图像自寻的弹药目标检测方法综述
Review on Target Detection of Image Homing Ammunition
查看参考文献80篇
|
文摘
|
弹载图像目标检测方法是实现图像自寻的弹药“发射后不管”、对目标进行自主打击的关键技术。弹药图像自寻的面临着成像环境恶劣,目标特性变化快,对算法体积、速度要求苛刻等问题。围绕弹载目标检测难点问题进行综述,将基于深度学习的目标检测方法区分为基于候选框、无候选框和基于transformer的方法,回顾了各类方法主要研究进展;对特征提取网络轻量化、预测特征图增强、非极大值抑制后处理算法、训练中样本均衡、模型压缩等弹载图像目标检测模型部署中的关键技术进行了梳理;对比了典型目标检测方法在ImageNet、COCO及弹载图像目标数据集上的性能,并对未来发展进行展望。 |
|
其他语种文摘
|
The onboard image target detection method is the key technology to realize the autonomous attack on the target by the “fire-and-forget” image homing ammunition. At present, the image homing of ammunition is faced with some problems, such as bad imaging environment, rapid change of targets' characteristics, and strict requirements for algorithm volume and speed. Firstly, the target detection methods based on deep learning are divided into methods based on anchor box, methods without anchor box and methods based on transformer, and the main technical progress of various methods is reviewed. Then, the key technologies in onboard image target detection model deployment, such as lightweight feature extraction network, enhancement of feature map for prediction, non-maximum suppression postprocessing algorithm, sample equalization in training, and model compression, are studied. Finally, the performances of the typical detection algorithms on ImageNet, COCO and datasets for onboard image are compared, and the possible development in the future is looked into. |
|
来源
|
兵工学报
,2022,43(10):2687-2704 【核心库】
|
|
DOI
|
10.12382/bgxb.2021.0610
|
|
关键词
|
弹载图像
;
目标检测
;
深度学习
;
模型部署
|
|
地址
|
陆军炮兵防空兵学院高过载弹药制导控制与信息感知实验室, 安徽, 合肥, 230031
|
|
语种
|
中文 |
|
文献类型
|
综述型 |
|
ISSN
|
1000-1093 |
|
学科
|
一般工业技术 |
|
基金
|
军队型号项目
|
|
文献收藏号
|
CSCD:7331159
|
参考文献 共
80
共4页
|
|
1.
钱立志.
电视末制导炮弹武器系统关键技术研究,2006:2-6
|
CSCD被引
6
次
|
|
|
|
|
2.
文苏丽. DARPA导引头成本转换项目分析.
战术导弹技术,2016(2):5-9
|
CSCD被引
1
次
|
|
|
|
|
3.
Girshick R. Rich feature hierarchies for accurate object detection and semantic segmentation.
Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2014:580-587
|
CSCD被引
95
次
|
|
|
|
|
4.
Felzenszwalb P F. Object detection with discriminatively trained part-based models.
IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(9):1627-1645
|
CSCD被引
541
次
|
|
|
|
|
5.
徐英. 面向合成孔径雷达图像任意方向舰船检测的改进YOLOv3模型.
兵工学报,2021,42(8):1698-1707
|
CSCD被引
6
次
|
|
|
|
|
6.
杨传栋. 基于CNN的弹载图像目标检测方法研究.
战术导弹技术,2019(4):85-92
|
CSCD被引
3
次
|
|
|
|
|
7.
雷鸣. 基于模型压缩YOLOv4的弹载图像舰船目标实时检测.
兵器装备工程学报,2021,42(9):225-230
|
CSCD被引
1
次
|
|
|
|
|
8.
陈栋. 面向深度学习的弹载图像处理异构加速现状分析.
航空兵器,2021,28(3):10-17
|
CSCD被引
3
次
|
|
|
|
|
9.
侯凯强. 弹载人工智能目标识别算法的嵌入式实现方法研究.
制导与引信,2019,40(3):40-45
|
CSCD被引
2
次
|
|
|
|
|
10.
钱立志. 一种弹载视频图像实时消旋方法.
弹箭与制导学报,2009,29(3):26-28
|
CSCD被引
1
次
|
|
|
|
|
11.
Ren S. Faster R-CNN: towards real-time object detection with region proposal networks.
IEEE Transactions on Pattern Analysis & Machine Intelligence,2015,39(6):1137-1149
|
CSCD被引
4394
次
|
|
|
|
|
12.
Liu W. SSD: single shot multibox detector.
Proceedings of the 14th European Conference on Computer Vision,2016:21-37
|
CSCD被引
333
次
|
|
|
|
|
13.
Redmon J. YOLO9000: better, faster, stronger.
Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2017:6517-6525
|
CSCD被引
50
次
|
|
|
|
|
14.
Redmon J.
Yolov3: an incremental improvement,2018
|
CSCD被引
699
次
|
|
|
|
|
15.
Bochkovskiy A.
YOLOv4: optimal speed and accuracy of object detection,2020
|
CSCD被引
430
次
|
|
|
|
|
16.
Liu S. Path aggregation network for instance segmentation.
Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2018:8759-8768
|
CSCD被引
5
次
|
|
|
|
|
17.
Lin T Y. Focal loss for dense object detection.
IEEE Transactions on Pattern Analysis & Machine Intelligence,2017,99:2999-3007
|
CSCD被引
100
次
|
|
|
|
|
18.
Redmon J. You only look once:unified, real-time object detection.
Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2016:779-788
|
CSCD被引
107
次
|
|
|
|
|
19.
Huang L.
DenseBox: unifying landmark localization with end to end object detection,2015
|
CSCD被引
4
次
|
|
|
|
|
20.
Tian Z.
FCOS: fully convolutional one-stage object detection,2018
|
CSCD被引
1
次
|
|
|
|
|
了解气象卫星更多信息，请访问