skip to main content

Poster: DNN Models for Underground Root Tuber Image Reconstruction using WiFi CSI

  • Said Elhadi
  • , Yang Zhao*
  • *Corresponding author for this work
  • Harbin Institute of Technology Shenzhen

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Non-invasive monitoring of underground biomass like root tubers is vital for smart agriculture. We present a wireless sensing system using Wi-Fi Channel State Information (CSI) from a low-cost ESP32 mesh network for high-resolution underground tuber imaging. Our approach uses synchronized CSI data collection and deep neural network (DNN) models including UNet, FCN and DeepLabV3+ for image reconstruction. We describe the testbed, data processing, experiments and DNN models in this paper. Comparative results show DNN models using the CSI data significantly outperforms those using traditional RSSI data. The DeepLabV3+ model using CSI data achieves the best imaging accuracy with an IoU of 0.6971, demonstrating the potential of WiFi CSI for fine-grained underground tuber sensing.

Original languageEnglish
Title of host publicationMobiSys 2025 - Proceedings of the 23rd ACM international Conference on Mobile Systems, Applications, and Services
PublisherAssociation for Computing Machinery, Inc
Pages613-614
Number of pages2
ISBN (Electronic)9798400714535
DOIs
StatePublished - 25 Sep 2025
Externally publishedYes
Event23rd ACM International Conference on Mobile Systems, Applications, and Services, MobiSys 2025 - Anaheim, United States
Duration: 23 Jun 202527 Jun 2025

Publication series

NameMobiSys 2025 - Proceedings of the 23rd ACM international Conference on Mobile Systems, Applications, and Services

Conference

Conference23rd ACM International Conference on Mobile Systems, Applications, and Services, MobiSys 2025
Country/TerritoryUnited States
CityAnaheim
Period23/06/2527/06/25

Keywords

  • deep neural network
  • image reconstruction
  • mesh networks
  • underground sensing
  • wi-fi CSI

Fingerprint

Dive into the research topics of 'Poster: DNN Models for Underground Root Tuber Image Reconstruction using WiFi CSI'. Together they form a unique fingerprint.

Cite this