Ship target detection method based on YOLOv4 algorithm

• Main Authors: XIONG JUXIA, JIA XUQIANG, ZHANG JIUWEN, WU JINZHAO, SU WEI, QU ZHIYI
• Format: Patent
• Language: Chinese; English
• Published: 08.10.2021
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS

The invention belongs to the technical field of ship detection, and particularly discloses a ship target detection method based on a YOLOv4 algorithm, and the method comprises the following steps: S1, building a ship target detection model based on the YOLOv4 algorithm; S2, acquiring a to-be-detected image of a ship target; and S3, inputting the ship target to-be-detected image into the ship target detection model to obtain a ship target detection result image. According to the method, the problems of difficulty in ship target extraction, low generalization ability of a detection model and limited detection precision in the prior art are solved. 本发明属于船舶检测技术领域，具体公开一种基于YOLOv4算法的船舶目标检测方法，包括如下步骤：S1：基于YOLOv4算法建立船舶目标检测模型；S2：获取船舶目标待检测图像；S3：将船舶目标待检测图像输入船舶目标检测模型，得到船舶目标检测结果图像。本发明解决了现有技术存在的提取船舶目标困难、检测模型泛化能力不强以及检测的精度有限的问题。