基于并行附加特征提取网络的SSD地面小目标检测模型

doi:10.3969/j.issn.0372-2112.2020.01.010

电子学报 ›› 2020, Vol. 48 ›› Issue (1): 84-91.DOI: 10.3969/j.issn.0372-2112.2020.01.010

基于并行附加特征提取网络的SSD地面小目标检测模型

李宝奇, 贺昱曜, 强伟, 何灵蛟

西北工业大学航海学院, 陕西西安 710072

收稿日期:2019-01-02 修回日期:2019-08-03 出版日期:2020-01-25
- 通讯作者:
- 李宝奇
- 作者简介:
- 贺昱曜 男,1956年生,陕西富平人.教授,西北工业大学博士生导师,主要研究方向为精确制导与仿真、智能控制与智能优化理论、图像处理理论与算法.E-mail:heyyao@nwpu.edu.cn;强伟男,1986年12月生,陕西延安人.现于西北工业大学航海学院攻读硕士学位,研究方向为图像分类、图像语义分割及目标检测与识别等;何灵蛟 男,1994年12月生,甘肃会宁人.现于西北工业大学航海学院攻读硕士学位,研究方向为图像增强、图像语义分割及目标检测与识别.
- 基金资助:
- 国家自然科学基金 (No.61271143）

SSD with Parallel Additional Feature Extraction Network for Ground Small Target Detection

LI Bao-qi, HE Yu-yao, QIANG Wei, HE Ling-jiao

School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, Shaanxi 710072, China

Received:2019-01-02 Revised:2019-08-03 Online:2020-01-25 Published:2020-01-25
- Corresponding author:
- LI Bao-qi
- Supported by:
- National Natural Science Foundation of China (No.61271143)

摘要/Abstract

摘要： 针对SSD原始附加特征提取网络（Original Additional Feature Extraction Network，OAFEN）中stride操作造成图像小目标信息丢失和串联结构产生的多尺度特征之间冗余度较大的问题，提出了一种计算量小、感受野大的深度可分离空洞卷积（Depthwise Separable Dilated Convolution，DSDC），并利用DSDC设计了一个包含三个独立子网络的并行附加特征提取网络（Parallel Additional Feature Extraction Network，PAFEN）.PAFEN上路用两个DSDC提取尺寸为19*19和3*3的特征图；中路用一个DSDC提取尺寸为10*10的特征图；下路用两个DSDC提取尺寸为5*5和1*1的特征图.实验结果表明，在SSD框架内，PAFEN在mAP和检测时间等方面均优于OAFEN，适用于地面小目标的检测任务.

关键词: 目标检测, SSD, 深度可分离卷积, 空洞卷积, 深度可分离空洞卷积, 并行附加特征提取网络

Abstract: Aiming at the problems of small target information loss caused by stride operation and large redundancy among multi-scale feature maps generated by serial structure in original additional feature extraction network (OAFEN) of SSD, a depthwise separable dilated convolution (DSDC) with small computation and large field of receptivity is proposed; then a parallel additional feature extraction network (PAFEN) with three independent subnetworks is designed by using five DSDCs. In upper subnetwork of PAFEN,two DSDCs are used to extract 19*19 and 3*3 feature maps. In intermediate subnetwork of PAFEN, one DSDC is used to extract 10*10 feature maps.In lower subnetwork of PAFEN, two DSDCs are used to extract 5*5 and 1*1 feature maps. The experimental results show that within the framework of SSD, PAFEN is superior to OAFEN in terms of mAP and detection time, and is suitable for ground small target detection tasks.

Key words: target detection, SSD, depthwise separable convolution, dilated convolution, depthwise separable dilated convolution, parallel additional feature extraction network

中图分类号:

TP183

李宝奇, 贺昱曜, 强伟, 等. 基于并行附加特征提取网络的SSD地面小目标检测模型[J]. 电子学报, 2020, 48(1): 84-91.

LI Bao-qi, HE Yu-yao, QIANG Wei, et al. SSD with Parallel Additional Feature Extraction Network for Ground Small Target Detection[J]. Acta Electronica Sinica, 2020, 48(1): 84-91.

