复杂场景伪装小目标机载偏振遥感检测方法

沈英; 张硕; 王舒; 苏云; 薛芳; 黄峰

doi:10.12382/bgxb.2024.0797

您当前的位置：

首页 >

文章列表页 >

复杂场景伪装小目标机载偏振遥感检测方法

更新时间：2025-09-05

- 复杂场景伪装小目标机载偏振遥感检测方法
- A Method for Detecting the Camouflaged Small Target in Complex Scene Using Airborne Polarization Remote Sensing
- 兵工学报 2025年46卷第7期页码：240797
- 作者机构：
  
  1. 福州大学机械工程及自动化学院, 福建福州 350108
  2. 北京空间机电研究所, 北京 100094
- 作者简介：
  
  *huangf@fzu.edu.cn
- 基金信息：
  
  国家自然科学基金项目(62005049);福建省自然科学基金项目(2020J01451);福建省教育厅中青年教师教育科研项目(JAT190003)
- DOI：10.12382/bgxb.2024.0797
  中图分类号：
- 收稿：2024-09-04，
  
  网络首发：2025-08-12，
  
  纸质出版：2025-07-31
- 稿件说明：
移动端阅览
沈英, 张硕, 王舒, 等. 复杂场景伪装小目标机载偏振遥感检测方法[J]. 兵工学报, 2025,46(7):240797.

Ying SHEN, Shuo ZHANG, Shu WANG, et al. A Method for Detecting the Camouflaged Small Target in Complex Scene Using Airborne Polarization Remote Sensing[J]. Acta Armamentarii, 2025, 46(7): 240797.
沈英, 张硕, 王舒, 等. 复杂场景伪装小目标机载偏振遥感检测方法[J]. 兵工学报, 2025,46(7):240797. DOI： 10.12382/bgxb.2024.0797.

Ying SHEN, Shuo ZHANG, Shu WANG, et al. A Method for Detecting the Camouflaged Small Target in Complex Scene Using Airborne Polarization Remote Sensing[J]. Acta Armamentarii, 2025, 46(7): 240797. DOI： 10.12382/bgxb.2024.0797.

摘要

无人机遥感探测在军事侦察领域发挥着重要作用

偏振探测利用偏振光与物体相互作用产生的偏振变化来提高目标对比度。然而在复杂场景下

伪装小目标与背景特征差异较小且空间信息不足

存在检测困难的问题。为此提出一种偏振伪装小目标检测算法(Polarization Camouflaged Small Object Detection-YOLO

PCSOD-YOLO)

设计了高效层注意力模块-坐标注意力特征提取模块和空间金字塔池化跨阶段局部通道-3D权重注意力感受野模块

捕获目标的偏振特征和语义信息

增强上下文信息理解能力;设计了动态小目标检测头

通过动态卷积增强对小目标特征提取能力的同时

利用不同尺度的特征信息

联合多通道特征信息输出小目标检测结果。构建伪装小目标偏振图像数据集(Polarization Image of Camouflaged Small Objects

PICSO)。在PICSO数据集上的实验表明

所提出的方法可以有效检测伪装小目标

mAP

0.5

达到92.4%

mAP

0.5:0.95

达到47.8%

检测速率达到60.6帧/s

满足实时性要求。

Abstract

Unmanned aerial vehicle (UAV) remote sensing detection plays an important role in military reconnaissance

and the polarization detection is to utilize the polarization changes generated by the interaction between polarized light and target to improve the target contrast.However

in complex scenes

the small targets are less distinguishable from the background due to their similar features and the insufficient spatial information

resulting in difficulties in detection.To this end

a polarization camouflaged small object detection (PCSOD)-YOLO algorithm is proposed

and an efficient layer attention module-coordinated attention (ELAM-CA) and a spatial pyramid pooling cross stage partial channel-3D weights attention (SPPCSPC-3DWA) module are designed to capture the polarization features and semantic information of target

enhancing the ability to understand the contextual information.A dynamic small target detection head is designed to enhance the ability to extract the features of small targets through dynamic convolution

and the detected results of small target are outputted using the feature information from different scales and the multi-channel feature information.A polarization image of camouflaged small objects (PICSO) dataset is construc

ted for the camouflaged small target polarization images.Experiments on the PICSO dataset show that the proposed method can effectively detect the camouflaged small targets

with

mAP

0.5

and

mAP

0.5:0.95

reaching 92.4% and 47.8%

respectively.The detection rate reaches 60.6 frames per second

meeting the real-time requirements.

