Plankton detection method under unbalanced population distribution condition

Abstract

The invention relates to the field of computer vision, adversarial learning and deep learning target detection, in particular to a multi-class plankton detection method under the condition of unbalanced plankton population distribution. According to the invention, on one hand, a cyclic adversarial neural network structure is integrated, and image sample data of a non-dominant distribution population is expanded, therefore, the sample data of various groups of images are balanced in quantity, the over-fitting phenomenon of the detection model in training is avoided, and the overall recognition precision is improved. And on the other hand, the algorithm introduces a DenseNet structure with a feature reuse characteristic on the basis of the YOLOV3 model to replace a down-sampling layer in the original YOLOV3 model, so that the feature loss of the fine features of the plankton in the transmission process of the deep neural network layer is reduced, and the stability of feature propagation is improved.

Description

technical field [0001] The invention relates to the fields of computer vision, adversarial learning and deep learning target detection, and specifically relates to a multi-type plankton detection method under the condition of unbalanced distribution of plankton populations. Background technique [0002] Plankton is the most basic component of the marine ecosystem. As producers and primary consumers, they provide food sources for organisms at the upper level of the food chain and play an important role in the global ocean carbon cycle. At the same time, plankton can respond rapidly to changes in the marine water environment (such as eutrophication or pollution), and are also considered indicators of marine water health. Therefore, a comprehensive understanding of the distribution and abundance of plankton in the marine environment is crucial for studying the marine carbon cycle and predicting the occurrence of natural disasters such as red tides. [0003] Different plankton ...

AI Technical Summary

Problems solved by technology

However, during the transfer process of the target feature in the deep neural network structure, due to operations such as downsampling and pooling, some features are often lost, which increases the difficulty of target recognition.

Images