A video processing and data retrieval framework for fish population monitoring

@inproceedings{BeauxisAussalet2013AVP,
  title={A video processing and data retrieval framework for fish population monitoring},
  author={Emma Beauxis-Aussalet and Simone Palazzo and Gayathri Devi Nadarajan and Elvira Arslanova and Concetto Spampinato and Lynda Hardman},
  booktitle={MAED '13},
  year={2013}
}
In this work we present a framework for fish population monitoring through the analysis of underwater videos. We specifically focus on the user information needs, and on the dynamic data extraction and retrieval mechanisms that support them. Sophisticated though a software tool may be, it is ultimately important that its interface satisfies users' actual needs and that users can easily focus on the specific data of interest. In the case of fish population monitoring, marine biologists have to… 

Figures from this paper

Interactive Visualization of Video Data for Fish Population Monitoring
TLDR
This work presents a visualization interface addressing two challenges: providing information about fish populations as well as computer vision uncertainty; and enabling the exploration of specific subsets of the video data depending on user needs.
Video Based Live Tracking of Fishes in Tanks
TLDR
A system to tackle the challenge of tracking and classifying fish in real time, using Background Subtraction techniques to detect the fish, followed by Feature Matching methods to track their movements over time.
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.
Large Scale Data Processing in Ecology: A Case Study on Long-Term Underwater Video Monitoring
TLDR
A case study of large-scale video processing on HPC facilities for underwater fish monitoring in the context of the Fish4Knowledge project 3, where a system to analyse long-term underwater camera footage has been developed.
Uncertainty-Aware Visualization of Fish Populations
TLDR
An interface for studying sh populations is presented that addresses two challenges: provide information about sh populations as well as computer vision uncertainty; and enable open-ended data exploration.
Coastal observatories for monitoring of fish behaviour and their responses to environmental changes
TLDR
Two key approaches for the future improvement of cabled observatory technology are: the application of Artificial Intelligence to aid in the analysis of increasingly large, complex, and highly interrelated biological and environmental data sets, and the development of geographical observational networks to enable the reliable spatial analysis of observed populations over extended distances.
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.
Uncertainty-aware estimation of population abundance using machine learning
TLDR
This work proposes a method that improves classification quality by using limited groundtruth data to extrapolate the potential errors in larger datasets and significantly improves the counting of elements per class.
Summary abstract for the 2nd ACM international workshop on multimedia analysis for ecological data
The 2nd ACM International Workshop on Multimedia Analysis for Ecological Data (MAED'13) is held as part of ACM Multimedia 2013. MAED'13, following the first workshop of the MAED series (MAED'12) that
Underwater human body detection using computer vision algorithms
TLDR
Thresholding, Background Subtraction, Interframe Difference and Foreground Detection methods have been applied to create the silhouette of the people under the water to detect and to track the people in a risk of suffocation in the water quickly.
...
...

References

SHOWING 1-10 OF 20 REFERENCES
Particle Filter-Based Predictive Tracking for Robust Fish Counting
TLDR
The proposed approach provides adequate means for the acquisition of relevant information about characteristics of different fish species such as swimming ability, time of migration and peak flow rates, and is able to estimate fish trajectories over time.
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
Quantitative performance analysis of object detection algorithms on underwater video footage
TLDR
Six state-of-the-art object detection algorithms are evaluated in the task of fish detection in unconstrained, underwater video footage, discussing the properties of each of them and giving a detailed report of the achieved performance.
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.
Detecting, Tracking and Counting Fish in Low Quality Unconstrained Underwater Videos
TLDR
Unlike existing fish-counting methods, this approach provides a reliable method in which the fish number is computed in unconstrained environments and under several scenarios (murky water, algae on camera lens, moving plants, low contrast, etc.).
Detecting fish in underwater video using the EM algorithm
  • Fiona F. Evans
  • Computer Science
    Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429)
  • 2003
We consider the problem of detecting fish in underwater video. We adopt a modeling framework, where the shape of each fish is assumed to be multivariate Gaussian. Mixture modeling is used to classify
Underwater Live Fish Recognition Using a Balance-Guaranteed Optimized Tree
TLDR
This work presents a Balance-Guaranteed Optimized Tree (BGOT) to control the error accumulation in hierarchical classification and, therefore, achieve better performance on a live fish image dataset.
Semantics and Planning Based Workflow Composition for Video Processing
TLDR
This work proposes a novel workflow composition approach that hinges upon ontologies and planning as its core technologies within an integrated framework that provides a speed up of over 90 % in execution time for video classification tasks using full automatic processing compared to manual methods without loss of accuracy.
Evaluation of tracking algorithm performance without ground-truth data
TLDR
This paper proposes a novel tool that enables image processing researchers to test the performance of tracking algorithms without resorting to hand-labeled ground truth data and shows how this approach is able to reflect the quality of the performed tracking.
Enhancing object detection performance by integrating motion objectness and perceptual organization
  • C. Spampinato, S. Palazzo
  • Computer Science
    Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012)
  • 2012
TLDR
A method to improve the performance of motion detection algorithms by estimating the probability that a detected blob is actually an object of interest, which was trained and tested on two “real-life” environments and showed an increase of theperformance of four state-of-art motion detectiongorithms.
...
...