基于国产嵌入式智能计算平台的无人机检测方法

doi:10.12382/bgxb.2022.A013

摘要/Abstract

摘要： 面向陆地战场上对反无人机侦察的现实需求，提出一种基于国产嵌入式智能计算平台的无人机检测方法。针对无人机体型小、易受战场环境影响而不易察觉的难题，采用红外、可见光图像和视频流等多源输入进行目标检测；针对嵌入式平台算力和存储能力有限的特性，构建轻量化深度神经网络，通过将单次多盒检测器（SSD）中的特征提取网络替换为MobileNet进行模型优化；选用国产嵌入式平台比特大陆SE5智能计算盒进行验证，完成模型转换和移植。实验结果表明：所提基于轻量化深度神经网络MobileNet-SSD的无人机检测方法在国产嵌入式智能计算平台上能够准确判断出目标的类别，且平均识别精度和帧率与在开发环境中运行差距不大。充分表明所提方法在国产嵌入式智能计算平台上进行移植后，能够在速度和精度方面满足应用环境对无人机检测算法实时性与准确性的要求。

关键词: 无人机检测, 智能计算平台, 反无人机, 轻量化深度神经网络

Abstract: A UAV detection method based on a domestic embedded intelligent computing platform is proposed to meet the actual requirements of anti-unmanned aerial vehicle(UAV) reconnaissance on the land battlefield. For the problem that UAV is small in size and not easy to be detected in the battlefield environment，the detection method is to use infrared and visible light images and video streams inputs for target detection. For the limited computing power and storage capacity of embedded platform，a lightweight deep neural network is built，and the feature extraction network in single shot multi-box detector(SSD) is replaced with MobileNet for model compression. The embedded platform Bitmain SE5 intelligent computing box is selected for verification， and the model conversion and transplantation are achieved. The experimental result shows that the proposed UAV detection method based on the lightweight deep neural network MobileNet-SSD can accurately determine the type of targets on the embedded intelligent computing platform， and the mean recognition accuracy and frame rate are basically same with those running in the development environment. It fully shows that the detection method can meet the requirements of the real-time and accuracy of UAV detection algorithm in the application environment in terms of speed and accuracy after being transplanted on the embedded intelligent computing platform.

Key words: UAVdetection, embeddedintelligentcomputingplatform, anti-UAV, lightweightdeepneuralnetwork

中图分类号:

E919
TP181

崔令飞，郭永红，修全发，史超，张硕阳. 基于国产嵌入式智能计算平台的无人机检测方法[J]. 兵工学报, 2022, 43(S1): 146-154.

CUI Lingfei， GUO Yonghong， XIU Quanfa， SHI Chao， ZHANG Shuoyang. UAV Detection Method Based on Domestic Embedded Intelligent Computing Platform[J]. Acta Armamentarii, 2022, 43(S1): 146-154.

