首页 > 论文 > 液晶与显示 > 33卷 > 9期(pp:793-800)

基于深度学习的航空对地小目标检测

Detection of small target in aerial photography based on deep learning

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对航拍图像中对地小目标识别率低、定位效果差的问题,提出了一种基于深度学习的目标检测算法。该算法利用VGG16网络作为微调网络,并添加部分深层网络,通过提取目标浅层特征与深层特征进行联合训练,克服检测过程中定位与识别相互矛盾的问题。提出把奇异值分解技术应用于卷积特征压缩处理,降低模型的计算与存储需求,并且采用多尺度训练方法以适应航空目标尺度的变化。实验结果表明,在通用数据集PASCAL上可以实现0.76 mAP,检测速度达16 fps,在专用航空目标数据集UCAS-AOD上可以实现0.63 mAP,检测速度达18 fps。基本满足对小目标检测精确度的要求,并且检测速度可以接近实时检测效果。

Abstract

In order to solve the problem of low recognition rate and poor positioning in aerial images, a target detection method based on deep learning is proposed. This algorithm uses VGG16 network as a fine tuning network and adds some deep network in it. Joint training is carried out by extracting the features of the shallow layers and the deep features of the target to overcome the contradiction between location and recognition in the process of detection. The singular value decomposition technology is used to compress the convolution features to reduce the computing and storage requirements of the model, and Multi scale training method is adopted to adapt to the change of aerial target scale. The experimental results show that 0.76 mAP can be implemented on the general data set PASCAL, and the detection speed is 16 fps. The 0.63 mAP can be achieved on the special aviation target data set UCAS-AOD, and the detection speed is 18 fps. It can satisfy the requirements for small target detection accuracy, and the detection speed can be close to the real-time detection effect.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391

DOI:10.3788/yjyxs20183309.0793

所属栏目:图像处理

基金项目:国家自然科学基金(No.61705225)

收稿日期:2018-04-02

修改稿日期:2018-06-08

网络出版日期:--

作者单位    点击查看

梁华:中国科学院 长春光学精密机械与物理研究所,吉林 长春130033中国科学院大学,北京100049
宋玉龙:中国科学院 长春光学精密机械与物理研究所,吉林 长春130033
钱锋:中国科学院 长春光学精密机械与物理研究所,吉林 长春130033
宋策:中国科学院 长春光学精密机械与物理研究所,吉林 长春130033

联系人作者:宋玉龙(songYL@ciomp.ac.cn)

备注:梁华(1993-),男,四川宜宾人,硕士研究生,2016年于重庆大学获得学士学位,主要从事机器学习与图像检测方面的研究。E-mail:lianghua_ucas@foxmail.com

【1】LOWED G. Distinctive image features from scale-invariant keypoints [J]. International Journal of Computer Vision, 2004, 60(2): 91-110.

【2】齐冰洁,刘金国,张博研,等. 高分辨率遥感图像SIFT和SURF算法匹配性能研究[J]. 中国光学,2017,10(3):331-339.
QI B J, LIU J G, ZHANG B Y, et al. Research on matching performance of SIFT and SURF algorithms for high resolution remote sensing image [J]. Chinese Optics, 2017, 10(3): 331-339. (in Chinese)

【3】王梅,屠大维,周许超. SIFT特征匹配和差分相乘融合的运动目标检测[J]. 光学 精密工程,2011,19(4):892-899.
WANG M, TU D W, ZHOU X C. Moving object detection by combining SIFT and differential multiplication [J]. Optics and Precision Engineering, 2011, 19(4): 892-899. (in Chinese)

【4】耿庆田,赵浩宇,于繁华,等. 基于改进HOG特征提取的车型识别算法[J]. 中国光学,2018,11(2):174-181.
GENG Q T, ZHAO H Y, YU F H, et al. Vehicle type recognition algorithm based on improved HOG feature [J]. Chinese Optics, 2018, 11(2): 174-181. (in Chinese)

【5】GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation [C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus, OH, USA: IEEE, 2014: 580-587.

【6】FELZENSZWALB P F, GIRSHICK R B, MCALLESTER D, et al. Object detection with discriminatively trained part-based models [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(9): 1627-1645.

【7】Felzenszwalb P, Mcallester D, Ramanan D. A discriminatively trained, multiscale, deformable part mode[J].IEEE Conference on Computer Visionand Pattern Recognition[J].2008,8:1-8.

【8】刘峰,沈同圣,马新星,等. 基于多波段深度神经网络的舰船目标识别[J]. 光学 精密工程,2017,25(11):2939-2946.
LIU F, SHEN T S, MA X X, et al. Ship recognition based on multi-band deep neural network [J]. Optics and Precision Engineering, 2017, 25(11): 2939-2946. (in Chinese)

【9】李宇,刘雪莹,张洪群,等. 基于卷积神经网络的光学遥感图像检索[J]. 光学 精密工程,2018,26(1):200-207.
LI Y, LIU X Y, ZHANG H Q, et al. Optical remote sensing image retrieval based on convolutional neural networks [J]. Optics and Precision Engineering, 2018, 26(1): 200-207. (in Chinese)

【10】LIN T Y, DOLLAR P, GIRSHICK R, et al. Feature pyramid networks for object detection [C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, Hawaii, USA: IEEE, 2017: 936-944.

【11】LIU W, ANGUELOV D, ERHAN D, et al. SSD: Single shot MultiBox detector [C]//Proceedings of the 14th European Conference. Amsterdam, The Netherlands: Springer, 2016: 21-37.

【12】HE K M, ZHANG X Y, REN S Q, 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.

【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, et al. You only look once: Unified, real-time object detection [C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA: IEEE, 2016: 779-788.

【15】BODLA N, SINGH B, CHELLAPPA R, et al. Soft-NMS —Improving object detection with one line of code [C]//Proceedings of 2017 IEEE International Conference on Computer Vision. Venice, Italy: IEEE, 2017: 5562-5570.

【16】SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition [J]. arXiv:1409.1556, 2014.

【17】LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition [J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.

【18】KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks [C]//Proceedings of the 25th International Conference on Neural Information Processing Systems. Lake Tahoe, Nevada: Curran Associates Inc., 2012: 1097-1105.

【19】ZEILER M D, FERGUS R. Visualizing and understanding convolutional networks [C]//Proceedings of the 13th European Conference. Zurich, Switzerland: Springer, 2014: 818-833.

引用该论文

LIANG Hua,SONG Yu-long,QIAN Feng,SONG Ce. Detection of small target in aerial photography based on deep learning[J]. Chinese Journal of Liquid Crystals and Displays, 2018, 33(9): 793-800

梁华,宋玉龙,钱锋,宋策. 基于深度学习的航空对地小目标检测[J]. 液晶与显示, 2018, 33(9): 793-800

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF