Automatic image capturing and processing for PetrolWatch

Yi Fei Dong*, Salil Kanhere, Chun Tung Chou, Ren Ping Liu

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contribution

13 Citations (Scopus)

Abstract

In our previous work [1], we proposed a Participatory Sensing (PS) architecture called PetrolWatch to collect and share fuel prices from camera images of road-side price board (billboard) of service (or gas) stations. A key part of the PetrolWatch architecture, and the main focus of this paper, is the automatic billboard image capture from a moving car without user intervention. We develop the system design and implementation of the automatic image collection for PetrolWatch. Capturing a clear image by an unassisted mobile phone from a moving car is proved to be a challenge by our street driving experiments. We design the camera control and image pre-selection schemes to address this challenge. In particular, we leverage the advanced capabilities of modern mobile phones to design an acceptable camera triggering range and set the camera focus accordingly. Experiment results show that our design improve fuel price extraction rate by more than 40%. To deal with blurred images caused by vehicle vibrations, we design a set of pre-selection thresholds based on the measures from embedded accelerometer of the mobile phone. Our experiments show that our pre-selection improves the system efficiency by eliminating 78.57% of the blurred images.

Original languageEnglish
Title of host publicationICON 2011
Subtitle of host publication17th IEEE International Conference on Networks
Place of PublicationPiscataway, NJ
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages236-240
Number of pages5
ISBN (Electronic)9781457718250, 9781457718267
ISBN (Print)9781457718243
DOIs
Publication statusPublished - 2011
Externally publishedYes
Event17th IEEE International Conference on Networks, ICON 2011 - Singapore, Singapore
Duration: 14 Dec 201116 Dec 2011

Other

Other17th IEEE International Conference on Networks, ICON 2011
CountrySingapore
CitySingapore
Period14/12/1116/12/11

Keywords

  • Automatic data collection
  • Computer-vision-based sensing
  • Consumer pricing information gathering
  • Participatory sensor networks
  • Vehicular sensor networks

Fingerprint Dive into the research topics of 'Automatic image capturing and processing for PetrolWatch'. Together they form a unique fingerprint.

Cite this