一种干扰环境下线阵复合成像引信目标识别算法

doi:10.12382/bgxb.2024.0708

摘要/Abstract

摘要：

为解决激光成像引信在烟雾、扬尘和伪装干扰下目标识别性能差的问题,提出一种线阵激光/线阵近红外复合成像目标识别算法。根据成像模型确立标定矩阵,得到激光点云与近红外图像的空间映射关系。构建了基于深度学习的目标识别算法框架,在数据输入层提出了一种体素融合模块,通过编码近红外像素级特征以增强点云,在中间层提出了一种鸟瞰图视角融合模块实现特征级融合,自适应动态调节双模态特征权重。基于自建的仿真数据集对算法进行验证,实验结果表明所提出的算法能够显著提高烟雾、扬尘和伪装干扰下的目标识别精度。

关键词: 复合成像引信, 目标识别, 激光点云, 近红外图像, 融合算法

Abstract:

In order to address the issue of the poor target recognition performance of laser imaging fuze under smoke,dust,and camouflage interference,a target recognition algorithm using linear array laser and linear array near-infrared compound imaging is proposed.A calibration matrix is established according to the imaging model,and the spatial mapping relationship between the laser point cloud and the near-infrared image is obtained.A deep learning-based target recognition algorithmic framework is constructed,and a voxel fusion module is proposed at the data input layer to enhance the point cloud by encoding near-infrared pixel-level features.A BEV fusion module is proposed at the middle layer to achieve feature-level fusion with adaptive dynamic adjustment of bimodal feature weights.The proposed algorithm is validated based on a custom simulation dataset.The experimental results show that the proposed algorithm can significantly improve the accuracy of target recognition under smoke,dust and camouflage interference.

Key words: compound imaging fuze, target recognition, laser point cloud, near-infrared image, fusion algorithm

高铭泽, 徐立新, 施小龙, 王伟翰, 王凤杰, 胡诗苑, 吴沿江, 陈慧敏. 一种干扰环境下线阵复合成像引信目标识别算法[J]. 兵工学报, 2025, 46(7): 240708-.

GAO Mingze, XU Lixin, SHI Xiaolong, WANG Weihan, WANG Fengjie, HU Shiyuan, WU Yanjiang, CHEN Huimin. A Target Recognition Algorithm for Linear Array Compound Imaging Fuze under Jamming Conditions[J]. Acta Armamentarii, 2025, 46(7): 240708-.

图/表 10

图1 复合成像与坐标系转换示意图

Fig.1 Schematic diagram of composite imaging and coordinate system conversion

图2 激光/近红外融合3D目标识别算法框架

Fig.2 3D target detection algorithmic framework using laser and near-infrared fusion

图3 体素融合模块

Fig.3 Voxel fusion module

图4 激光点云分支网络架构

Fig.4 Laser point cloud branch network architecture.

图5 近红外图像分支网络架构

Fig.5 Near-infrared image branch network architecture.

图6 BEV融合模块

Fig.6 BEV fusion module

图7 数据集部分数据样本可视化

Fig.7 Visualization of partial samples of the dataset

表1 对比实验结果

Table 1 Comparative experimental results

算法	模态	Δ	mAP	坦克AP@0.7			卡车AP@0.7			汽车AP@0.7
算法	模态	Δ	mAP	烟雾	扬尘	伪装	烟雾	扬尘	伪装	烟雾	扬尘	伪装
SECOND^[22]	L	-	33.85	64.20	70.38	68.97	29.45	21.41	34.97	5.39	8.67	1.20
PointPillar^[21]	L	+0.32	34.17	63.40	71.40	72.38	29.46	25.65	34.01	3.94	6.58	0.67
CLOCs^[17]	L+C	+4.11	38.28	79.41	80.50	78.99	35.50	18.18	35.93	8.08	3.47	4.44
MVX-Net^[12]	L+C	+48.21	86.49	85.75	80.70	82.23	83.61	86.09	81.05	97.08	87.59	94.29
BEVFusion^[20]	L+C	+5.19	91.68	99.73	99.90	90.91	87.88	87.39	89.96	86.90	85.13	97.30
本文算法	L+C	+4.07	95.75	90.13	98.87	98.71	90.06	98.48	98.66	99.10	89.18	98.57

