Fish trajectory tracking method and system based on artificial neural network

Abstract

The invention relates to a fish trajectory tracking method and system based on an artificial neural network. The method comprises the following steps of S1, acquiring a video or an image of a target fish; S2, obtaining a fish body image with a label as an initial training sample set, inputting the initial training sample set into a Unet convolutional neural network, and carrying out iterative training through a deep learning algorithm to obtain a fish body recognition neural network model; S3, recognizing a fish body in the acquired video or image of the target fish by utilizing a fish body recognition neural network model, segmenting a fish body form, and calculating the position of a preset point in the fish body; and S4, obtaining the motion trail of the target fish by using a target tracking algorithm, and analyzing the motion characteristics of the target fish. The method can accurately perform identification and trajectory tracking on the fish body, and thereby dependence of an experiment on an illumination condition is reduced, influence of mirror reflection and water surface fluctuation of the fish tank are overcome, high calculation efficiency is realized, the method can be applied to a long-time experiment video, and identification and trajectory tracking effects are improved.

Description

technical field [0001] The invention belongs to the technical field of fish trajectory tracking, and in particular relates to a fish trajectory tracking method and system based on an artificial neural network. Background technique [0002] Fish have swimming behaviors when feeding, migrating, and escaping from predators. Through the monitoring and analysis of fish swimming behaviors, it can well serve water quality monitoring, biomedicine, aquaculture, ecological protection, and engineering planning and construction. Cavefish broadly refers to freshwater fish living in underground caves, rivers and lakes in karst karst landforms. China is the country with the richest species of cavefish in the world. In recent years, in order to protect cavefish, laboratory research on cavefish will gradually increase. In laboratory cavefish behavior studies, tracking fish trajectories and behaviors can help analyze fish preferences for different water flow and water quality conditions, and...

AI Technical Summary

Problems solved by technology

[0006] Aiming at the technical problems of the current fish identification and trajectory tracking methods in the above-mentioned prior art that have relatively low computational efficiency, are difficult to apply to long-term experimental videos, and are difficult to improve the effect of identification and trajectory tracking, the present invention provides a Fish trajectory tracking method based on artificial neural network, U-net convolutional neural network learns through previous training, and builds a fish body recognition neural network model after passing the test, and infers according to the learned fish outline, color, posture and other characteristics The fish information in the video obtained by the experiment can accurately identify and track the fish body, thereby reducing the dependence of the experiment on lighting conditions and overcoming the influence of the mirror reflection of the fish tank and water surface fluctuations. The calculation efficiency is high and can be applied to long-term In the experimental video of time, the effect of recognition and trajectory tracking is improved

Images