Ship image target detection method based on deep learning

Abstract

The invention provides a ship target detection and recognition method based on deep learning, and the method comprises the following steps: S1, building a pixel attention model, and preprocessing a ship image; S2, generating a ship anchoring frame by using KMeans clustering, and converting a label boundary frame; S3, building a YOLOV3 network structure based on a pixel attention model; S4, training a network by using a training optimization method; and S5, performing post-processing on network output by using a non-maximum suppression algorithm to avoid the problem of repeated detection. According to the ship target detection and recognition method based on deep learning, ship target detection and recognition can be realized under various complex backgrounds and resolutions, and the ship target detection and recognition method has a good application prospect in the fields of ship industry, maritime affair management and the like.

Description

technical field [0001] The invention relates to a deep learning and target detection technology, in particular to a deep learning-based ship image target detection method, which belongs to the field of deep learning and computer vision. Background technique [0002] Ship target detection and recognition methods can be divided into three strategies, including end-to-end network structure, two-stage network structure and improved network structure based on the former two. For the end-to-end ship target detection and recognition network structure, Ling Ziqin, Chang Yang-Lang and Wang Bingde directly used YOLOV1, YOLOV2 and YOLOV3 networks to realize ship target detection and recognition, but the network effect could not meet the engineering use standard. Xia Ye and others built a ship target detection and recognition system using the SSD network, and achieved a certain improvement in the detection accuracy of the network, but sacrificed the real-time performance of the network....

AI Technical Summary

Problems solved by technology

In general, S-CNN can be regarded as an R-CNN optimized by a general method, which has a great improvement in the generation of candidate bounding boxes, but has no improvement in the target recognition of images inside the candidate bounding boxes.

Images