图8 部分场景预测结果可视化

Fig.8 Visualization of predicted results for partial scenes

表2 消融实验结果

Table 2 Ablation experimental results

VFM	BEVFM	mAP
VFM	BEVFM	烟雾	扬尘	伪装
		95.39	92.91	90.83
√		93.82	92.09	93.84
	√	96.82	94.87	92.31
√	√	98.58	95.47	94.11

参考文献 25

[4]	周瑜, 贺伟. 激光成像引信的目标识别方法研究[J]. 激光技术, 2023, 47(2):267-272.
	ZHOU Y, HE W. Target recognition method of laser imaging fuze[J]. Laser Technology, 2023, 47(2):267-272. (in Chinese)
[5]	武军安, 郭锐, 刘荣忠, 等. 用于弹载线阵红外与激光扫描成像引信的轻量化卷积神经网络目标识别方法[J]. 弹道学报, 2021, 33(3):89-96. doi: 10.12115/j.issn.1004-499X(2021)03-014
	WU J A, GUO R, LIU R Z, et al. A lightweight convolutional neural network target recognition method for missile-borne fuse linear array infrared and lidar-scanning image[J]. Journal of Ballistics, 2021, 33(3):89-96. (in Chinese)
[6]	郭甲崇, 刘星, 袁俊, 等. 激光/红外复合扫描引信目标识别算法[J]. 激光与红外, 2020, 50(2):184-191.
	GUO J C, LIU X, YUAN J, et al. Target recognition algorithm for laser/infrared composite scanning fuze[J]. Laser & Infrared, 2020, 50(2):184-191 (in Chinese).
[7]	张远利. 短波红外成像技术在军事上的应用进展[J]. 应用激光, 2024, 44(4):171-177.
	ZHANG Y L. Advancements in the military applications of short-wave infrared imaging technology[J]. Applied Laser, 2024, 44(4):171-177 (in Chinese).
[8]	BUSTOS N, MASHHADI M, LAI-YUEN S K, et al. A systematic literature review on object detection using near infrared and thermal images[J]. Neurocomputing, 2023,560:126804.
[9]	许建康, 刘丙新, 杜雨隆, 等. 船舶溢油污染海冰可见光-近红外反射光谱特征及其角度效应[J]. 光谱学与光谱分析, 2024, 44(7):2075-2082.
	XU J K, LIU B X, DU Y L, et al. Visible near-infrared reflection spectrum characteristics and angular effects of sea ice contaminated by ship oil spills[J]. Spectroscopy and Spectral Analysis, 2024, 44(7):2075-2082 (in Chinese).
[10]	KARANGWA J, LIU J, ZENG Z X. Vehicle detection for autonomous driving:a review of algorithms and datasets[J]. IEEE Transactions on Intelligent Transportation Systems, 2023, 24(11):11568-11594.
[11]	熊光明, 罗震, 孙冬, 等. 基于红外相机和毫米波雷达融合的烟雾遮挡无人驾驶车辆目标检测与跟踪[J]. 兵工学报, 2024, 45(3):893-906. doi: 10.12382/bgxb.2022.0602
	XIONG G M, LUO Z, SUN D, et al. Object detection and tracking for unmanned vehicles based on fusion of infrared camera and MMW radar in smoke-obscured environment[J]. Acta Armamentarii, 2024, 45(3):893-906. (in Chinese) doi: 10.12382/bgxb.2022.0602
[12]	SINDAGI V A, ZHOU Y, TUZEL C, et al. MVX-Net:multimodal VoxelNet for 3D object detection[C]//Proceedings of 2019 International Conference on Robotics and Automation.Montreal, Canada:IEEE,2019:7276-7282.
[13]	VORA S, LANG A H, HELOU B, et al. PointPainting:sequential fusion for 3D object detection[C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle,WA, US:IEEE,2020:4603-4611.
[14]	WANG C W, MA C, ZHU M, et al. PointAugmenting:cross-modal augmentation for 3D object detection[C]//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Online:IEEE,2021:11789-11798.
