System and method for recognizing ships under visible light on basis of convolutional neural network

Abstract

The invention relates to a system and method for recognizing ships under visible light on the basis of a convolutional neural network. The system comprises an image preprocessing module, an image augmentation module, a ship object detection model training module, a false alarm removal module, a ship classification model training module, a region zooming module and a ship classification model, wherein the image preprocessing module is used for removing interference information in images; the image augmentation module is used for augmenting a picture training set through carrying out cropping, segmentation and variable illumination on existing images; the ship object detection model training module is used for training a model for ship detection by using an object detection model framework;the false alarm removal module is used for removing recognized parts; the ship classification model training module is used for training an object detection model framework by using a data set; the region zooming module is used for randomly selecting a region for the images so as to enlarge the data set; and the ship classification model is used for classifying detected ships. At present, the system for recognizing ships under visible light on the basis of the convolutional neural network has precision higher than that of traditional ship recognition method in the field of ship recognition.

Description

technical field [0001] The invention relates to computer vision, machine learning, and image processing, and in particular to a ship recognition system and method based on a convolutional neural network under visible light conditions, so as to quickly and effectively locate and identify ships within a limited time. Background technique [0002] With the development of society and economy, maritime traffic is increasingly busy, and accidents are inevitable. Whether ships can be effectively identified has a great effect on economic development and maritime safety management and protection. Not only that, ship recognition technology also has military strategic significance in order to accurately track ship targets and achieve precise guidance. At present, there is still a lack of ship detection and recognition systems under visible light conditions. The more common ship recognition process is preprocessing + feature extraction + classifier. The main defect of this method is tha...

AI Technical Summary

Problems solved by technology

At present, there is still a lack of ship detection and recognition systems under visible light conditions. The more common ship recognition process is preprocessing + feature extraction + classifier. The main defect of this method is that it needs to use complex image processing algorithms, and the experimental results are not good too ideal

In addition, the continuous improvement of deep learning theory and technology has promoted the rapid development of deep learning ship recognition technology. However, the latest data shows that the recognition accuracy can only reach about 84%, and it is imminent to improve the ship recognition accuracy.

As an important branch of deep learning, the convolutional neural network (CNN) forms a more abstract high-level representation by combining low-level features, and has been successfully applied to recognition tasks such as handwritten character recognition, face recognition, and pedestrian detection. There are still many problems in the traditional ship identification process. The existing problems of traditional ship identification are: the area selection strategy based on the sliding window is not targeted; the time complexity is high, and the window is redundant; not very robust

The traditional manual counting method not only consumes manpower and material resources, but also has insufficient recognition accuracy and efficiency

Images