关键词

Keywords

references

ZHANG Z , ZHU L . A review on unmanned aerial vehicle remote sensing:platforms,sensors,data processing methods,and applications [J ] . Drones , 2023 , 7 ( 6 ): 398 .

ZHOU X F , WU Z C , CONG R M . Decoupling and integration network for camouflaged object detection [J ] . IEEE Transactions on Multimedia , 2024 ,26: 7114 - 7129 .

ZHANG Y Z , WU C Y , ZHANG T , et al. Full-scale feature aggregation and grouping feature reconstruction based UAV image target detection [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2024 ,62:5621411.

ZHU Z , LI X B , ZHAI J S , et al. PODB:a learning-based polarimetric object detection benchmark for road scenes in adverse weather conditions [J ] . Information Fusion , 2024 ,108:102385.

ZHU Z Q , ZHENG R Z , QI G Q , et al. Small object detection method based on global multi-level perception and dynamic region aggregation [J ] . IEEE Transactions on Circuits and Systems for Video Technology ,2024:1.

WANG X , WANG A R , YI J L , et al. Small object detection based on deep learning for remote sensing:a comprehensive review [J ] . Remote Sensing , 2023 , 15 ( 13 ): 3265 .

CHAN S X , YU M M , CHEN Z M , et al. Regional contextual information modeling for small object detection on highways [J ] . IEEE Transactions on Instrumentation and Measurement , 2023 ,72:2531613.

CUI L S , LÜ P , JIANG X H , et al. Context-aware block net for small object detection [J ] . IEEE Transactions on Cybernetics , 2020 , 52 ( 4 ): 2300 - 2313 .

JIANG Q Y , DAI J Y , RUI T , et al. Context-based oriented object detector for small objects in remote sensing imagery [J ] . IEEE Access , 2022 ,10: 100526 - 100539 .

胡焱 , 原子昊 , 涂晓光 , 等 . 基于对比学习的改进SSD目标检测算法 [J ] . 红外技术 , 2024 , 46 ( 5 ): 548 - 555 .

HU Y , YUAN Z H , TU X G , et al. Improved SSD object detection algorithm based on contrastive learning [J ] . Infrared Technology , 2024 , 46 ( 5 ): 548 - 555 . (in Chinese)

SHI T J , GONG J N , HU J M , et al. Adaptive feature fusion with attention-guided small target detection in remote sensing images [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2023 ,61:5623116.

WANG X T , LU R T , BI H X , et al. An infrared small target detection method based on attention mechanism [J ] . Sensors , 2023 , 23 ( 20 ): 8608 .

QU J S , TANG Z B , ZHANG L , et al. Remote sensing small object detection network based on attention mechanism and multi-scale feature fusion [J ] . Remote Sensing , 2023 , 15 ( 11 ): 2728 .

肖振久 , 张杰浩 , 林渤翰 . 特征协同与细粒度感知的遥感图像小目标检测 [J ] . 光电工程 , 2024 , 51 ( 6 ): 52 - 65 .

XIAO Z J , ZHANG J H , LIN B H . Feature coordination and fine-grained perception of small targets in remote sensing images [J ] . Opto-Electron Engineering , 2024 , 51 ( 6 ): 52 - 65 . (in Chinese)

ZHANG H Y , LI M , MIAO D Q , et al. Construction of a feature enhancement network for small object detection [J ] . Pattern Recognition , 2023 ,143:109801.

ZHANG Q , REN J , LIANG H , et al. BFE-net:bidirectional multi-scale feature enhancement for small object detection [J ] . Applied Sciences , 2022 , 12 ( 7 ): 3587 .

郭永红 , 牛海涛 , 史超 , 等 . 基于卷积和注意力机制的小样本目标检测 [J ] . 兵工学报 , 2023 , 44 ( 11 ): 3508 - 3515 . DOI: 10.12382/bgxb.2022.1167 http://doi.org/10.12382/bgxb.2022.1167 小样本目标检测(FSOD)旨在使检测器只用少量的训练样本就能适应未见的类别。典型的FSOD方法使用Faster R-CNN作为基本检测框架,利用卷积神经网络提取图像特征,而卷积神经网络中采用的旨在捕获尽可能多的图像信息的池化操作将不可避免地导致图像信息的丢失。在主干网络中引入混合扩张卷积,以确保更大的感受野并最大限度地减少图像信息的损失。在k-shot设置中,为充分利用给定的支持数据,提出支持特征动态融合模块,以每个支持特征和查询特征之间的相关性为权重,自适应地融合支持特征,以获得更强大的支持线索。实验结果表明,新方法在公共Pascal VOC和MS-COCO数据集上实现了较好的FSOD性能。

