Microalgae identification method based on improved YOLOv3

Abstract

The invention provides a microalgae identification method based on improved YOLOv3, which comprises: collecting microalgae microscopic images, and making a data set of the microalgae images; performing data enhancement on the data set; dividing the enhanced data set into a training set, a verification set and a test set, labeling microalgae in the data set, and generating a labeled image; constructing an improved YOLOv3 target detection model; setting training parameters, and training the constructed YOLOv3 target detection model based on the data set; and classifying and positioning the test set images based on the trained YOLOv3 target detection model. According to the method, an improved YOLOv3 target detection model is adopted, a lightweight Mobilenet network is used for replacing an original feature extraction network darknet53 of YOLOv3, the operation speed can be remarkably increased, network parameters are greatly reduced, meanwhile, a spatial pyramid pool structure SPP is introduced, region features can be combined and connected in the same convolution layer with different scales, and the method is suitable for large-scale detection, so the position error is small when a small object is detected, and the CIoU is used for optimizing the loss function to further improve the detection precision.

Description

technical field [0001] The invention relates to the technical field of identification of microalgae species in marine and ship ballast water, in particular, to an improved YOLOv3-based identification method for microalgae. Background technique [0002] The ship's ballast water plays an important role in maintaining a safe and stable state during the voyage, but the ballast water discharged by ships on international voyages provides a channel for alien biological invasion. With the development of economic globalization, the volume of seaborne trade has grown rapidly, and the ecological invasion caused by ship ballast water has gradually emerged, which has attracted widespread attention in the fields of global environmental protection and shipping, and is recognized as one of the major threats to the global marine ecology and marine economy. . According to the International Council for the Exploration of the Sea (ICES), 94% of potentially harmful marine organisms are transmit...

AI Technical Summary

Problems solved by technology

The type and quantity of algae are key indicators in ballast water detection. The current conventional method is manual detection. The testing requires high skills and proficiency of the staff, and in the process of a large number of testing, the staff is prone to fatigue and lack of objectivity, which makes the test results unqualified and the error rate is high

Deep learning algorithms in the field of target detection are mainly divided into two-stage target detection algorithms and single-stage target detection algorithms. The two-stage target detection algorithm has the problem of consuming detection time; the single-stage target detection algorithm has a fast detection speed, but the recognition has similar characteristics. The accuracy rate of different targets with different features is low, especially in the current target detection field, most of which are used for detection on macroscopic objects, and are rarely used in microscopic fields. Therefore, it is necessary to consider whether the detection of microscopic objects will some new problems arise

Images