Fish growth evaluation method, device, equipment and storage medium

Abstract

The invention relates to a fish growth evaluation method, a device, equipment and a storage medium. The method comprises the steps: obtaining continuous N frames of fish images, and N is an integer greater than 1; respectively carrying out the following processing on every two continuous frames of fish images: extracting the features of fishes in the two continuous frames of fish images, recognizing the same fish in the two continuous frames of fish images, and distributing the same recognition to the same fish; according to the recognition of the fish in the N frames of fish images, obtaininga motion trail of the fish; and evaluating the growth trend of the fish according to the movement track of the fish. The method and the device are used for improving the accuracy of fish growth evaluation.

Description

technical field [0001] The present application relates to the field of aquaculture, in particular to a fish growth evaluation method, device, equipment and storage medium. Background technique [0002] According to the analysis of the aquatic product industry, the world's aquaculture is most developed in Asia, accounting for nearly 90% of the world's aquaculture. China is one of the major aquaculture countries in Asia and one of the countries with the longest history of aquaculture in the world. [0003] In order to create green, healthy and safe aquaculture, we need to observe the growth of fish. By observing the growth of fish, in order to deal with problems in time, so as to ensure the healthy growth of fish. Under normal circumstances, underwater cameras will continuously take images of fish schools, detect suitable fish through algorithms and obtain fish body size information, and then perform statistical analysis on the body size information of all images. This meth...

AI Technical Summary

Problems solved by technology

This method evaluates the growth of fish based on the information of the fish in a single image, and cannot fully estimate the growth trend of the fish. It is one-sided and the accuracy of the evaluation is poor.

[0004] In addition, there are also existing technologies in the prior art: the target is segmented by segmenting the image, and then tracked by the traditional algorithm, and the growth of the fish is evaluated according to the tracking result. The impact of external factors is relatively large, resulting in inaccurate assessment of fish

Furthermore, ignoring the continuity of timing and only relying on rules to match the same target in multiple frames of images, this operation is prone to errors and omissions, especially when the frame rate is low, the effect is very bad

Images