T
Teresa Ko
Researcher at University of California, Los Angeles
Publications - 31
Citations - 520
Teresa Ko is an academic researcher from University of California, Los Angeles. The author has contributed to research in topics: Wireless sensor network & Key distribution in wireless sensor networks. The author has an hindex of 12, co-authored 31 publications receiving 517 citations. Previous affiliations of Teresa Ko include Google & Sandia National Laboratories.
Papers
More filters
Book ChapterDOI
Background Subtraction on Distributions
TL;DR: In this article, the authors developed a background modeling and subtraction scheme that analyzes the temporal variation of intensity or color distributions, instead of either looking at temporal variations of point statistics, or the spatial variation of region statistics in isolation.
Patent
Information-based self-organization of sensor nodes of a sensor network
Teresa Ko,Nina M. Berry +1 more
TL;DR: In this paper, a sensor node detects a plurality of information-based events and determines whether at least one other sensor node is an information neighbor of the sensor node based on at least a portion of the plurality of events.
Proceedings ArticleDOI
Warping background subtraction
TL;DR: A background model that differentiates between background motion and foreground objects is presented, and changes in intensity/color histograms of pixel neighborhoods can be used to discriminate foreground and background regions.
Journal ArticleDOI
Heartbeat of a nest: Using imagers as biological sensors
Teresa Ko,Shaun Ahmadian,John Hicks,Mohammad Rahimi,Deborah Estrin,Stefano Soatto,Sharon Coe,Michael Hamilton +7 more
TL;DR: In this article, a scalable end-to-end system for vision-based monitoring of natural environments, and illustrate its use for the analysis of avian nesting cycles is presented.
Journal Article
Heartbeat of a Nest: Using Imagers as Biological Sensors
Shaun Ahmadian,Teresa Ko,Sharon Coe,Michael Hamilton,Mohammad Rahimi,Stefano Soatto,Deborah Estrin +6 more
TL;DR: A scalable end-to-end system for vision-based monitoring of natural environments, and its use for the analysis of avian nesting cycles is illustrated and an exploration of system performance under varying image resolution and frame rate suggest that an in situ adaptive vision system is technically feasible.