Batteryless image sensors present an opportunity for long-life, long-range sensor deployments that require zero maintenance and have low cost. Such deployments are critical for enabling remote sensing applications, e.g. instrumenting national highways, where individual devices are deployed far (kms away) from supporting infrastructure. In this work, we develop and characterize Camaroptera, the first batteryless image-sensing platform to combine energy-harvesting with active, long-range (LoRa) communication. We also equip Camaroptera with a Machine Learning-based processing pipeline to mitigate costly, long-distance communication of image data. This processing pipeline filters out uninteresting images, and only transmits the images interesting to the application. We show that compared to running a traditional Sense-and-Send workload, Camaroptera’s Local Inference pipeline captures and sends upto 12 × more images of interest to an application. By performing Local Inference, Camaroptera also sends upto 6.5 × fewer uninteresting images, instead using that energy to capture upto 14.7 × more new images, increasing its sensing effectiveness and availability. We fully prototype the Camaroptera hardware platform in a compact, 2cm x 3cm x 5cm volume. Our evaluation demonstrates the viability of a batteryless, remote, visual-sensing platform in a small package that collects and usefully processes acquired data and transmits it over long distances (kms), while being deployed for multiple decades with zero maintenance.

Camaroptera: A Long-Range Image Sensor with Local Inference for Remote Sensing Applications / Desai, Harsh; Nardello, Matteo; Brunelli, Davide; Lucia, Brandon. - In: ACM TRANSACTIONS ON EMBEDDED COMPUTING SYSTEMS. - ISSN 1539-9087. - 21:3(2022), pp. 32.1-32.25. [10.1145/3510850]

Camaroptera: A Long-Range Image Sensor with Local Inference for Remote Sensing Applications

Nardello, Matteo
Secondo
;
Brunelli, Davide
Penultimo
;
2022-01-01

Abstract

Batteryless image sensors present an opportunity for long-life, long-range sensor deployments that require zero maintenance and have low cost. Such deployments are critical for enabling remote sensing applications, e.g. instrumenting national highways, where individual devices are deployed far (kms away) from supporting infrastructure. In this work, we develop and characterize Camaroptera, the first batteryless image-sensing platform to combine energy-harvesting with active, long-range (LoRa) communication. We also equip Camaroptera with a Machine Learning-based processing pipeline to mitigate costly, long-distance communication of image data. This processing pipeline filters out uninteresting images, and only transmits the images interesting to the application. We show that compared to running a traditional Sense-and-Send workload, Camaroptera’s Local Inference pipeline captures and sends upto 12 × more images of interest to an application. By performing Local Inference, Camaroptera also sends upto 6.5 × fewer uninteresting images, instead using that energy to capture upto 14.7 × more new images, increasing its sensing effectiveness and availability. We fully prototype the Camaroptera hardware platform in a compact, 2cm x 3cm x 5cm volume. Our evaluation demonstrates the viability of a batteryless, remote, visual-sensing platform in a small package that collects and usefully processes acquired data and transmits it over long distances (kms), while being deployed for multiple decades with zero maintenance.
2022
3
Desai, Harsh; Nardello, Matteo; Brunelli, Davide; Lucia, Brandon
Camaroptera: A Long-Range Image Sensor with Local Inference for Remote Sensing Applications / Desai, Harsh; Nardello, Matteo; Brunelli, Davide; Lucia, Brandon. - In: ACM TRANSACTIONS ON EMBEDDED COMPUTING SYSTEMS. - ISSN 1539-9087. - 21:3(2022), pp. 32.1-32.25. [10.1145/3510850]
File in questo prodotto:
File Dimensione Formato  
3510850.pdf

accesso aperto

Tipologia: Post-print referato (Refereed author’s manuscript)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.39 MB
Formato Adobe PDF
1.39 MB Adobe PDF Visualizza/Apri
3510850.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 5.44 MB
Formato Adobe PDF
5.44 MB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/332741
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 18
  • ???jsp.display-item.citation.isi??? 12
social impact