Fish Detection And Tracking For Turbid Underwater Video

Object detection and tracking play a vital role in underwater research in recent+ decades. The uncontrolled scene and low visibility in an underwater environment usually makes moving fish object detection difficult. Our study is divided into two parts, in the first part we discuss the effect of varying turbidity on underwater color component and second part we implement an automatic fish detection and tracking algorithm from underwater video the turbidity plays the major role in detecting the initial points. The algorithm consists of two subsystems: Fish detection is based on hybrid algorithms in order to obtain accurate results and fish tracking in a video is performed using a Kalman filter. An experiment conducted in laboratory under controlled environment validated significant results. Obtained output states a detection rate for clear water with low turbidity at almost 95% and results for low quality with high turbidity of the water is above 80%.

[1]  Ekram Hossain,et al.  Fish activity tracking and species identification in underwater video , 2016, 2016 5th International Conference on Informatics, Electronics and Vision (ICIEV).

[2]  Ahmad Shahrizan Abdul Ghani,et al.  Integration of enhanced background filtering and wavelet fusion for high visibility and detection rate of deep sea underwater image of underwater vehicle , 2017, 2017 5th International Conference on Information and Communication Technology (ICoIC7).

[3]  Nazia Halim,et al.  Motion Capture Systems Using Optimal Signal Processing Algorithm: A State-of-the-art Literature , 2018 .

[4]  O. Delaunoy,et al.  Towards Detecting Changes in Underwater Image Sequences , 2008, OCEANS 2008 - MTS/IEEE Kobe Techno-Ocean.

[5]  Arto Kaarna,et al.  Using low-quality video sequences for fish detection and tracking , 2016, 2016 SAI Computing Conference (SAI).

[6]  Samarth Borkar,et al.  Comprehensive Survey on Underwater Object Detection and Tracking , 2018 .

[7]  Joo Kooi Tan,et al.  Moving objects detection employing iterative update of the background , 2017, Artificial Life and Robotics.

[8]  Sanjiv V. Bonde,et al.  A Fusion Based Visibility Enhancement of Single Underwater Hazy Image , 2018 .

[9]  Xiaoyan Wang,et al.  Three-Frame Difference Algorithm Research Based on Mathematical Morphology , 2012 .

[10]  Shubh Lakshmi Agrwal,et al.  Optimized dynamic background subtraction technique for moving object detection and tracking , 2017, 2017 2nd International Conference on Telecommunication and Networks (TEL-NET).

[11]  S. V. Bonde,et al.  Underwater image restoration using single color channel prior , 2016, 2016 International Conference on Signal and Information Processing (IConSIP).

[12]  Habib Mohammed Hussien,et al.  Detection and Tracking System of Moving Objects Based on MATLAB , 2014 .

[13]  S. R. Sulistiyanti,et al.  A moving objects detection in underwater video using subtraction of the background model , 2017, 2017 4th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI).

[14]  Joo Kooi Tan,et al.  Detecting moving objects from a video taken by a moving camera using sequential inference of background images , 2014, Artificial Life and Robotics.

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

[16]  Tuan Van Pham,et al.  Fish detection and movement tracking , 2015, 2015 International Conference on Advanced Technologies for Communications (ATC).

[17]  Ji-Sang Yoo,et al.  Object tracking using Kalman filter , 2009 .

[18]  Haiyong Zheng,et al.  Combining background subtraction and three-frame difference to detect moving object from underwater video , 2016, OCEANS 2016 - Shanghai.

[19]  Robert B. Fisher,et al.  Detecting, Tracking and Counting Fish in Low Quality Unconstrained Underwater Videos , 2008, VISAPP.

[20]  W. Eric L. Grimson,et al.  Learning Patterns of Activity Using Real-Time Tracking , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  Jaya S. Kulchandani,et al.  Moving object detection: Review of recent research trends , 2015, 2015 International Conference on Pervasive Computing (ICPC).

[22]  Ye Bo.  Algorithm of extracting moving object silhouette based on frame fusion under complex background , 2006 .