参考文献

[1] RAJA ABDULLAH R S A,SALAH A,ISMAIL A,et al.LTE-based passive bistatic radar system for detection of ground-moving targets[J].ETRI Journal,2016,38(2):302-313.
[2] SUNGHO K,WOO-JIN S,SO-HYUN K.Robust ground target detection by SAR and IR sensor fusion using adaboost-based feature selection[J].Sensors,2016,16(7):1117-1134.
[3] XU H,YANG Z,CHEN G,et al.A ground moving target detection approach based on shadow feature with multichannel high-resolution synthetic aperture radar[J].IEEE Geoscience and Remote Sensing Letters,2016,13(10):1-5.
[4] BREITENSTEIN M D,REICHLIN F,LEIBE B,et al.Online multiperson tracking-by-detection from a single,uncalibrated camera[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(9):1820-1833.
[5] 罗会兰,童康,孔繁胜.基于深度学习的视频中人体动作识别进展综述[J].电子学报,2019,47(5):1162-1173. LUO Hui-lan,TONG Kang,KONG Fan-sheng.The progress of human action recognition in videos based on deep learning:a review[J].Acta Electronica Sinica,2019,47(5):1162-1173.(in Chinese)
[6] LECUN Y,BENGIO Y,HINTON G.Deep learning[J].Nature,2015,521(7553):436-444.
[7] SCHMIDHUBER,JÜRGEN.Deep learning in neural networks:An overview[J].Neural Networks,2015,61:85-117.
[8] KRIZHEVSKY A,SUTSKEVER I,HINTON G.Imagenet classification with deep convolutional neural networks[A].International Conference on Neural Information Processing Systems[C].Doha:Curran Associates Inc,2012.1097-1105.
[9] HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition[A].Conference on Computer Vision and Pattern Recognition[C].Las Vegas:IEEE,2016.770-778.
[10] XIE S,GIRSHICK R,DOLLÁR P,et al.Aggregated residual transformations for deep neural networks[A].Conference on Computer Vision and Pattern Recognition[C].Honolulu:IEEE,2017.1492-1500.
[11] GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation[A].Conference on Computer Vision and Pattern Recognition[C].Columbus:IEEE,2014.580-587.
[12] GIRSHICK R.Fast R-CNN[A].Proceedings of the IEEE International Conference on Computer Vision[C].Santiago:IEEE,2015.1440-1448.
[13] HE K,ZHANG X,REN S,et al.Spatial pyramid pooling in deep convolutional networks for visual recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(9):1904-1916.
[14] REN S,HE K,GIRSHICK R,et al.Faster R-CNN:Towards real-time object detection with region proposal networks[A].Advances in Neural Information Processing Systems[C].Canada:Curran Associates Inc,2015.91-99.
[15] REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once:Unified,real-time object detection[A].Conference on Computer Vision and Pattern Recognition[C].Las Vegas:IEEE,2016.779-788.
[16] LIU W,ANGUELOV D,ERHAN D,et al.SSD:Single shot multibox detector[A].European Conference on Computer Vision[C].Cham:Springer,2016.21-37.
[17] YU F,KOLTUN V.Multi-scale context aggregation by dilated convolutions[J].ArXiv Preprint,2015,arXiv:1511.07122.
[18] CHEN L C,PAPANDREOU G,KOKKINOS I,et al.Deeplab:Semantic image segmentation with deep convolutional nets,Atreus convolution,and fully connected CRFS[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,40(4):834-848.
[19] WANG P,CHEN P,YUAN Y,et al.Understanding convolution for semantic segmentation[A].Winter Conference on Applications of Computer Vision (WACV)[C].Lake Tahoe:IEEE,2018.1451-1460.
[20] LI Z,ZHOU F.FSSD:feature fusion single shot multibox detector[J].ArXiv Preprint,2017,arXiv:1712.00960.
[21] FU C Y,LIU W,RANGA A,et al.DSSD:Deconvolutional single shot detector[J].ArXiv Preprint,2017,arXiv:1701.06659.
[22] ZHOU P,NI B,GENG C,et al.Scale-transferrable object detection[A].Conference on Computer Vision and Pattern Recognition[C].Salt Lake City:IEEE,2018.528-537.
[23] HOWARD A G,ZHU M,CHEN B,et al.Mobilenets:Efficient convolutional neural networks for mobile vision applications[J].ArXiv Preprint,2017,arXiv:1704.04861.
[24] LI Z,PENG C,YU G,et al.Detnet:A backbone network for object detection[J].ArXiv Preprint,2018,arXiv:1804.06215.
[25] SINGH B,DAVIS L S.An analysis of scale invariance in object detection snip[A].Conference on Computer Vision and Pattern Recognition[C].Salt Lake City:IEEE,2018.3578-3587.
[26] CAI Z,VASCONCELOS N.Cascade R-CNN:Delving into high quality object detection[A].Conference on Computer Vision and Pattern Recognition[C].Salt Lake City:IEEE,2018.6154-6162.
[27] LI J,LIANG X,WEI Y,et al.Perceptual generative adversarial networks for small object detection[A].Conference on Computer Vision and Pattern Recognition[C].Honolulu:IEEE,2017.1222-1230.
[28] 李宝奇,贺昱曜,何灵蛟,强伟.基于全卷积神经网络的非对称并行语义分割模型[J].电子学报,2019,47(5):1058-1064. LI Bao-qi,HE Yu-yao,HE Ling-jiao,QIANG Wei.Asymmetric parallel semantic segmentation model based on full convolutional neural network[J].Acta Electronica Sinica,2019,47(5):1058-1064.(in Chinese)

