Change Detection and Blob Tracking of Fish in Underwater Scenarios

In this paper, the difficult task of detecting fishes in underwater scenarios is analyzed with a special focus on crowded scenes where the differentiation between separate fishes is even more challenging. An extension for the Gaussian Switch Model is developed for the detection which applies an intelligent update scheme to create more accurate background models even for difficult scenes. To deal with very crowded areas in the scene we use the Flux Tensor to create a first coarse segmentation and only update areas that are with high certainty background. The spatial coherency is increased by the N\(^2\)Cut, which is a Ncut adaption to change detection. More relevant information are gathered with a novel blob tracker that uses a specially developed energy function and handling of errors during the change detection. This method keeps the generality of the whole approach so that it can be used for any moving object. The proposed algorithm enabled us to get very accurate underwater segmentations as well as precise results in tracking scenarios.

[1]  Majid Mirmehdi,et al.  Multiple human tracking in RGB-depth data: a survey , 2017, IET Comput. Vis..

[2]  Afshin Dehghan,et al.  Part-based multiple-person tracking with partial occlusion handling , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Alex Pentland,et al.  Pfinder: Real-Time Tracking of the Human Body , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Konrad Schindler,et al.  Smooth Foreground-Background Segmentation for Video Processing , 2006, ACCV.

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

[6]  Jun-Seok Oh,et al.  Road sign detection and shape recognition invariant to sign defects , 2012, 2012 IEEE International Conference on Electro/Information Technology.

[7]  Konrad Schindler,et al.  Multi-target tracking by continuous energy minimization , 2011, CVPR 2011.

[8]  Rui Wang,et al.  Static and Moving Object Detection Using Flux Tensor with Split Gaussian Models , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[9]  Joachim Denzler,et al.  Multi-person Tracking-by-Detection Based on Calibrated Multi-camera Systems , 2012, ICCVG.

[10]  Pascal Fua,et al.  Robust People Tracking with Global Trajectory Optimization , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[11]  Fahimeh Farhadifard,et al.  Dataset on underwater change detection , 2016, OCEANS 2016 MTS/IEEE Monterey.

[12]  S. Bianco,et al.  How Far Can You Get By Combining Change Detection Algorithms? , 2015, ICIAP.

[13]  P. KaewTrakulPong,et al.  An Improved Adaptive Background Mixture Model for Real-time Tracking with Shadow Detection , 2002 .

[14]  Luc Van Gool,et al.  Online Multiperson Tracking-by-Detection from a Single, Uncalibrated Camera , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Uwe von Lukas,et al.  Change Detection in Crowded Underwater Scenes - Via an Extended Gaussian Switch Model Combined with a Flux Tensor Pre-segmentation , 2017, VISIGRAPP.

[16]  Jörg Franke,et al.  Implementation of the Hungarian Method for object tracking on a camera monitored transportation system , 2012, ROBOTIK.

[17]  Ferdinand van der Heijden,et al.  Efficient adaptive density estimation per image pixel for the task of background subtraction , 2006, Pattern Recognit. Lett..

[18]  H. Kuhn.  The Hungarian method for the assignment problem , 1955 .

[19]  W. Eric L. Grimson,et al.  Adaptive background mixture models for real-time tracking , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[20]  J. Ferryman,et al.  PETS2009: Dataset and challenge , 2009, 2009 Twelfth IEEE International Workshop on Performance Evaluation of Tracking and Surveillance.

[21]  Bin Wang,et al.  Structure Integral Transform Versus Radon Transform: A 2D Mathematical Tool for Invariant Shape Recognition , 2016, IEEE Transactions on Image Processing.

[22]  Z. Zivkovic.  Improved adaptive Gaussian mixture model for background subtraction , 2004, ICPR 2004.

[23]  Enrico Gutzeit,et al.  Video Segmentation via a Gaussian Switch Background Model and Higher Order Markov Random Fields , 2015, VISAPP.

[24]  Xiangjun Liu,et al.  Object Tracking Based on Local Feature Matching , 2012, 2012 Fifth International Symposium on Computational Intelligence and Design.

[25]  Guna Seetharaman,et al.  Flux Tensor Constrained Geodesic Active Contours with Sensor Fusion for Persistent Object Tracking , 2007, J. Multim..

[26]  Rainer Stiefelhagen,et al.  Evaluating Multiple Object Tracking Performance: The CLEAR MOT Metrics , 2008, EURASIP J. Image Video Process..

[27]  N. L. Seed,et al.  Approaches to static background identification and removal , 1993 .

[28]  Uwe von Lukas,et al.  Real time video segmentation optimization with a modified Normalized Cut , 2015, 2015 9th International Symposium on Image and Signal Processing and Analysis (ISPA).