基于多域雷達(dá)回波數(shù)據(jù)融合的海面小目標(biāo)分類網(wǎng)絡(luò)模型

趙子健; 許述文; 水鵬朗

doi:10.11999/JEIT240818

基于多域雷達(dá)回波數(shù)據(jù)融合的海面小目標(biāo)分類網(wǎng)絡(luò)模型

doi: 10.11999/JEIT240818 cstr: 32379.14.JEIT240818

西安電子科技大學(xué)雷達(dá)信號(hào)處理全國(guó)重點(diǎn)實(shí)驗(yàn)室西安 710071

基金項(xiàng)目: 國(guó)家自然科學(xué)基金(62371382)

詳細(xì)信息

作者簡(jiǎn)介:
趙子?。耗?，博士生，研究方向?yàn)楹Ｃ嫘∧繕?biāo)識(shí)別、深度學(xué)習(xí)、機(jī)器學(xué)習(xí)、目標(biāo)檢測(cè)等

許述文：男，教授，研究方向?yàn)槔走_(dá)目標(biāo)檢測(cè)與識(shí)別、機(jī)器學(xué)習(xí)、時(shí)頻分析、SAR圖像處理等

水鵬朗：男，教授，研究方向?yàn)楹ｋs波建模、雷達(dá)目標(biāo)檢測(cè)與識(shí)別、圖像處理等

通訊作者:
水鵬朗　plshui@xidian.edu.cn

中圖分類號(hào): TN957.52
計(jì)量
- 文章訪問(wèn)數(shù): 412
- HTML全文瀏覽量: 136
- PDF下載量: 70
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2024-09-24
- 修回日期: 2025-02-21
- 網(wǎng)絡(luò)出版日期: 2025-03-06
- 刊出日期: 2025-03-01

A Network Model for Sea Surface Small Targets Classification Based on Multidomain Radar Echo Data Fusion

National Key Laboratory of Radar Signal Processing, Xidian University, Xi’an 710071, China

Funds: The National Natural Science Foundation of China (62371382)

