Multifactorial uncertainty assessment for monitoring population abundance using computer vision

@article{BeauxisAussalet2015MultifactorialUA,
  title={Multifactorial uncertainty assessment for monitoring population abundance using computer vision},
  author={Emma Beauxis-Aussalet and Lynda Hardman},
  journal={2015 IEEE International Conference on Data Science and Advanced Analytics (DSAA)},
  year={2015},
  pages={1-10}
}
  • Emma Beauxis-Aussalet, L. Hardman
  • Published 2015
  • Environmental Science, Computer Science
  • 2015 IEEE International Conference on Data Science and Advanced Analytics (DSAA)
Computer vision enables in-situ monitoring of animal populations at a lower cost and with less ecosystem disturbance than with human observers. However, computer vision uncertainty may not be fully understood by end-users, and the uncertainty assessments performed by technology experts may not fully address end-user needs. This knowledge gap can yield misinterpretations of computer vision data, and trust issues impeding the transfer of valuable technologies. We bridge this gap with a user… 

Figures and Tables from this paper

Understanding Uncertainty Issues in the Exploration of Fish Counts
TLDR
This chapter discusses the means for ecologists to investigate the uncertainty in computer vision results, and addresses a set of uncertainty factors identified by interviewing both ecology and computer vision experts.
Fish4Knowledge: Collecting and Analyzing Massive Coral Reef Fish Video Data
TLDR
This book is a useful resource for system builders, as it gives an overview of the many new methods that were created to build the Fish4Knowledge system in a manner that also allows readers to see how all the components fit together.
Extended Methods to Handle Classification Biases
TLDR
This work presents the applicability and drawbacks of existing methods and extends them with three novel methods for bias correction, and discusses the need for establishing theory and guidelines for choosing the methods and classifier to apply.

References

SHOWING 1-10 OF 38 REFERENCES
Uncertainty propagation in models driven by remotely sensed data
Do you need experts in the crowd?: a case study in image annotation for marine biology
TLDR
This paper studies a case where the goal is to identify fish species in images extracted from videos taken by underwater cameras, a task that typically requires profound domain knowledge in marine biology and hence would be difficult, if not impossible, for the crowd.
Supporting Non-Experts' Awareness of Uncertainty: Negative Effects of Simple Visualizations in Multiple Views
TLDR
A study of an interactive visualization of computer vision results and uncertainty and the design and insights contribute to other cases where non-experts need to familiarize with novel datasets and explore their uncertainty.
Automated processing and identification of benthic invertebrate samples
TLDR
BugID is the first system of its kind that allows users to select thresholds for rejection depending on the required use, and has several advantages over other automated insect classification systems, including automated handling of specimens, the able to isolate nontarget and novel species, and the ability to identify specimens across different stages of larval development.
A case study of trust issues in scientific video collections
TLDR
The main finding is that disclosing details about the video processing and provenance data allows biologists to compare the results with their traditional statistical methods, thus increasing their trust in the results.
Visualizing Geospatial Information Uncertainty: What We Know and What We Need to Know
TLDR
Progress toward visual tools and methods to help analysts manage and understand information uncertainty are reviewed and progress toward frameworks for representing uncertainty, visual representation and user control of displays of information uncertainty is assessed.
A framework for uncertainty-aware visual analytics
TLDR
It is shown that data transformations, such as regression, principal component analysis and k-means clustering, can be adapted to account for uncertainty and lead to better visualizations that improve the decision-making process and help analysts gain insight on the analytic process itself.
Proceedings of the 1st ACM international workshop on Multimedia analysis for ecological data
TLDR
The workshop outlines the state of the research on the most recent methods for the processing and interpretation of multimedia data recorded for monitoring ecological systems and accepts 7 papers covering the following topics.
Covariance based Fish Tracking in Real-life Underwater Environment
In this paper we present a covariance based tracking algorithm for intelligent video analysis to assist marine biologists in understanding the complex marine ecosystem in the Ken-Ding sub-tropical
Automated species identification: why not?
  • K. Gaston, M. O'Neill
  • Biology
    Philosophical transactions of the Royal Society of London. Series B, Biological sciences
  • 2004
TLDR
It is argued that progress in the development of automated species identification is extremely encouraging that such an approach has the potential to make a valuable contribution to reducing the burden of routine identifications.
...
...