基于优化SSD的低空无人机检测方法

doi:10.3778/j.issn.1002-8331.2201-0067

摘要/Abstract

摘要： 针对浅层特征缺乏语义信息和小目标特征不显著的问题，提出了一种基于多尺度特征融合和注意力的低空无人机（unmanned aerial vehicle，UAV）检测方法。首先提出一种多尺度特征融合模块，将不同尺度的特征图进行有效融合，使浅层特征图的细节纹理信息和深层特征图的语义信息得到充分的利用，改善浅层特征语义信息不足的问题。然后在网络特征图输出处引入一种不降维局部跨信道交互策略和核大小自适应选择的通道注意力机制，以极其轻量级的方式获取跨通道的交互信息。为使先验框和有效感受野匹配，优化默认框设置方法，更好地检测小目标。使用自制无人机数据集进行验证，结果表明改进后算法平均准确率为84.07%，比原始SSD（single shot multibox detector）算法提高了7.81个百分点，检测速度达到31.3?frame/s。

关键词: 目标检测, 多尺度特征融合, 低空无人机, 注意力机制

Abstract: For the problems of shallow features lacking semantic information and small target features not significant, a low-altitude UAV（unmanned aerial vehicle） detection method based on attention and multi-scale feature fusion is proposed. Firstly, a multi-scale feature fusion module is proposed to effectively fuse the feature maps of different scales. The detailed texture information of shallow features map and semantic information of deep features map are fully utilized to improve the lack of semantic information of shallow features. Then a local cross-channel interaction strategy without dimensionality reduction and a channel attention mechanism for adaptive selection of core size are introduced at the output of the network feature graph to obtain cross-channel interaction information in an extremely lightweight way. Finally, in order to match the prior boxes with effective receptive field, the default box setting method is optimized to better detect small targets. The self-made UAV data set is used for verification. The results show that the average accuracy of this method is 84.07%, which is 7.81 percentage points higher than original SSD（single shot multibox detector） algorithm, and the detection speed is 31.3 frame/s.

Key words: object detection, multi-scale feature fusion, low-altitude UAV, attentional mechanism

张灵灵, 王鹏, 李晓艳, 吕志刚, 邸若海. 基于优化SSD的低空无人机检测方法[J]. 计算机工程与应用, 2022, 58(16): 204-212.

ZHANG Lingling, WANG Peng, LI Xiaoyan, LYU Zhigang, DI Ruohai. Low-Altitude UAV Detection Method Based on Optimized SSD[J]. Computer Engineering and Applications, 2022, 58(16): 204-212.

