论文信息 - Overview of the LifeCLEF 2014 Fish Task

Overview of the LifeCLEF 2014 Fish Task

This paper describes the LifeCLEF 2014 fish task, which aimed at benchmarking automatic fish detection and recognition methods by processing underwater visual data. The task consisted of videobased subtasks for fish detection and fish species recognition in videos and one image-based task for fish species classification in still images. Our underwater visual datasets consisted of about 2,000 videos taken from the Fish4Knowledge video repository and more than 200,000 annotations automatically obtained and manually validated. About fifty teams registered to the fish task, but only two teams submitted runs: the I3S team for subtask 3 and LSIS/DYNI team for subtask 4. The results achieved by both teams are satisfactory.

Robert B. Fisher | Simone Palazzo | Concetto Spampinato | Bas Boom

[1] Hervé Glotin,et al. Sparse coding for histograms of local binary patterns applied for image categorization: Toward a Bag-of-Scenes analysis , 2012, Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012).

[2] Andrea Vedaldi,et al. Vlfeat: an open and portable library of computer vision algorithms , 2010, ACM Multimedia.

[3] Robert B. Fisher,et al. A research tool for long-term and continuous analysis of fish assemblage in coral-reefs using underwater camera footage , 2014, Ecol. Informatics.

[4] Simone Palazzo,et al. An innovative web-based collaborative platform for video annotation , 2014, Multimedia Tools and Applications.

[5] Simone Palazzo,et al. Nonparametric label propagation using mutual local similarity in nearest neighbors , 2015, Comput. Vis. Image Underst..

[6] Marc Van Droogenbroeck,et al. ViBe: A Universal Background Subtraction Algorithm for Video Sequences , 2011, IEEE Transactions on Image Processing.