Conference paper Open Access

Through-Screen Visible Light Sensing Empowered by Embedded Deep Learning

Liu, Hao; Ye, Hanting; Yang, Jie; Wang, Qing


JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/a5b1b6d2-c8d3-436c-889d-124bb2fe4a71/AIChallengeIoT2021_Through-Screen%20VLS.pdf"
      }, 
      "checksum": "md5:9fc03485ef13a9329b8301fc86ffa802", 
      "bucket": "a5b1b6d2-c8d3-436c-889d-124bb2fe4a71", 
      "key": "AIChallengeIoT2021_Through-Screen VLS.pdf", 
      "type": "pdf", 
      "size": 1297786
    }
  ], 
  "owners": [
    64376
  ], 
  "doi": "10.1145/3485730.3493454", 
  "stats": {
    "version_unique_downloads": 12.0, 
    "unique_views": 24.0, 
    "views": 24.0, 
    "version_views": 24.0, 
    "unique_downloads": 12.0, 
    "version_unique_views": 24.0, 
    "volume": 15573432.0, 
    "version_downloads": 12.0, 
    "downloads": 12.0, 
    "version_volume": 15573432.0
  }, 
  "links": {
    "doi": "https://doi.org/10.1145/3485730.3493454", 
    "latest_html": "https://zenodo.org/record/5646942", 
    "bucket": "https://zenodo.org/api/files/a5b1b6d2-c8d3-436c-889d-124bb2fe4a71", 
    "badge": "https://zenodo.org/badge/doi/10.1145/3485730.3493454.svg", 
    "html": "https://zenodo.org/record/5646942", 
    "latest": "https://zenodo.org/api/records/5646942"
  }, 
  "created": "2021-11-05T08:16:04.090581+00:00", 
  "updated": "2021-11-05T13:48:32.259791+00:00", 
  "conceptrecid": "5646941", 
  "revision": 2, 
  "id": 5646942, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.1145/3485730.3493454", 
    "description": "<p>Motivated by the trend of realizing full screens on devices such as smartphones, in this work we propose through-screen sensing with visible light for the application of fingertip air-writing. The system can recognize handwritten digits with under-screen photodiodes as the receiver. The key idea is to recognize the weak light reflected by the finger when the finger writes the digits on top of a screen. The proposed air-writing system has immunity to scene changes because it has a fixed screen light source. However, the screen is a double-edged sword as both a signal source and a noise source. We propose a data preprocessing method to reduce the interference of the screen as a noise source. We design an embedded deep learning model, a customized model ConvRNN, to model the spatial and temporal patterns in the dynamic and weak reflected signal for air-writing digits recognition. The evaluation results show that our through-screen fingertip air-writing system with visible light can achieve accuracy up to 91%. Results further show that the size of the customized ConvRNN model can be reduced by 94% with less<br>\nthan a 10% drop in performance.</p>", 
    "license": {
      "id": "CC-BY-4.0"
    }, 
    "title": "Through-Screen Visible Light Sensing Empowered by Embedded Deep Learning", 
    "relations": {
      "version": [
        {
          "count": 1, 
          "index": 0, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "5646941"
          }, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "5646942"
          }
        }
      ]
    }, 
    "grants": [
      {
        "code": "814215", 
        "links": {
          "self": "https://zenodo.org/api/grants/10.13039/501100000780::814215"
        }, 
        "title": "European Training Network in Low-energy Visible Light IoT Systems", 
        "acronym": "ENLIGHTEM", 
        "program": "H2020", 
        "funder": {
          "doi": "10.13039/501100000780", 
          "acronyms": [], 
          "name": "European Commission", 
          "links": {
            "self": "https://zenodo.org/api/funders/10.13039/501100000780"
          }
        }
      }
    ], 
    "publication_date": "2021-11-05", 
    "creators": [
      {
        "affiliation": "TU Delft", 
        "name": "Liu, Hao"
      }, 
      {
        "affiliation": "TU Delft", 
        "name": "Ye, Hanting"
      }, 
      {
        "affiliation": "TU Delft", 
        "name": "Yang, Jie"
      }, 
      {
        "affiliation": "TU Delft", 
        "name": "Wang, Qing"
      }
    ], 
    "meeting": {
      "acronym": "AIChallengeIoT", 
      "url": "https://aichallengeiot.github.io/", 
      "dates": "15-17 November 2021", 
      "place": "Coimbra, Portugal", 
      "title": "Workshop on Workshop on Challenges in Artificial Intelligence and Machine Learning for Internet of Things in conjuction with ACM SenSys 2021"
    }, 
    "access_right": "open", 
    "resource_type": {
      "subtype": "conferencepaper", 
      "type": "publication", 
      "title": "Conference paper"
    }
  }
}
24
12
views
downloads
Views 24
Downloads 12
Data volume 15.6 MB
Unique views 24
Unique downloads 12

Share

Cite as