|
|
|
| Multi-Modal Warship Image Generation and Its Key Part Detection |
| WANG Yili1， LI Qiang1， SHEN Junyi2， YANG Yidong2， WANG Qi1 |
| 1. School of Artificial Intelligence， Optics and Electronics， Northwestern Polytechnical University， Xi'an 710072， Shaanxi， China； 2. Shanghai Electro-Mechanical Engineering Institute， Shanghai 201109， China |
|
|
|
|
Abstract Visible images, synthetic aperture radar（SAR） images, and infrared images have distinct advantages, including high resolution, robust resistance to environmental interference, and clear visualisation of thermal objects, respectively. Utilising the combination of these three modalities, the key components of a warship can be accurately detected under all-day and all-weather conditions. However, existing publicly available warship datasets only consist of single-modality images. Thus, there is a lack of datasets that allow three modalities to be aligned in both time and space. To resolve this issue, this paper proposed a method for constructing a multi-modal warship image dataset through a virtual engine and multi-modal data generation model. The dataset comprised 5 055 images, with 1 685 visible images, 1 685 infrared images, and 1 685 SAR images, each with a resolution of 640×640 pixels. To allow accurate detection of the key components of a warship, this paper introduced a method via adaptive region localisation. Specifically, the reconstructed three modal images were utilised as input data. A multi-scale feature extraction neck module was employed to acquire features by exploring the information complementary of multiple modalities at different scales. To better locate the region of the objects, a regional adaptive localisation module was designed. Finally, the key parts of the warship were detected accurately. Experimental results on the constructed multi-modal warship image dataset demonstrate that the proposed method can increase detection accuracy. When compared to the benchmark model, the proposed method improves the mean average precision by 5.52% when the IoU threshold is 0.5.
|
|
Received: 20 January 2024
Published: 22 March 2025
|
|
|
|
|
|
| [1] |
LI Chuchen, TANG Shanjun, ZHAO Bingqing. Weak Object Detection Algorithm Based on High Resolution Remote Sensing Image of UAV Platform[J]. Air & Space Defense, 2025, 8(1): 41-47. |
| [2] |
LYU Tao, CHEN Jing, XUE Shanye. Joint Analysis of Product Indicators Based on Multi-Source and Multi-Modal Data in Discrete Manufacturing[J]. Air & Space Defense, 2024, 7(5): 110-119. |
| [3] |
LIU Jing, GUO Xiaolei, ZHANG Xinhai, MAO Jingjun, LYU Ruiheng. A Lightweight Aerial Rotated Object Detection Algorithm of Air-to-Surface Missile[J]. Air & Space Defense, 2024, 7(4): 106-113. |
| [4] |
ZHANG Xiaoyu, DU Xiangrun, ZHANG Jialiang, TAN Panlong, YANG Shibo. Research on Infrared Image Object Detection Method Based on Deformable DETR[J]. Air & Space Defense, 2024, 7(1): 16-23. |
| [5] |
WEI Zhifei, SONG Quanhong, LI Fang, YANG Qingyu, WANG Aihua. Research on Object Detection Algorithm Based on Neural Network Model Compression Technique[J]. Air & Space Defense, 2021, 4(4): 107-112. |
| [6] |
QIU Zhongyu, ZHAO Wenlong, GAO Wen, PAN Hongtao, SHI Randong. Comparison and Analysis of Object Detection Algorithm Based on Dynamic Vision Sensor[J]. Air & Space Defense, 2021, 4(4): 101-106. |
| [7] |
QI Shengyong, ZANG Yuejin, LYU Guoyun, DU Ming. Research on Air Target Image Generation Algorithm Based on Generative Adversarial Networks[J]. Air & Space Defense, 2021, 4(2): 67-73. |
| [8] |
JIANG Xinghao, ZHAO Zheyu, XU Ke . Adversarial Attack Technology for Vision-Based Aircraft Intelligent Object Detection[J]. Air & Space Defense, 2021, 4(1): 8-13. |
|
|
|
|
2025, Vol. 8 