摘要

摘要: 海面小目標(biāo)識(shí)別是海事雷達(dá)監(jiān)視任務(wù)中一個(gè)重要且具有挑戰(zhàn)性的問(wèn)題。由于海面小目標(biāo)類型多樣、環(huán)境復(fù)雜多變，對(duì)其進(jìn)行有效分類存在較大困難。在高分辨體制雷達(dá)下，海面小目標(biāo)通常只占據(jù)一或幾個(gè)距離單元，缺乏足夠的空間散射結(jié)構(gòu)信息，因此目標(biāo)的雷達(dá)截面積(RCS)起伏和徑向速度變化成為分類的主要依據(jù)。為此，該文提出一種基于多域雷達(dá)回波數(shù)據(jù)融合的分類網(wǎng)絡(luò)模型，用于海面小目標(biāo)的分類任務(wù)。由于不同域的數(shù)據(jù)具有其特殊的物理意義，因此該文構(gòu)建了時(shí)域LeNet(T-LeNet)神經(jīng)網(wǎng)絡(luò)模塊和時(shí)頻特征提取神經(jīng)網(wǎng)絡(luò)模塊，分別從雷達(dá)海面回波信號(hào)的幅度序列和時(shí)頻分布(TFD)即時(shí)頻圖中提取特征。其中幅度序列主要反映了目標(biāo)RCS的起伏特性，而時(shí)頻圖不僅反映RCS起伏特性，還能體現(xiàn)目標(biāo)徑向速度的變化。最后，利用IPIX, CSIR數(shù)據(jù)庫(kù)和自測(cè)的無(wú)人機(jī)數(shù)據(jù)集構(gòu)建了包括4種海面小目標(biāo)的數(shù)據(jù)集：錨定漂浮小球、漂浮船只、低空無(wú)人機(jī)(UAV)和移動(dòng)的快艇。實(shí)驗(yàn)結(jié)果表明所提方法具有良好的識(shí)別能力。
- 海面小目標(biāo) /
- 目標(biāo)分類 /
- 多特征融合 /
- 神經(jīng)網(wǎng)絡(luò)
Abstract: Objective Small target recognition on the sea surface is a critical and challenging task in maritime radar surveillance. The variety of small targets and the complexity of the sea surface environment make their classification difficult. Due to the small size of these targets, typically occupying only one or a few range cells under high-resolution radar systems, there is insufficient spatial scattering structure information for classification. The primary information for classification comes from the target’s Radar Cross Section (RCS) fluctuation and radial velocity change. This study proposes a classification network model based on multidomain radar echo data fusion, providing a theoretical foundation for small target recognition in complex sea surface environments. Methods A small marine target classification network model is proposed, based on multidomain radar echo data fusion, incorporating both time domain and time-frequency domain. Given that data from different domains hold distinct physical significance, a Time-domain LeNet (T-LeNet) neural network module and a time-frequency feature extraction neural network module are designed to extract features from the amplitude sequence and the Time-Frequency Distribution (TFD), respectively. The amplitude sequence primarily reflects the fluctuation characteristics of the target’s RCS, while the TFD captures both the RCS fluctuations and variations in the target’s radial velocity. By extracting deep information from small sea surface targets, effective differential features are obtained, leading to improved classification results. The advantages of the multidomain data fusion approach are validated through ablation experiments, where the amplitude sequence is fused with the input TFD, or the TFD is fused with the input amplitude sequence. Additionally, the effect of network depth on recognition performance is explored by using ResNet architectures with varying depths for time-frequency feature extraction. Results and Discussions A dataset containing four types of small sea surface targets is constructed using measured data to evaluate the effectiveness of the proposed method. Six evaluation metrics are used to assess the model’s classification ability. The experimental results show that when only the TFD is input, the best recognition performance is achieved by the ResNet18 network. This is due to ResNet18’s ability to prevent gradient vanishing and explosion through residual connections, enabling a deeper network capable of more effectively extracting differential features between targets. When only the amplitude sequence is input, the recognition performance of the T-LeNet network improves significantly compared to the performance with only the TFD input. Fusing the amplitude sequence with the T-LeNet network, based solely on the input of the TFD, leads to a notable increase in recognition performance. Thus, incorporating information from other domains, such as time-domain information (amplitude sequence), and extracting abstract features from one-dimensional data with T-LeNet, while also capturing deeper target features from multidomain and multidimensional aspects, significantly enhances the network’s recognition capability. The best recognition performance occurs when both the amplitude sequence and TFD are input using the ResNet18 network, achieving an accuracy of 97.21%, which represents a 21.1% improvement over the TFD-only input with the Vgg16 network (Table 3). The confusion matrix reveals that Class I and Class II targets are more accurately classified when using only the amplitude sequence, with average accuracy improvements of 5.5% and 85.1%, respectively, compared to the TFD-only input. Class IV targets are better classified when using only the TFD, with an average accuracy improvement of 5.5% compared to the amplitude sequence input. There is no significant difference in the accuracy of Class III targets (Fig. 5). Comparing the classification results of different ResNet networks shows that increasing the depth of the ResNet network does not significantly enhance recognition performance (Table 4). Analyzing the loss and accuracy of the various experiments in both the training and validation sets reveals that combining the T-LeNet network improves performance further. Specifically, the accuracy of AlexNet, Vgg16, and ResNet18 in the validation set improves by approximately 7.7%, 5.3% and 3.6%, respectively, while the loss in both the training and validation sets decreases (Fig. 6). Conclusions This paper proposes a small sea surface target classification method based on Convolutional Neural Networks (CNN) and data fusion. The method considers both the time domain and time-frequency domain, leveraging their distinct physical significance. It constructs the T-LeNet network module and the time-frequency feature extraction network module to extract deep information from small sea surface targets across multiple domains and dimensions. The abstract features jointly extracted from the time domain and time-frequency domain are fused for multidomain and multidimensional classification. The experimental results demonstrate that the proposed method exhibits strong recognition capability for small sea surface targets.
- Sea Surface Small target /
- Target classification /
- Multi-feature fusion /
- Neural network

HTML全文

圖 1 4種海面小目標(biāo)

下載: 全尺寸圖片幻燈片

圖 2 4類目標(biāo)的幅度序列和時(shí)頻圖示例

下載: 全尺寸圖片幻燈片

圖 3 目標(biāo)識(shí)別網(wǎng)絡(luò)流程圖

下載: 全尺寸圖片幻燈片

圖 4 網(wǎng)絡(luò)結(jié)構(gòu)

下載: 全尺寸圖片幻燈片

圖 5 混淆矩陣

下載: 全尺寸圖片幻燈片

圖 6 不同實(shí)驗(yàn)在訓(xùn)練集和驗(yàn)證集的損失與準(zhǔn)確率

下載: 全尺寸圖片幻燈片

表 1 4類目標(biāo)與其對(duì)應(yīng)的雷達(dá)參數(shù)

目標(biāo)類型	數(shù)據(jù)來(lái)源	距離分辨率(m)	重頻(kHz)	載頻(GHz)	極化方式	工作模式	波束寬度(°)	海況(級(jí))	訓(xùn)練樣本數(shù)	測(cè)試樣本數(shù)
錨定漂浮小球	IPIX93	30	1	9.39	HH/HV/VH/VV	駐留模式	0.9	2/3	21940	6560
漂浮船只	IPIX98	30	1	9.39	HH/HV/VH/VV	駐留模式	0.9	/	12768	3416
低空無(wú)人機(jī)	靈山島	3	4	10.00	HH/VV	駐留模式	1.1	2	7569	1 893
移動(dòng)的快艇	CSIR	15	2.5/5	6.90	VV	跟蹤模式	1.8	3	2920	964