GUO Y H , NIU H T , SHI C , et al. Few-shot object detection based on convolution network and attention mechanism [J ] . Acta Armamentarii . 2023 , 44 ( 11 ): 3508 - 3515 . (in Chinese) DOI: 10.12382/bgxb.2022.1167 http://doi.org/10.12382/bgxb.2022.1167 Few-shot object detection(FSOD) aims to enable the detector with a small number of training samples. Typical FSOD method takes Faster R-CNN as the basic detection framework, and uses a convolutional neural network to extract the image features. However, the pooling operation used in the convolutional neural network inevitably leads to the loss of image information. Therefore, a hybrid dilated convolution is introduced into the backbone network to ensure a larger receptive field and minimize the loss of image information. A support feature dynamic fusion module is proposed to further utilize the given support data in k -shot setting, which adaptively fuses the support features with the weight of the correlation between each support feature and query feature to obtain stronger support clues. Experimental results show that rhe proposed method achieves good and state-of-the-art FSOD performance on public Pascal VOC and MS-COCO datasets.

ZHANG Y , YE M , ZHU G Y , et al. FFCA-YOLO for small object detection in remote sensing images [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2024 ,62:5611215.

TANG F Z , GUI L Q , LIU J B , et al. Metal target detection method using passive millimeter-wave polarimetric imagery [J ] . Optics Express , 2020 , 28 ( 9 ): 13336 - 13351 . DOI: 10.1364/OE.390385 http://doi.org/10.1364/OE.390385 Polarization-based passive millimeter-wave imaging has been applied in several applications, including material clustering, pattern recognition, and target detection. We present here a general formulation of a metal target detection method called dual linear polarization discriminator (DLPD), utilizing passive millimeter-wave polarimetric imagery. Several potential discriminators are defined, and linear polarization difference ratio (LPDR) is selected and proposed to be a new feature discriminator that is sensitive to material composition and able to reduce ambient radiation effects when detecting target with different material and shape. Furthermore, the detection criterion is verified utilizing the threshold values determined by a statistical analysis of LPDR. Outdoor experiments demonstrate that the proposed detection method is highly effective for detecting a metal target in a complex background.

LIU J Y , LI S T , DIAN R W , et al. DT-F transformer:dual transpose fusion transformer for polarization image fusion [J ] . Information Fusion , 2024 ,106:102274.

沈英 , 刘贤财 , 王舒 , 等 . 基于偏振编码图像的低空伪装目标实时检测 [J ] . 兵工学报 , 2024 , 45 ( 5 ): 1374 - 1383 . DOI: 10.12382/bgxb.2022.1289 http://doi.org/10.12382/bgxb.2022.1289 偏振可以提高无人机的自主侦察能力,但易受到探测角度和目标材质的影响,从而降低偏振检测的鲁棒性。为此,提出一种基于偏振图像的低空伪装目标实时检测算法YOLO-P,采用融合多偏振方向信息的编码图像作为输入,应用三维卷积模块提取不同偏振方向图像之间的联系特征;引入特征增强模块对多层次特征进行进一步增强;采用跨层级特征聚合网络,充分利用不同尺度的特征信息,完成特征的有效聚合,最终联合多通道特征信息输出检测结果。构建包含10类目标的低空伪装目标偏振图像数据集PICO(Polarization Image of Camouflaged Objects)。在PICO数据集上的实验结果表明,新方法可以有效检测伪装目标,mAP<sub>0.5:0.95</sub>达到52.0%,mAP<sub>0.5</sub>达到91.5%,检测速率达到55.0帧/s,满足实时性要求。

SHEN Y , LIU X C , WANG S , et al. Real-time detection of low-altitude camouflage targets based on polarization coded images [J ] . Acta Armamentarii , 2024 , 45 ( 5 ): 1374 - 1383 . (in Chinese) DOI: 10.12382/bgxb.2022.1289 http://doi.org/10.12382/bgxb.2022.1289 Polarization can improve the autonomous reconnaissance capability of unmanned aerial vehicle, but it is easily interfered by the variation of detection angle and target materials, which affects the robustness of polarization detection. In this paper, a real-time low-altitude camouflaged target detection algorithm of YOLO-Polarization based on polarized images is proposed. The coded image fused with multi-polarization direction information is used as input, the 3D convolution module is applied to extract the connection features from the different polarization direction images, and a feature enhancement module (FEM) is introduced to further enhance the multi-level features. In addition, the cross-level feature aggregation network is adopted to make full use of the feature information of different scales to complete the effective aggregation of features, and finally combined with multi-channel feature information output detection results. A dataset consisting of polarized images of low-altitude camouflaged targets (PICO) which include 10 types of targets is constructed. The experimental results based on PICO dataset show that the proposed method can effectively detect the camouflaged targets, with mAP 0.5:0.95 up to 52.0% and mAP 0.5 up to 91.5%. The detection rate achieves 55.0 frames/s, which meets the requirement of real-time detection.

