一种基于分层多尺度卷积特征提取的坦克装甲目标图像检测方法
Image Detection Method for Tank and Armored Targets Based on Hierarchical Multi-scale Convolution Feature Extraction
查看参考文献27篇
文摘
|
针对坦克装甲目标的图像检测任务,提出一种基于分层多尺度卷积特征提取的目标检测方法。采用迁移学习的设计思路,在VGG-16网络的基础上针对目标检测任务对网络的结构和参数进行修改和微调,结合建议区域提取网络和目标检测子网络来实现对目标的精确检测。对于建议区域提取网络,在多个不同分辨率的卷积特征图上分层提取多种尺度的建议区域,增强对弱小目标的检测能力;对于目标检测子网络,选用分辨率更高的卷积特征图来提取目标,并额外增加了一个上采样层来提升特征图的分辨率。通过结合多尺度训练、困难负样本挖掘等多种设计和训练方法,所提出的方法在构建的坦克装甲目标数据集上取得了优异的检测效果,目标检测的精度和速度均优于目前主流的检测方法。 |
其他语种文摘
|
A target detection method based on hierarchical multi-scale convolution feature extraction is proposed for the image detection of tank and armored targets. The idea of transfer learning is used to mo-dify and fine-tune the structure and parameters of VGG-16 network according to the target detection task,and the region proposal network and the detection sub-network are combined to realize the accurate detection of targets. For the region proposal network,the multi-scale proposals are extracted from the convolution feature maps of different resolutions to enhance the detection capability of small targets. For the object detection sub-network,the feature maps with high-resolution convolution are used to extract the targets,and an upsampling layer is added to enhance the resolution of the feature maps. With the help of multi-scale training and hard negative sample mining,the proposed method achieves the excellent results in the tank and armored target data set,and its detection accuracy and speed are better than the those of current mainstream detection methods. |
来源
|
兵工学报
,2017,38(9):1681-1691 【核心库】
|
DOI
|
10.3969/j.issn.1000-1093.2017.09.003
|
关键词
|
兵器科学与技术
;
目标探测与识别
;
卷积神经网络
;
坦克装甲目标
;
目标检测
|
地址
|
装甲兵工程学院控制工程系, 北京, 100072
|
语种
|
中文 |
文献类型
|
研究性论文 |
ISSN
|
1000-1093 |
学科
|
自动化技术、计算机技术 |
基金
|
总装备部院校科技创新工程项目
|
文献收藏号
|
CSCD:6083862
|
参考文献 共
27
共2页
|
1.
尹宏鹏. 基于视觉的目标检测与跟踪综述.
自动化学报,2016,42(10):1466-1489
|
CSCD被引
117
次
|
|
|
|
2.
王铁虎. 精确打击作战与装甲装备未来发展.
兵工学报,2010,31(增刊2):59-65
|
CSCD被引
2
次
|
|
|
|
3.
郭明玮. 基于支持向量机的目标检测算法综述.
控制与决策,2014,29(2):193-200
|
CSCD被引
34
次
|
|
|
|
4.
Felzenszwalb P. Object detection with discriminatively trained part based models.
IEEE Tran-sactions on Pattern Analysis and Machine Intelligence,2010,32(9):1627-1645
|
CSCD被引
541
次
|
|
|
|
5.
吴青青. 复杂背景下的颜色分离背景差分目标检测方法.
兵工学报,2013,34(4):501-506
|
CSCD被引
6
次
|
|
|
|
6.
Krizhevsky A. Image Net classification with deep convolutional neural networks.
Proceedings of the 2012 Advances in Neural Information Processing Systems,2012:1097-1105
|
CSCD被引
15
次
|
|
|
|
7.
Deng J. Image Net: a large-scale hierarchical image database.
Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition,2009:248-255
|
CSCD被引
116
次
|
|
|
|
8.
Girshick R. Rich feature hierarchies for accurate object detection and semantic segmentation.
Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition,2014:580-587
|
CSCD被引
197
次
|
|
|
|
9.
Uijlings J R. Selective search for object recognition.
International Journal of Computer Vision,2013,104(2):154-171
|
CSCD被引
437
次
|
|
|
|
10.
Everingham M. The Pascal visual object classes (VOC) challenge.
International Journal of Computer Vision,2010,88(2):303-338
|
CSCD被引
753
次
|
|
|
|
11.
Girshick R. Fast R-CNN.
Proceedings of the IEEE 14th International Conference on Computer Vision,2015:1440-1448
|
CSCD被引
3
次
|
|
|
|
12.
Ren S Q. Faster R-CNN: towards real-time object detection with region proposal networks.
Proceedings of the 2015 Advances in Neural Information Processing Systems,2015:91-99
|
CSCD被引
2
次
|
|
|
|
13.
Lin T Y. Microsoft COCO: common objects in context.
Proceedings of the 13th European Conference on Computer Vision,2014:740-755
|
CSCD被引
173
次
|
|
|
|
14.
Zeiler M D. Visualizing and understanding convolutional neural networks.
Proceedings of the 13rd European Conference on Computer Vision,2014:818-833
|
CSCD被引
1
次
|
|
|
|
15.
Simonyan K.
Very deep convolutional networks for large-scale image recognition,2015
|
CSCD被引
568
次
|
|
|
|
16.
Redmon J.
You only look once: unified, real-time object detection,2016
|
CSCD被引
12
次
|
|
|
|
17.
Liu W.
SSD: single shot multi box detector,2016
|
CSCD被引
1
次
|
|
|
|
18.
Oquab M. Learning and transferring mid-level image representations using convolutional neural networks.
Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition,2014:1717-1724
|
CSCD被引
13
次
|
|
|
|
19.
石祥滨. 基于深度学习混合模型迁移学习的图像分类.
系统仿真学报,2016,28(1):167-174
|
CSCD被引
21
次
|
|
|
|
20.
Le Cun Y. Back propagation applied to hand written zip code recognition.
Neural Computation,1989,1(4):541-551
|
CSCD被引
536
次
|
|
|
|
|