• About
  • About the Department
  • Contact
  • Directions
  • Partners
  • Rooms
  • Systems & Software
  • Conduit
  • News
  • Events
• People
  • Our Community
  • Faculty
  • Staff
  • Grad Students
  • Ugrad Students
  • Alums
  • Directory
• Research
  • Research Links
  • Areas
  • Publications
• Degrees
  • Degree Programs
  • Doctoral
  • Masters
  • Undergrad
  • Programs
  • Miscellaneous
• Courses
  • Course List
  • Schedule
  • Sections
  • TA Program

Thesis Proposal

"Supporting Complex Tasks in Visual Sensor Networks"

Jie Mao

Wednesday, December 16, 2009 at 1:00 P.M.

Lubrano Conference Room (CIT 4th floor)

Visual sensor networks (VSN) are networks of smart cameras capable of local image processing and data communication. Different from traditional camera-based surveillance network where cameras simply stream their image data to a centralized server for processing, cameras in VSNs form a distributed system, performing information extraction and collaborating on application-specific tasks. Due to the resource constraints of the camera nodes such as restricted computation capacity, remaining battery power and available bandwidth, VSNs usually need to limit the amount of data being exchanged among the camera nodes and the complexity of algorithms running on the camera nodes.

This thesis work shows how complex vision tasks can be integrated with networking requirements in two different VSN contexts. The first context is large-scale ad-hoc wireless smart cameras working on battery power which resembles the architecture of general wireless sensor networks. In this context we build geographic hash table (GHT) based network protocols adaptive to the nature of image sensors. These protocols decouple the events from the camera locations. Simulation results show that these protocols allow efficient distributed camera calibration and event-based constraint processing. The second context is smaller-scale static wired smart cameras with constant power supplies which can be found in public spaces that need surveillance such as airports and casinos. We avoid heavy-weight processing by employing only basic feature sets and simple vision algorithms. Simple vision algorithms are fallible by themselves, but can be fused to produce credible results comparable to richer features with more resource-hungry algorithms. We build a real camera network with resource management and exploit the spatial-temporal relationships among cameras based on their overlapping or nearby field-of-views to allow efficient camera collaborations and maximize the effectiveness of data exchange.

Host: John Jannotti