基于并行附加特征提取网络的SSD地面小目标检测模型

SSD with Parallel Additional Feature Extraction Network for Ground Small Target Detection

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	贺军义, 吴梦翔, 宋成, 张敏, 张俊楠. 双目视觉辅助PDR的组合导航定位方法[J]. 电子学报, 2023, 51(3): 736-745.
[2]	唐维伟, 钟胜, 卢金仪, 颜露新, 谭富中, 邹旭, 徐文辉. 基于FPGA的Skynet网络结构优化及高时效实现[J]. 电子学报, 2023, 51(2): 314-323.
[3]	柳长源, 张玉亮, 毕晓君. 基于多阶段提议稀疏区域卷积网络的城市交通目标检测[J]. 电子学报, 2023, 51(1): 26-31.
[4]	琚长瑞, 秦晓燕, 袁广林, 李豪, 朱虹. 尺度敏感损失与特征融合的快速小目标检测方法[J]. 电子学报, 2022, 50(9): 2119-2126.
[5]	李超, 黄新宇, 王凯. 基于特征融合和自学习锚框的高分辨率图像小目标检测算法[J]. 电子学报, 2022, 50(7): 1684-1695.
[6]	包中华, 卢建斌, 田永华, 田树森. 密集杂波背景下雷达微弱海面目标的修正Hough变换TBD检测新方法[J]. 电子学报, 2022, 50(7): 1735-1743.
[7]	廖勇, 李玉杰. 一种轻量化低复杂度的FDD大规模MIMO系统CSI反馈方法[J]. 电子学报, 2022, 50(5): 1211-1217.
[8]	肖进胜, 张舒豪, 陈云华, 王元方, 杨力衡. 双向特征融合与特征选择的遥感影像目标检测[J]. 电子学报, 2022, 50(2): 267-272.
[9]	李斌, 齐延荣, 周清雷. 基于Winograd算法的目标检测加速器设计与优化[J]. 电子学报, 2022, 50(10): 2387-2397.
[10]	罗会兰, 袁璞, 童康. 基于深度学习的显著性目标检测方法综述[J]. 电子学报, 2021, 49(7): 1417-1427.
[11]	程旭, 宋晨, 史金钢, 周琳, 张毅锋, 郑钰辉. 基于深度学习的通用目标检测研究综述[J]. 电子学报, 2021, 49(7): 1428-1438.
[12]	周勇, 陈思霖, 赵佳琦, 张迪, 王瀚正. 基于弱语义注意力的遥感图像可解释目标检测[J]. 电子学报, 2021, 49(4): 679-689.
[13]	王洪雁, 张海坤, 罗宇华, 汪祖民. 复杂动态背景下基于群稀疏的运动目标检测方法[J]. 电子学报, 2021, 49(12): 2330-2338.
[14]	罗大鹏, 杜国庆, 曾志鹏, 魏龙生, 高常鑫, 陈应, 肖菲, 罗琛. 基于少量样本学习的多目标检测跟踪方法[J]. 电子学报, 2021, 49(1): 183-191.
[15]	李维刚, 叶欣, 赵云涛, 王文波. 基于改进YOLOv3算法的带钢表面缺陷检测[J]. 电子学报, 2020, 48(7): 1284-1292.