光遥感图像舰船目标在检测识别过程中会存在诸多干扰,导致无法精准识别出舰船目标,对此,研究光学遥感图像中舰船识别方法。首先,在光学遥感图像内提取舰船目标显著性区域,抑制云雾、海杂波与海域陆地等背景信息对舰船目标识别的影响,完成光学遥感图像舰船目标的粗识别。然后,基于提取到的光学遥感图像显著性区域,利用CNN网络对其进行舰船目标精识别。实验结果表明,设计方法可以有效提取光学遥感图像的舰船目标显著性区域,并提取显著性区域的舰船目标特征;舰船目标识别精度始终高于95%,具有实用性。
There are many interferences in the detection and recognition process of ship targets in optical remote sensing images, which make it difficult to accurately identify ship targets. Therefore, research is conducted on ship recognition methods in optical remote sensing images. Firstly, extract the salient regions of ship targets in optical remote sensing images, suppress the influence of background information such as clouds, sea clutter, and sea land on ship target recognition, and complete rough recognition of ship targets in optical remote sensing images. Then, based on the extracted salient regions of optical remote sensing images, a CNN network is used for precise recognition of ship targets. The experimental results show that the design method can effectively extract the salient regions of ship targets in optical remote sensing images, and extract the ship target features in the salient regions; The accuracy of ship target recognition is always above 95%, which is practical.
2024,46(16): 143-147 收稿日期:2024-02-12
DOI:10.3404/j.issn.1672-7649.2024.16.023
分类号:TP391
作者简介:丁梦磊(1990 – ),男,硕士,工程师,研究方向为水下发射
参考文献:
[1] 许德刚, 王再庆, 邢奎杰, 等. 改进YOLOv6的遥感图像目标检测算法[J]. 计算机工程与应用, 2024, 60(3): 119-128.
XU Degang, WANG Zaiqing, XING Kuijie, et al. Remote sensing image target detection algorithm based on improved YOLOv6[J]. Computer Engineering and Applications, 2024, 60(3): 119-128.
[2] 付宏建, 白宏阳, 郭宏伟, 等. 融合多注意力机制的光学遥感图像目标检测方法[J]. 光子学报, 2022, 51(12): 304-312.
FU Hongjian, BAI Hongyang, GUO Hongwei, et al. Object detection method of optical remote sensing image with multi-attention mechanism[J]. Acta Photonica Sinica, 2022, 51(12): 304-312.
[3] 成倩, 李佳, 杜娟. 基于YOLOv5的光学遥感图像舰船目标检测算法[J]. 系统工程与电子技术, 2023, 45(5): 1270-1276.
CHENG Qian, LI Jia, DU Juan. Ship target detection algorithm of optical remote sensing image based on YOLOv5[J]. Systems Engineering and Electronics, 2023, 45(5): 1270-1276.
[4] 王慧赢, 王春平, 付强, 等. 面向嵌入式平台的轻量级光学遥感图像舰船检测[J]. 光学学报, 2023, 43(12): 113-126.
WANG Huiying, WANG Chunping, FU Qiang, et al. Lightweight ship detection based on optical remote sensing images for embedded platform[J]. Acta Optica Sinica, 2023, 43(12): 113-126.
[5] BAILI N, MOALLA M, FRIGUI H, et al. Multistage approach for automatic target detection and recognition in infrared imagery using deep learning[J]. Journal of Applied Remote Sensing, 2022, 16(4): 048505.1-048505.18.
[6] CHERRI A K, NAZAR A S. Class-associative multiple target recognition for highly compressed color images in a joint transform correlator[J]. Optical Engineering, 2022, 61(12): 123102.1-123102.18.
[7] 殷赞, 王超杰, 程子恒, 等. 一种基于注意力机制卷积神经网络模型的自动调制识别算法[J]. 电波科学学报, 2023, 38(5): 773-779.
YIN Zan, WANG Chaojie, CHENG Ziheng, et al. An automatic modulation recognition algorithm based on convolutional neural networks with attention mechanism[J]. Chinese Journal of Radio Science, 2023, 38(5): 773-779.
[8] 廉小亲, 黄雪, 高超, 等. 基于Frost滤波和改进CNN的SAR图像TR方法[J]. 计算机仿真, 2023, 40(5): 49-55,233.
LIAN Xiaoqin, HUANG Xue, GAO Chao, et al. A method for recognizing SAR image target based on frost filter and improved convolutional neural network[J]. Computer Simulation, 2023, 40(5): 49-55+233.