WANG C Y , BOCHKOVSKIY A , LIAO H Y M . YOLOv7:trainable bag-of-freebies sets new state-of-the-art for real-time object detectors [C ] //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington,D.C. , US:IEEE ,2023: 7464 - 7475 .

HOU Q B , ZHOU D Q , FENG J S . Coordinate attention for efficient mobile network design [C ] //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington,D.C. , US:IEEE ,2021: 13708 - 13717 .

ZHOU Q , SHI H M , XIANG W K , et al. DPNet:dual-path network for real-time object detection with lightweight attention [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2024 , 36 ( 3 ): 1 - 15 .

YANG L X , ZHANG R Y , LI L D , et al. Simam : a simple , parameter-free attention module for convolutional neural networks [C ] //Proceedings of International Conference on Machine Learning.PMLR , 2021 ,139: 11863 - 11874 .

LI C , ZHOU A , YAO A . Omni-dimensional dynamic convolution:arXiv:2209. 07947 [R ] . Ithaca,NY , US : Cornell Universit , 2022:2209 . 07947 .

LIN T Y , MAIRE M , BELONGIE S , et al. Microsoft coco:common objects in context [C ] //Proceedings of the 13rd European Conference on Computer Vision.Zurich,Switzerland , 2014 ,8693: 740 - 755 .

惠康华 , 杨卫 , 刘浩翰 , 等 . 基于YOLOv5的增强多尺度目标检测方法 [J ] . 兵工学报 , 2023 , 44 ( 9 ): 2600 - 2610 . DOI: 10.12382/bgxb.2022.1147 http://doi.org/10.12382/bgxb.2022.1147 针对复杂场景下初始锚框难以匹配目标及多尺度检测能力不强的问题,提出一种基于YOLOv5的增强多尺度目标检测(EM-YOLOv5)方法。通过Kmeans++聚类算法,获得适应当前检测场景下的多尺度初始化锚框,使得网络更容易捕捉到不同尺度目标;在Bottleneck结构中增加多条不同尺度的并行卷积支路,在保留原有特征信息的同时融合多尺度的特征信息,增强模型的全局感知能力。在VisDrone2019、COCO2017和PASCAL VOC2012数据集上对提出的EM-YOLOv5s模型进行测试。实验结果表明,与YOLOv5s模型相比,mAP@0.5∶0.95、mAP@0.5等关键指标均有一定提升,在PASCAL VOC2012上,mAP@0.5∶0.95提升5.2%,而检测时间仅增加1.9ms,说明EM-YOLOv5模型能够有效地提升通用复杂场景下的目标检测精度。

HUI K H , YANG W , LIU H H , et al. An enhanced multi-scale target detection method based on YOLOv5. [J ] . Acta Aarmamentarii , 2023 , 44 ( 9 ): 2600 - 2610 . (in Chinese)

TIAN Z , SHEN C H , CHEN H , et al. FCOS:a simple and strong anchor-free object detector [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2020 , 44 ( 4 ): 1922 - 1933 .

GE Z , LIU S T , WANG F , et al. YOLOX:exceeding yolo series in 2021:arXiv:2107.08430 [R ] . Ithaca,NY , US : Cornell Universit , 2021:2107 . 08430 .

ZOU C , JEON W S , RHEE S Y . Research on the multiple small target detection methodology in remote sensing [J ] . Sensors , 2024 , 24 ( 10 ): 3211 .

DONG Y , YANG H T , LIU S L , et al. Optical remote sensing object detection based on background separation and small object compensation strategy [J ] . IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing ,2024: 1 - 11 .

浏览量

2486

下载量

CNKI被引量

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于偏振编码图像的低空伪装目标实时检测

面向无人机航拍小目标的跨层动态检测网络

面向空基侦察平台的轻量化多通道军事小目标检测算法

基于代理模型的人体钝击响应特征快速预测方法

视场约束下无人机动态降落图像视觉伺服控制