Automated Fish Detection And Identification
Loading...
Date
2015-10
Authors
Wong, Poh Lee
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Recognition and identification of fish using computational methods have increasingly become a popular research endeavour among researchers. The methods are important as the information displayed by the fish such as trajectory patterns, location and colour could determine whether the fish are healthy or under stress. Current methods are not accurate especially when there exist thresholds such as bubbles and some lighted spots which might be identified as fish. Besides, the recognition and identification rate of the existing systems can still be improved to obtain better and more accurate results. In order to achieve a better recognition and identification rate, an improved scheme consisting of a combination of several methods is constructed. First of all, the first approach is to propose an object tracking method for the purpose of locating the position of fish for real-time videos. This includes the consideration of tracking multiple fish in a single tank in an automated way. The detection and identification rate may be slow due to the on-going tracking process especially in a real-time environment. Real-time refers to the ability to perform the detection, recognition and identification process providing an output without significant delay. A more accurate fish tracking method is proposed as well as a systematic method to identify and detect fish swimming patterns. In this research, the particle filter algorithm is enhanced and further combined with the motion detection algorithm for fish tracking. A dual camera system is also proposed to obtain better detection rate. The second approach includes the design and development of an enhanced method for dynamically cropping and segmenting images in real-time environment. This method is proposed to extract each image of the fish from every successive video frame to reduce the tendency of detecting the background as an object. The third approach includes an adapted object characterisation method which utilises colour feature descriptors to represent the fish in a computational form for further processing. In this study, an object characterisation method, GCFD (Generalized Colour Fourier Descriptor) is adapted to suit the environment for more accurate identification of the fish. A feature matching method based on distance matching is used to match the feature vectors of the segmented images for classifying the specific fish in the recorded video. In addition, a real-time prototype system which models the fish swimming pattern incorporating all the proposed methods is developed to evaluate the methods proposed in this study. Based on the results, the proposed methods show improvements which result in a better real-time fish recognition and identification system. The proposed object tracking method shows improvement over the original particle filter method. Based on the average percentage in terms of the accuracy for the dynamic cropping and segmentation method in real time, an acceptable value of 84.71% was recorded. The object characterisation method which is adapted for fish recognition and identification in real time shows an improvement over existing colour feature descriptors. As a whole, the main output of this research could be used by aquaculturist to track and monitor fish in the water computationally in real-time instead of using the conventional way.
Description
Keywords
Electronic Computer