下載: 導(dǎo)出CSV

表 2 混淆矩陣

		預(yù)測(cè)類別
		目標(biāo)1	目標(biāo)2	目標(biāo)3	目標(biāo)4
真實(shí)類別	目標(biāo)1	T₁P₁	F₁P₂	F₁P₃	F₁P₄
	目標(biāo)2	F₂P₁	T₂P₂	F₂P₃	F₂P₄
	目標(biāo)3	F₃P₁	F₃P₂	T₃P₃	F₃P₄
	目標(biāo)4	F₄P₁	F₄P₂	F₄P₃	T₄P₄

下載: 導(dǎo)出CSV

表 3 不同實(shí)驗(yàn)在6個(gè)評(píng)價(jià)指標(biāo)下的分類結(jié)果

	準(zhǔn)確率	誤差	精確度	召回率	F1-measure	Kappa
時(shí)頻圖+AlexNet	0.7773	0.2227	0.8139	0.7912	0.8024	0.6403
時(shí)頻圖+Vgg16^[5]	0.8022	0.1978	0.8461	0.8202	0.8330	0.6792
時(shí)頻圖+ResNet18	0.8145	0.1855	0.8487	0.8238	0.8361	0.7006
幅度序列+T-LeNet	0.9250	0.0750	0.9145	0.9130	0.9138	0.8823
幅度序列+時(shí)頻圖+T-LeNet+AlexNet	0.9426	0.0574	0.9440	0.9528	0.9484	0.9106
幅度序列+時(shí)頻圖+T-LeNet+Vgg16	0.9549	0.0451	0.9558	0.9578	0.9568	0.9296
幅度序列+時(shí)頻圖+T-LeNet+ResNet18	0.9721	0.0279	0.9708	0.9776	0.9742	0.9567

下載: 導(dǎo)出CSV

表 4 不同ResNet網(wǎng)絡(luò)在6個(gè)評(píng)價(jià)指標(biāo)下的分類結(jié)果

	準(zhǔn)確率	誤差	精確度	召回率	F1-measure	Kappa
時(shí)頻圖+ResNet18	0.8145	0.1855	0.8487	0.8238	0.8361	0.7006
時(shí)頻圖+ResNet34	0.8245	0.1755	0.8677	0.8379	0.8525	0.7165
時(shí)頻圖+ResNet50	0.8202	0.1798	0.8619	0.8359	0.8487	0.7100
幅度序列+時(shí)頻圖+T-LeNet+ResNet18	0.9721	0.0279	0.9708	0.9776	0.9742	0.9567
幅度序列+時(shí)頻圖+T-LeNet+ResNet34	0.9726	0.0274	0.9729	0.9775	0.9752	0.9574
幅度序列+時(shí)頻圖+T-LeNet+ResNet50	0.9736	0.0264	0.9707	0.9777	0.9742	0.9589

下載: 導(dǎo)出CSV

表 5 網(wǎng)絡(luò)的參數(shù)量、訓(xùn)練時(shí)間、測(cè)試時(shí)間和單個(gè)樣本測(cè)試時(shí)間

網(wǎng)絡(luò)	參數(shù)量(M)	訓(xùn)練時(shí)間(min)	測(cè)試時(shí)間(s)	單個(gè)樣本測(cè)試時(shí)間(ms)
T-LeNet	8.4669	7.25	23.87	1.86
AlexNet	61.1048	87.13	46.97	3.66
Vgg16	138.3651	216.15	55.05	4.29
ResNet18	11.1786	120.12	45.94	3.58
ResNet34	21.2867	195.19	72.65	5.66
ResNet50	23.5162	330.33	136.33	10.62
T-LeNet+AlexNet	71.7922	95.37	51.46	4.01
T-LeNet+Vgg16	149.0489	233.67	59.67	4.65
T-LeNet+ResNet18	21.7429	130.32	50.69	3.95
T-LeNet+ResNet34	31.8511	203.62	85.37	6.65
T-LeNet+ResNet50	34.4677	342.09	145.39	11.33

下載: 導(dǎo)出CSV

參考文獻(xiàn)(22)

