Edinburgh Research Explorer

Detecting abnormal fish trajectories using clustered and labeled data

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

Related Edinburgh Organisations

Open Access permissions

Open

Documents

http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6738303&tag=1
Original languageEnglish
Title of host publicationImage Processing (ICIP), 2013 20th IEEE International Conference on
Pages1476-1480
Number of pages5
DOIs
Publication statusPublished - 1 Sep 2013

Abstract

We propose an approach for the analysis of fish trajectories in unconstrained underwater videos. Trajectories are classified into two classes: normal trajectories which contain the usual behavior of fish and abnormal trajectories which indicate the behaviors that are not as common as the normal class. The paper presents two innovations: 1) a novel approach to abnormal trajectory detection and 2) improved performance on video based abnormal trajectory analysis of fish in unconstrained conditions. First we extract a set of features from trajectories and apply PCA. We then perform clustering on a subset of features. Based on the clustering, outlier detection is applied to each cluster. Improved results are obtained which is significant considering the challenges of underwater environments, low video quality, and erratic movement of fish.

    Research areas

  • biology computing, feature extraction, object detection, pattern clustering, principal component analysis, video signal processing, PCA, abnormal fish trajectory detection, abnormal trajectory detection, clustered data, feature clustering, labeled data, outlier detection, unconstrained underwater videos, Abnormal Trajectory, Clustered and Labeled Data, Feature Selection, Fish Behavior, Outlier Detection

Download statistics

No data available

ID: 14135017