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.

(2013). Detecting abnormal fish trajectories using clustered and labeled data . Retrieved from https://hdl.handle.net/10446/260642

Detecting abnormal fish trajectories using clustered and labeled data

Beyan, Cigdem;
2013-01-01

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.
2013
Beyan, Cigdem; Fisher, Robert B.
File allegato/i alla scheda:
File Dimensione del file Formato  
IC07_Detecting abnormal fish trajectories using clustered and labeled data.pdf

Solo gestori di archivio

Versione: publisher's version - versione editoriale
Licenza: Licenza default Aisberg
Dimensione del file 864.28 kB
Formato Adobe PDF
864.28 kB Adobe PDF   Visualizza/Apri
ICIP 2013 cover+INDEX.pdf

Solo gestori di archivio

Versione: cover/index - copertina/indice
Licenza: Licenza default Aisberg
Dimensione del file 375.47 kB
Formato Adobe PDF
375.47 kB Adobe PDF   Visualizza/Apri
Pubblicazioni consigliate

Aisberg ©2008 Servizi bibliotecari, Università degli studi di Bergamo | Terms of use/Condizioni di utilizzo

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10446/260642
Citazioni
  • Scopus 29
  • ???jsp.display-item.citation.isi??? 19
social impact