[1]	ZHANG Tianwen, ZHANG Xiaoling, KE Xiao, et al. HOG-ShipCLSNet: A novel deep learning network with HOG feature fusion for SAR ship classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 5210322. doi: 10.1109/TGRS.2021.3082759.
[2]	關(guān)鍵. 雷達(dá)海上目標(biāo)特性綜述[J]. 雷達(dá)學(xué)報(bào), 2020, 9(4): 674–683. doi: 10.12000/JR20114. GUAN Jian. Summary of marine radar target characteristics[J]. Journal of Radars, 2020, 9(4): 674–683. doi: 10.12000/JR20114.
[3]	NI Jun, ZHANG Fan, YIN Qiang, et al. Random neighbor pixel-block-based deep recurrent learning for polarimetric SAR image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 59(9): 7557–7569. doi: 10.1109/TGRS.2020.3037209.
[4]	LEE S J, LEE M J, KIM K T, et al. Classification of ISAR images using variable cross-range resolutions[J]. IEEE Transactions on Aerospace and Electronic Systems, 2018, 54(5): 2291–2303. doi: 10.1109/TAES.2018.2814211.
[5]	XU Shuwen, RU Hongtao, LI Dongchen, et al. Marine radar small target classification based on block-whitened time-frequency spectrogram and pre-trained CNN[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 5101311. doi: 10.1109/TGRS.2023.3240693.
[6]	GUO Zixun and SHUI Penglang. Anomaly based sea-surface small target detection using K-nearest neighbor classification[J]. IEEE Transactions on Aerospace and Electronic Systems, 2020, 56(6): 4947–4964. doi: 10.1109/TAES.2020.3011868.
[7]	KUO B C, HO H H, LI C H, et al. A kernel-based feature selection method for SVM with RBF kernel for hyperspectral image classification[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014, 7(1): 317–326. doi: 10.1109/JSTARS.2013.2262926.
[8]	YIN Qiang, CHENG Jianda, ZHANG Fan, et al. Interpretable POLSAR image classification based on adaptive-dimension feature space decision tree[J]. IEEE Access, 2020, 8: 173826–173837. doi: 10.1109/ACCESS.2020.3023134.
[9]	JIA Qingwei, DENG Tingquan, WANG Yan, et al. Discriminative label correlation based robust structure learning for multi-label feature selection[J]. Pattern Recognition, 2024, 154: 110583. doi: 10.1016/j.patcog.2024.110583.
[10]	ZHONG Jingyu, SHANG Ronghua, ZHAO Feng, et al. Negative label and noise information guided disambiguation for partial multi-label learning[J]. IEEE Transactions on Multimedia, 2024, 26: 9920–9935. doi: 10.1109/TMM.2024.3402534.
[11]	ZHAO Jie, LING Yun, HUANG Faliang, et al. Incremental feature selection for dynamic incomplete data using sub-tolerance relations[J]. Pattern Recognition, 2024, 148: 110125. doi: 10.1016/j.patcog.2023.110125.
[12]	ZOU Yizhang, HU Xuegang, and LI Peipei. Gradient-based multi-label feature selection considering three-way variable interaction[J]. Pattern Recognition, 2024, 145: 109900. doi: 10.1016/j.patcog.2023.109900.
[13]	SUN Xu, GAO Junyu, and YUAN Yuan. Alignment and fusion using distinct sensor data for multimodal aerial scene classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 5626811. doi: 10.1109/TGRS.2024.3406697.
[14]	WU Xin, HONG Danfeng, and CHANUSSOT J. Convolutional neural networks for multimodal remote sensing data classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 5517010. doi: 10.1109/TGRS.2021.3124913.
[15]	DUAN Guoxing, WANG Yunhua, ZHANG Yanmin, et al. A network model for detecting marine floating weak targets based on multimodal data fusion of radar echoes[J]. Sensors, 2022, 22(23): 9163. doi: 10.3390/s22239163.
[16]	Cognitive Systems Laboratory. The IPIX radar database[EB/OL]. http://soma.ece.mcmaster.ca/ipix, 2001.
[17]	The Defense, Peace, Safety, and Security Unit of the Council for Scientific and Industrial Research. The Fynmeet radar database[EB/OL]. http://www.csir.co.ca/small_boat_detection, 2007.
[18]	RICHARD C. Time-frequency-based detection using discrete-time discrete-frequency Wigner distributions[J]. IEEE Transactions on Signal Processing, 2002, 50(9): 2170–2176. doi: 10.1109/TSP.2002.801927.
[19]	HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, USA, 2016: 770–778. doi: 10.1109/CVPR.2016.90.
[20]	KAYED M, ANTER A, and MOHAMED H. Classification of garments from fashion MNIST dataset using CNN LeNet-5 architecture[C]. 2020 International Conference on Innovative Trends in Communication and Computer Engineering (ITCE), Aswan, Egypt, 2020: 238–243. doi: 10.1109/ITCE48509.2020.9047776.
[21]	KRIZHEVSKY A, SUTSKEVER I, and HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84–90. doi: 10.1145/3065386.
[22]	SIMONYAN K and ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[C]. The 3rd International Conference on Learning Representations, San Diego, USA, 2015.