Article: Research on multi-view attitude measurement method for shipboard equipment with multiple feature points Journal: International Journal of Information and Communication Technology (IJICT) 2026 Vol.27 No.48 pp.48 - 62 Abstract: To achieve dynamic attitude monitoring of shipboard equipment and overcome the limited generality of traditional single-view methods, this paper proposes a multi-feature-point, multi-view attitude measurement approach. The method is designed as a redundant supplement to existing attitude measurement systems, providing additional attitude information under complex operating conditions. An improved MobileNet-v2 network incorporating squeeze-and-excitation modules is employed for feature point extraction from equipment images, achieving a detection accuracy of 95.4% on the test set. Based on multi-view observations and known equipment geometry, the three-dimensional coordinates of feature points in the camera coordinate system are reconstructed, and the equipment attitude is estimated by solving the rotation matrix between the camera and body coordinate systems using singular value decomposition. Experimental validation on a small-scale multirotor UAV platform demonstrates root mean square errors of 0.708° in pitch, 0.833° in roll, and 0.593° in heading, indicating good potential for attitude monitoring of large-scale ship equipment. Inderscience Publishers - linking academia, business and industry through research

Title: Research on multi-view attitude measurement method for shipboard equipment with multiple feature points

Authors: Yue Wang; Yaojin Wu; Guicai Fu; Yaqi Chang; Bingqi Liu

Addresses: School of Aerospace Engineering, North University of China, Taiyuan 030051, China ' School of Aerospace Engineering, North University of China, Taiyuan 030051, China ' School of Instrumentation and Optoelectronic Engineering, Beihang University, Beijing 100191, China ' School of Aerospace Engineering, North University of China, Taiyuan 030051, China ' College of Automation (College of Artificial Intelligence), Beijing Information Science and Technology University, Beijing 100192, China

Abstract: To achieve dynamic attitude monitoring of shipboard equipment and overcome the limited generality of traditional single-view methods, this paper proposes a multi-feature-point, multi-view attitude measurement approach. The method is designed as a redundant supplement to existing attitude measurement systems, providing additional attitude information under complex operating conditions. An improved MobileNet-v2 network incorporating squeeze-and-excitation modules is employed for feature point extraction from equipment images, achieving a detection accuracy of 95.4% on the test set. Based on multi-view observations and known equipment geometry, the three-dimensional coordinates of feature points in the camera coordinate system are reconstructed, and the equipment attitude is estimated by solving the rotation matrix between the camera and body coordinate systems using singular value decomposition. Experimental validation on a small-scale multirotor UAV platform demonstrates root mean square errors of 0.708° in pitch, 0.833° in roll, and 0.593° in heading, indicating good potential for attitude monitoring of large-scale ship equipment.

Keywords: shipboard drones; attitude measurement; MobileNet-v2; multi-view.

DOI: 10.1504/IJICT.2026.153549

International Journal of Information and Communication Technology, 2026 Vol.27 No.48, pp.48 - 62

Received: 04 Jan 2026
Accepted: 29 Jan 2026
Published online: 13 May 2026 *

Title: Research on multi-view attitude measurement method for shipboard equipment with multiple feature points

Keep up-to-date