Ship identity recognition method and system based on deep learning

• Main Authors: ZENG QINGCHAO, GUO HAO, YANG XUAN, CHEN JINGYU, YAN YINGSU, LI YANZE, DONG JINBAO
• Format: Patent
• Language: Chinese; English
• Published: 10.08.2021
• 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 relates to a ship identity recognition method and system based on deep learning, computer equipment and a computer readable storage medium. The method comprises the following steps: acquiring a ship image; carrying out target detection based on a deep learning network to detect the ship types, positions and ship plate positions in the ship images; carrying out character recognition based on a deep learning network to extract all character positions and contents in the ship image; according to the ship sign position and the character position, filtering character content of a non-ship sign to obtain real ship sign character content; and analyzing the identity of the ship based on the ship category and the ship sign character content. The method is not depend on the AIS to carry out ship identity recognition, is high in precision and good in real-time performance, and can effectively solve the problem that evidence collection of ships without AIS equipment is difficult. 本发明涉及一种基于深度学习的船舶身份识别方法及系统、计