基于深度可分离卷积的实时遥感目标检测算法

王成龙; 赵倩; 赵琰; 郭彤

doi:doi:10.3969/j.issn.1671-637x.2022.08.009

电光与控制, 2022, 29 (8): 45, 网络出版: 2022-08-14

基于深度可分离卷积的实时遥感目标检测算法

A Real-Time Remote Sensing Target Detection Algorithm Based on Depth Separable Convolution

论文大纲

王成龙赵倩赵琰郭彤

作者单位

上海电力大学电子与信息工程学院, 上海 201000

遥感目标检测聚类深度可分离卷积参数量 remote sensing target detection clustering depth separable convolution parameter quantity 

摘要

针对基于深度学习的遥感目标检测算法参数冗余、计算量大且实时检测性能较差的问题, 提出了一种基于深度可分离卷积的实时遥感目标检测算法。首先通过K-means++算法对数据集进行锚框(Anchor)聚类分析, 使锚框参数更加符合遥感检测场景。为了降低模型参数量、提升检测速度, 以轻量级网络MobileNetv3作为主干网络进行特征提取; 此外, 基于深度可分离卷积的PANet(Path Aggregation Network)结构的设计, 使网络参数量进一步降低。改进后模型参数量仅为原来的18.3%, 检测速度提升2.19倍, 在UCAS_AOD, RSOD, DIOR这3个遥感数据集上进行测试, 实验结果表明, 算法鲁棒性强, 能够在保证模型检测精度的同时有效提高检测实时性。

Abstract

Remote sensing target detection algorithms based on deep learning have redundant parameters, large computation amount and poor real-time detection performance.To solve the above problems, a real-time remote sensing target detection algorithm based on depth separable convolution is proposed.The datasets are analyzed by anchor box (Anchor) clustering via the K-means++ algorithm, making the anchor box parameters more compliant with the remote sensing detection scenario.In order to reduce the quantity of model parameters and improve the detection speed, feature extraction is performed with the lightweight network MobileNetv3 as the backbone network.In addition, the design of PANet (Path Aggregation Network) structure based on depth separable convolution makes the quantity of network parameters further reduced.The quantity of model parameters after improvement is only 18.3% of the original, and the detection speed is 2.19 times faster than the original.Tests are conducted on three remote sensing datasets, that is, UCAS_AOD, RSOD and DIOR, and the experimental results show that the algorithm is robust and can effectively improve the real-time detection performance while ensuring the model detection accuracy.

参考文献

[1] YA Y, PAN H, JING Z L, et al.Fusion object detection of satellite imagery with arbitrary-oriented region convolutional neural network［J］.Aerospace Systems, 2019, 2(2):163-174.

[2] CHENG G, HAN J W.A survey on object detection in optical remote sensing images［J］.ISPRS Journal of Photogrammetry and Remote Sensing, 2016, 117:11-28.

[3] 王成龙,赵倩,郭彤.基于面部特征的深度学习安全帽检测［J］.上海电力大学学报,2021,37(3):303-307.

[4] REDMON J, FARHADI A.YOLOv3:an incremental improvement［EB/OL］.(2018-04-08)［2021-07-09］.https://arxiv.org/abs/1804.02767.

[5] LIU W, ANGUELOV D, ERHAN D, et al.SSD:single shot multibox detector［C］//European Conference on Computer Vision.Cham:Springer, 2016:21-37.

[6] 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.

[7] ZHOU X Y, WANG D Q, KRHENBHL P.Objects as points［EB/OL］.(2019-04-25)［2021-07-09］.https://arxiv.org/abs/1904.07850.

[8] TIAN Z, SHEN C H, CHEN H, et al.FCOS:fully convolutional one-stage object detection［C］//IEEE/CVF International Conference on Computer Vision.Seoul:IEEE, 2019:9626-9635.

[9] 蒋光峰,胡鹏程,叶桦,等.基于旋转中心点估计的遥感目标精确检测算法［J］.计算机应用研究,2021,38(9):2866-2870.

[10] XU D Q, WU Y Q.Improved YOLO-V3 with DenseNet for multi-scale remote sensing target detection［J］.Sensors, 2020, 20(15):4276.

[11] XU D Q, WU Y Q.FE-YOLO:a feature enhancement network for remote sensing target detection［J］.Remote Sensing, 2021, 13(7):1311.

[12] GUO F, QIAN Y, SHI Y F.Real-time railroad track components inspection based on the improved YOLOv4 framework［J］.Automation in Construction, 2021, 125:103596.

[13] BOCHKOVSKIY A, WANG C Y, LIAO H Y M.YOLOv4:optimal speed and accuracy of object detection［EB/OL］.(2020-04-23)［2021-07-09］.https://arxiv.org/abs/2004.10934.

[14] HOWARD A, SANDLER M, CHEN B, et al.Searching for MobileNetV3［C］//IEEE/CVF International Conference on Computer Vision.Seoul:IEEE, 2019:1314-1324.

[15] LIU S, QI L, QIN H F, et al.Path aggregation network for instance segmentation［C］//IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City, UT:IEEE, 2018:8759-8768.

[16] ZHU H G, CHEN X G, DAI W Q, et al.Orientation robust object detection in aerial images using deep convolutional neural network［C］//IEEE International Confe-rence on Image Processing.Quebec City:IEEE, 2015:3735-3739.

[17] XIAO Z F, LIU Q, TANG G F, et al.Elliptic Fourier transformation-based histograms of oriented gradients for rotationally invariant object detection in remote-sensing images［J］.International Journal of Remote Sensing, 2015, 36(2):618-644.

[18] LI K, WAN G, CHENG G, et al.Object detection in optical remote sensing images:a survey and a new benchmark［EB/OL］.(2019-09-22)［2021-07-09］.https://arxiv.org/abs/1909.00133v2.

[19] AGGARWAL S, SINGH P.Cuckoo, Bat and Krill Herd based k-means++ clustering algorithms［J］.Cluster Computing, 2019, 22(6):14169-14180.

[20] 邵伟平,王兴,曹昭睿,等.基于MobileNet与YOLOv3的轻量化卷积神经网络设计［J］.计算机应用,2020,40(增刊1):8-13.

[21] 公明,刘妍妍,李国宁.改进YOLO-v3的遥感图像舰船检测方法［J］.电光与控制,2020,27(5):102-107.

[22] 姚群力,胡显,雷宏.基于多尺度卷积神经网络的遥感目标检测研究［J］.光学学报,2019,39(11):346-353.

王成龙, 赵倩, 赵琰, 郭彤. 基于深度可分离卷积的实时遥感目标检测算法[J]. 电光与控制, 2022, 29(8): 45. WANG Chenglong, ZHAO Qian, ZHAO Yan, GUO Tong. A Real-Time Remote Sensing Target Detection Algorithm Based on Depth Separable Convolution[J]. Electronics Optics & Control, 2022, 29(8): 45.

基于深度可分离卷积的实时遥感目标检测算法

关于本站 Cookie 的使用提示

全站搜索

基于深度可分离卷积的实时遥感目标检测算法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索