Integrated sensing infrared imaging ship detection method integrated with local structure information

• Main Authors: YI HAIYANG, LIAN RUIYI, HAN YAQI, LU TIANSHU, PENG ZHENMING, LIAO JINGWEN, QIE RUOCHEN, ZHANG YIWEI
• Format: Patent
• Language: Chinese; English
• Published: 10.06.2022
• 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 discloses an integrated sensing infrared imaging ship detection method integrated with local structure information. The method mainly comprises the following steps: step 1, preparing infrared remote sensing ship data and carrying out preprocessing and data set division; step 2, inputting the training set image into an integrated sensing network for iterative training, wherein the working process of the network is as follows: extracting backbone features by using a bidirectional feature fusion network, extracting space attention by using a context attention network, generating a candidate box by using Mask-RPN, and performing final detection by using a detection head fused with local structure information; and step 3, inputting the test set image into the trained integrated sensing network to obtain a prediction frame position and a probability thereof, and obtaining a final detection result after removing a redundant frame through a non-maximum suppression operation. Local structure information