参考文献

［1］薛猛，周学文，孔维亮.反无人机系统研究现状及关键技术分析［J］.飞航导弹，2021(5):52-56，60.
XUE M，ZHOU X W，KONG W L.Research status and key technology analysis of anti-UAV system［J］.Aerodynamic Missile Journal，2021(5):52-56，60.(in Chinese)
［2］ CHEN Y，MENG H B，WEN X L，et al.Classification methods of a small sample target object in the sky based on the higher layer visualizing feature and transfer learning deep networks［J］.EURASIP Journal on Wireless Communications and Networking，2018(1):127.
［3］ AKER C，KALKAN S.Using deep networks for drone detection［C］∥Proceedings of the 14th IEEE International Conference on Advanced Video and Signal Based Surveillance.Lecce，Italy:IEEE，2017.
［4］梁杰，任君，李磊，等.基于典型几何形状精确回归的机场跑道检测方法［J］.兵工学报，2020，41(10):2045-2054.
LIANG J，REN J，LI L，et al.Airport runway detection algorithm based on accurate regression of typical geometric shapes［J］.Acta Armamentarii，2020，41(10):2045-2054.(in Chinese)
［5］李秋珍，熊饶饶，王汝鹏，等.基于SSD算法的实时无人机识别方法研究［J］.舰船电子工程，2019，39(5):30-35.
LI Q Z，XIONG R R，WANG R P，et al.Research on real-time UAV recognition method based on SSD algorithm［J］.Ship Electronic Engineering，2019，39(5):30-35.(in Chinese)
［6］王若霄，徐智勇，张建林.基于SSD的实时轻量级无人机检测算法［J］.半导体光电，2020，41(2):296-300.
WANG R X，XU Z Y，ZHANG J L.Real-time lightweight UAV detection method based on SSD algorithm［J］.Semiconductor Optoelectronics，2020，41(2):296-300.(in Chinese)
［7］侯鑫，曲国远，魏大洲，等.基于迭代稀疏训练的轻量化无人机目标检测算法［J/OL］.计算机研究与发展:1-11［2022-01-10］.http:∥kns.cnki.net/kcms/detail/11.1777.TP.20210527.1106.002.html.
HOU X，QU G Y，WEI D Z，et al.A lightweight UAV object detection algorithm based on iterative sparse training［J/OL］.Journal of Computer Research and Development：1-11［2022-01-10］.http:∥kns.cnki.net/kcms/detail/11.1777.TP.20210527.1106.002.html.(in Chinese)
［8］孔维刚，李文婧，王秋艳，等.基于改进YOLOv4算法的轻量化网络设计与实现［J］.计算机工程，2022，48（3）：181-188.
KONG W G，LI W J，WANG Q Y，et al.Design and implementation of lightweight network based on YOLOv4 algorithm［J］.Computer Engineering,2022,48(3):181-188. (in Chinese)
［9］ HEREDIA A.BARROS-GAVILANES G.Video processing inside embedded devices using SSD-Mobilenet to count mobility actors［C］∥Proceedings of the IEEE Colombian Conference on Application in Computational Intelligence.Barranquilla，Colombia：IEEE，2019.
［10］ ALI H.KHURSHEED M，FATIMA S K，SHUJA S M，et al.Object recognition for dental instruments using SSD-MobileNet［C］∥Proceedings of the 2019 International Conference on Information Science and Communication Technology.Karachi，Pakistan：IEEE，2019.
［11］ GIRSHICK R，DONAHUE J，DARRELL T，et al.Rich feature hierarchies for accurate object detection and semantic segmentation［C］∥Proceedings of IEEE Confrence on Computer Vision and Pattern Recognition.Columbus，OH，US：IEEE，2014:580-587.
［12］ GIRSHICK R.Fast R-CNN［C］∥Proceedings of IEEE International Conference on Computer Vision.Santiago，Chile:IEEE，2015:1440-1448.
［13］ REN S Q，HE K M，GIRSHICK R，et al.Faster R-CNN: towards real-time object detection with region proposal networks［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence，2017，39(6):1137-1149.
［14］ REDMON J，DIVVALA S，GIRSHICK R.You only look once: unified，real-time object detection［C］∥Proceedings of IEEE Confrence on Computer Vision and Pattern Recognition.Las Vegas，NV，US:IEEE，2016.
［15］ LIU W，ANGUELOV D，ERHAN D，et al.SSD:single shot multibox detector［C］∥Proceedings of the European Conference on Computer Vision.Amsterdam，the Netherlands:Springer，2016:21-37.
［16］文华.华为昇腾智能制造使能平台加速工业制造智能升级［J］.通信世界，2020(32):30-31.
WEN H.Huawei Centem intelligent manufacturing enables the platform to accelerate the intelligent upgrading of industrial manufacturing［J］.Communications World，2020(32):30-31.(in Chinese)
［17］吴中勤，韩钧宇.如何研发中国新一代自主可控的AI算法引擎［J］.人工智能，2019:112-121.
WU Z Q，HAN J Y.How to develop the new generation of autonomous and controllable AI algorithm engine in China［J］.Artificial Intelligence VIEW，2019:112-121.(in Chinese)
［18］ ABADI M，BARHAM P，CHEN J，et al.TensorFlow: a system for large-scale machine learning［C］∥Proceedings of the 12nd USENIX Symposium on Operating Systems Design and Implementation.Savannah，GA，US:USENIX，2016:265-283.
［19］ PASZKE A，GROSS S，MASSA F，et al.PyTorch:An imperative style，high-performance deep learning library［C］∥Proceedings of the 33rd Conference on Neural Information Processing Systems.Vancouver，Canada:Vancouver Convention Centre，2019:8026-8037.
［20］ JIA Y P，SHELHAMER E，DONAHUE J，et al.Caffe: Convolutional architecture for fast feature embedding［C］∥Proceedings of the 22nd ACM International Conference on Multimedia.Orlando，FL，US：ACM，2014: 675-678.
［21］ CHEN T Q，LI M，LI Y T，et al.MXNet:a flexible and efficient machine learning library for heterogeneous distributed systems［J/OL］.arXiv:1-6.(2015-12-02).http:∥www.cs.cmu.edu/~muli/file/mxnet-learning-sys.pdf.
［22］马艳军，于佃海，吴甜，等.飞桨：源于产业实践的开源深度学习平台［J］.数据与计算发展前沿，2019，1(1):105-115.
MA Y J，YU D H，WU T，et al.PaddlePaddle:an open-source deep learning platform from industrial practice［J］.Frontiers of Data & Computing，2019，1(1):105-115.(in Chinese)
［23］于璠.新一代深度学习框架研究［J］.大数据，2020，6(4):69-80.
YU F.Research on the next-generation deep learning framework［J］.Big Data Research，2020，6(4):69-80.(in Chinese)
［24］ HOWARD A G，ZHU M L，CHEN B，et al.Mobilenets:efficient convolutional neural networks for mobile vision applications［EB/OL］.Computer Science，2017. https:∥arxiv.org/abs/1704.04861.
［25］ SVANSTROM F，ENGLUND C，ALONSO-FERNANDEZ F. Real-time drone detection and tracking with visible，thermal and acoustic sensors［C］∥Proceedings of the 25th International Conference on Pattern Recognition.Milan，Italy:IEEE，2021.