[15]	CHEN X Z, MA H M, WAN J, et al. Multi-view 3D object detection network for autonomous driving[C]//Proceedings of 2017 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Honolulu,HI, US:IEEE,2017:6526-6534.
[16]	KU J, MOZIFIAN M, LEE J, et al. Joint 3D proposal generation and object detection from view aggregation[C]//Proceedings of 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems.Madrid, Spain:IEEE,2018:5750-5757.
[17]	PANG S, MORRIS D, RADHA H. CLOCs:camera-liDAR object candidates fusion for 3D object detection[C]//Proceedings of 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems.Las Vegas,NV, US:IEEE,2020:10386-10393.
[18]	LI Y W, YU A W, MENG T J, et al. DeepFusion:lidar-camera deep fusion for multi-modal 3D object detection[C]// Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition.New Orleans,LA, US:IEEE,2022:17161-17170.
[1]	孟祥盛, 李乐堃. 数字化激光扫描成像引信低空海面背景目标识别方法[J]. 红外与激光工程, 2023, 52(4):309-320.
	MENG X S, LI L K. Target recognition method of digital laser imaging fuze in ultra-low sea background[J]. Infrared and Laser Engineering, 2023, 52(4):309-320. (in Chinese)
[2]	郑震, 查冰婷, 张合. 基于DHGF算法的激光线扫描成像引信目标识别方法[J]. 中国激光, 2018, 45(7):147-154.
	ZHENG Z, ZHA B T, ZHANG H. Target recognition method of laser line scanning imaging fuze based on DHGF algorithm[J]. Chinese Journal of Lasers, 2018, 45(7):147-154. (in Chinese)
[3]	霍健, 陈慧敏, 马云飞, 等. 基于MEMS激光雷达的车辆目标识别算法[J]. 兵工学报, 2023, 44(4):940-948.
	HUO J, CHEN H M, MA Y F, et al. Vehicle target recognition algorithm based on MEMS LiDAR[J]. Acta Armamentarii, 2023, 44(4):940-948. (in Chinese) doi: 10.12382/bgxb.2021.0822
[19]	BAI X Y, HU Z Y, ZHU X G, et al. TransFusion:Robust LiDAR-camera fusion for 3D object detection with Transformers[C]//Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition.New Orleans,LA, US:IEEE,2022:1080-1089.
[20]	LIANG T T, XIW H W, YU K C, et al. BEVFusion:a simple and robust LiDAR-camera fusion framework[C]//Proceedings of Advances in Neural Information Processing Systems.New Orleans,LA, US:NIPS,2022:35.
[21]	LANG A H, VORA S, CAESAR H, et al. PointPillars:Fast encoders for object detection from point clouds[C]//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Long Beach,CA, US:IEEE,2019:12689-12697.
[22]	YAN Y, MAO Y X, LI B. SECOND:Sparsely embedded convolutional detection[J]. Sensors, 2018, 18(10):3337.
[23]	LIU Z, LIN Y T, CAO Y, et al. Swin transformer:Hierarchical vision transformer using shifted windows[C]//Proceedings of 2021 IEEE/CVF International Conference on Computer Vision. Montreal, Canada:IEEE, 2021,9992-10002.
[24]	PHILION J, FIDLER S. Lift,splat,shoot:encoding images from arbitrary camera rigs by implicitly unprojecting to 3D[C]//Proceedings of 16th European Conference on Computer Vision. Glasgow, UK:Springer, 2020,12359:194-210.
[25]	GEIGER A, LENZ P, URTASUN R.Are we ready for autonomous driving? The KITTI vision benchmark suite[C]//Proceedings of 2012 IEEE/CVF International Conference on Computer Vision. Providence,RI, US:IEEE,2012:3354-3361.