参考文献

[1] LAN Y，CHEN S.Current status and trends of plant protection UAV and its spraying technology in China[J].International Journal of Precision Agricultural Aviation，2018，1（1）：1-9.
[2] KINNEY J R.The eye of war：military perception from the telescope to the drone[J].The American Historical Review，2020，125（5）：1835-1836.
[3] ADADE R，AIBINU A M，EKUMAH B，et al.Unmanned aerial vehicle（UAV） applications in coastal zone management—a review[J].Environmental Monitoring and Assessment，2021，193（3）：154.
[4] AYAMGA M，AKABA S，NYAABA A A.Multifaceted applicability of drones：a review[J].Technological Forecasting and Social Change，2021，167：120677.
[5] 张瑞鑫，黎宁，张夏夏，等.基于优化CenterNet的低空无人机检测方法[J/OL].北京航空航天大学学报[2021-11-07].https：//doi.org/10.13700/j.bh.1001-5965.2021.0108.
ZHANG R X，LI N，ZHANG X X，et al.Low-altitude UAV detection method based on optimized CenterNet[J/OL].Journal of Beijing University of Aeronautics and Astronautics[2021-11-07].https：//doi.org/10.13700/j.bh.1001-5965.
2021.0108.
[6] SVANSTR?M F，ENGLUND C，ALONSO-FERNANDEZ F.Real-time drone detection and tracking with visible，thermal and acoustic sensors[C]//2020 25th International Conference on Pattern Recognition，2020：7265-7272.
[7] ARJMANDI Z，KANG J，PARK K，et al.Benchmark dataset of ultra-wideband radio based UAV positioning[C]//2020 IEEE 23rd International Conference on Intelligent Transportation Systems，2020.
[8] KUMAR S，JAIN A，RODRIGUES C A，et al.Gesture control of UAV using radio frequency[C]//3rd International Conference on Frontiers in Automobile and Mechanical Engineering，2020.
[9] REN J，JIANG X.A three-step classification framework to handle complex data distribution for radar UAV detection[J].Pattern Recognition，2021，111：107709.
[10] 罗俊海，王芝燕.无人机探测与对抗技术发展及应用综述[J].控制与决策，2022，37（3）：530-544.
LUO J H，WANG Z Y.A review of development and application of UAV detection and counter technology[J].Control and Decision，2022，37（3）：530-544.
[11] CHEN J F，LU K Y，WANG J X.Research on UAV image recognition based on convolutional neural network[C]//2020 IEEE International Conference on Artificial Intelligence and Computer Applications，2020.
[12] NIE J F，LUO T，LI H.Automatic hotspots detection based on UAV infrared images for large-scale PV plant[J].Electronics Letters，2020，56（19）：993-995.
[13] 邢姗姗，赵文龙.基于YOLO系列算法的复杂场景下无人机目标检测研究综述[J].计算机应用研究，2020，37（S2）：28-30.
XING S S，ZHAO W L.Review of UAV target detection in complex scenarios based on YOLO series algorithms[J].Application Research of Computers，2020，37（S2）：28-30.
[14] GIRSHICK R，DONAHUE J，DARRELL T，et al.Region-based convolutional networks for accurate object detection and segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2015，38（1）：142-158.
[15] REN S，HE K，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.
[16] REDMON J，FARHADI A.Yolov3：an incremental improvement[J].arXiv：1804.02767，2018.
[17] BOCHKOVSKIY A，WANG C Y，LIAO H.YOLOv4：optimal speed and accuracy of object detection[J].arXiv：2004.10934，2020.
[18] LIU W，ANGUELOV D，ERHAN D，et al.SSD：single shot multibox detector[C]//14th European Conference on Computer Vision.Cham：Springer，2016：21-37.
[19] 陈帅，尹洋，杨全顺.基于深度学习的无人机入侵检测方法[J].计算机系统应用，2021，30（4）：32-38.
CHEN S，YIN Y，YANG Q S.UAV intrusion detection method based on deep learning[J].Computer Systems and Applications，2021，30（4）：32-38.
[20] 刘佳铭.基于深度卷积神经网络的无人机识别方法研究[J].舰船电子工程，2019，39（2）：22-26.
LIU J M.Research on UAV recognition method based on DCNN[J].Ship Electronic Engineering，2019，39（2）：22-26.
[21] 周强，夏明赟.基于改进SSD算法的多无人机检测研究[J].信息技术，2020，44（12）：71-76.
ZHOU Q，XIA M Y.Research on multi-UAV detection based on improved SSD algorithm[J].Information Technology，2020，44（12）：71-76.
[22] 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 Optoelectronic，2020，41（2）：296-300.
[23] LI Z，ZHOU F.FSSD：feature fusion single shot multibox detector[J].arXiv：1712.00960，2017.
[24] LIM J S，ASTRID M，YOON H J，et al.Small object detection using context and attention[C]//2021 International Conference on Artificial Intelligence in Information and Communication，2021：181-186.
[25] 赵鹏飞，谢林柏，彭力.融合注意力机制的深层次小目标检测算法[J].计算机科学与探索，2022，16（4）：927-937.
ZHAO P F，XIE L B，PENG L.Deep small object detection algorithm integrating attention mechanism[J].Journal of Frontiers of Computer Science and Technology，2022，16（4）：927-937.
[26] 李文涛，彭力.多尺度通道注意力融合网络的小目标检测算法[J].计算机科学与探索，2021，15（12）：2390-2400.
LI W T，PENG L.Small objects detection algorithm with multi-scale channel attention fusion network[J].Journal of Frontiers of Computer Science and Technology，2021，15（12）：2390-2400.
[27] WANG Q，WU B，ZHU P，et al.ECA-Net：efficient channel attention for deep convolutional neural networks[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition，2020.
[28] HU J，SHEN L，ALBANIE S，et al.Squeeze-and-excitation networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2020，42（8）：2011-2023.
[29] SELVARAJU R R，COGSWELL M，DAS A，et al.Grad-CAM：visual explanations from deep networks via gradient-based localization[J].International Journal of Computer Vision，2020，128（2）：336-359.
[30] 王浩桐，郭中华.锚框策略匹配的SSD飞机遥感图像目标检测[J/OL].计算机科学与探索[2021-11-11].http：//kns.cnki.net/kcms/detail/11.5602.TP.20210726.1310.002.html.
WANG H T，GUO Z H.Target detection of SSD aircraft remote sensing images based on anchor frame[J/OL].Journal of Frontiers of Computer Science and Technology[2021-11-11].http：//kns.cnki.net/kcms/detail/11.5602.TP.
20210726.1310.002.html.
[31] FU C Y，LIU W，RANGA A，et al.DSSD：deconvolutional single shot detector[J].arXiv：1701.06659，2017.