|本期目录/Table of Contents|

[1]吴泽俊,赵彤洲*.基于区域显著性与稳定性的小目标检测方法[J].武汉工程大学学报,2020,42(03):332-337.[doi:10.19843/j.cnki.CN42-1779/TQ.201912016]
 WU Zejun,ZHAO Tongzhou*.Small Target Detection Method Based on Regional Stability and Saliency[J].Journal of Wuhan Institute of Technology,2020,42(03):332-337.[doi:10.19843/j.cnki.CN42-1779/TQ.201912016]
点击复制

基于区域显著性与稳定性的小目标检测方法(/HTML)
分享到:

《武汉工程大学学报》[ISSN:1674-2869/CN:42-1779/TQ]

卷:
42
期数:
2020年03期
页码:
332-337
栏目:
机电与信息工程
出版日期:
2023-03-14

文章信息/Info

Title:
Small Target Detection Method Based on Regional Stability and Saliency
文章编号:
1674 - 2869(2020)03 - 0332 - 06
作者:
吴泽俊赵彤洲*
武汉工程大学计算机科学与工程学院,湖北 武汉 430205
Author(s):
WU ZejunZHAO Tongzhou*
School of Computer Science & Technology, Wuhan Institute of Technology, Wuhan 430205, China
关键词:
小目标检测显著性特征稳定性特征
Keywords:
small target detection stability feature saliency feature
分类号:
TP391.4
DOI:
10.19843/j.cnki.CN42-1779/TQ.201912016
文献标志码:
A
摘要:
为解决彩色图像小目标检测中目标易丢失与虚警率高的问题,提出了一种基于区域显著性和稳定性标准增强的小目标检测方法( RSSEM )。首先,在区域稳定性特征提取阶段,针对滤波导致的边缘信息缺失问题,填充图像边界并采用多级阈值二值化图像,在聚类准则下二值图像进行区域聚类和二次后验,使本文方法对小目标有较高敏感度。其次,在区域显著性特征提取阶段,利用旋转对称高斯高通滤波对灰度图像进行滤波得到显著性特征图像。最后,融合稳定性特征与显著性特征,并对强噪声滤波后实现小目标检测。在RSS数据集上,与对照组相比,本文方法能显著降低小目标的丢失率和虚警率,比最先进的算法在精确度、召回率、F值上至少提高1%,表明RSSEM的有效性。
Abstract:
To solve the problems of target missing and high false alarm rate in the detection of small targets from color images, we proposed a small target detection method on the basis of regional saliency and stability enhancement metrics (RSSEM). First, aimed at the missing edge information caused by filter, the image boundaries were filled and image binarization was performed by multi-level thresholds at the stage of regional stability feature extraction. The detection of small target was improved as region clustering and secondary posterior were performed on the binary image. Second, the grayscale image was filtered with the rotational symmetric Gaussian high-pass filter to obtain the salient feature image at the stage of regional saliency feature extraction. Finally, the stability features and saliency features were merged, and small targets were detected after filtering strong noise. On the regional saliency and stability dataset, the rates of target missing and false alarm decrease significantly compared with the control group. The proposed method is at least 1% higher in accuracy, recall and F score in comparison with state-of-the-art methods, which indicates the effectiveness of RSSEM.

参考文献/References:

[1] HAN J, MA Y, ZHOU B, et al. A robust infrared small target detection algorithm based on human visual system[J]. IEEE Geoscience and Remote Sensing Letters,2014,11(12):2168-2172. [2] 宋康康,陈恳,郭运艳. 深度信息辅助的均值漂移目标跟踪算法[J]. 计算机工程与应用,2013,49(23):177-180. [3] 李宇杰,李煊鹏,张为公. 基于视觉的三维目标检测算法研究综述[J]. 计算机工程与应用,2020,56(1):11-24. [4] 刘阳,尚赵伟. 基于Kinect骨干信息的交通警察手势识别[J]. 计算机工程与应用,2015,51(3):157-161. [5] GAO C, WANG L, XIAO Y, et al. Infrared small-dim target detection based on Markov random field guided noise modeling[J]. Pattern Recognition,2018,1(76): 463-475. [6] NASIRI M, CHEHRESA S. Infrared small target enhancement based on variance difference [J]. Infrared Physics & Technology,2017,1(82):107-119. [7] LOU J, ZHU W, WANG H, et al. Small target detection combining regional stability and saliency in a color image[J]. Multimedia Tools and Applications,2017, 76(13):14781-14798. [8] MATAS J, CHUM O, URBAN M, et al. Robust wide- baseline stereo from maximally stable extremal regions[J]. Image and Vision Computing,2004,22(10): 761-767. [9] ACHANTA R, HEMAMI S S, ESTRADA F J, et al. Frequency-tuned salient region detection[C]// Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition. Miami:IEEE, 2009:1597-1604. [10] 肖永强,王海晖,刘奥丽,等. 双目实时目标三维测量实现方法的研究[J]. 武汉工程大学学报,2016,38(4): 386-393. [11] 王海涛,姜文东,程远,等. 两级上下文卷积网络宽视场图像小目标检测方法[J]. 计算机测量与控制,2019, 27(6):199-204. [12] 张思宇,张轶. 基于多尺度特征融合的小目标行人检 测[J]. 计算机工程与科学,2019,41(9):1627-1634. [13] 单义,杨金福,武随烁,等. 基于跳跃连接金字塔模型的小目标检测[J]. 智能系统学报,2019,10(30):1-7. [14] CHEN H, LEOU J. Multispectral and multiresolution image fusion using particle swarm optimization[J]. Multimedia Tools and Applications,2012,60(3):495- 518. [15] CHEN C, LI H, WEI Y, et al. A local contrast method for small infrared target detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014,52(1):574- 581.

相似文献/References:

备注/Memo

备注/Memo:
收稿日期:2019-12-17基金项目:国家自然科学基金(61573324);武汉研究院开放性课题(IWHS20192031);武汉工程大学第八届研究生教育创新基金(CX2018195)作者简介:吴泽俊,硕士研究生。E-mail:wzj199310@163.com*通讯作者:赵彤洲,博士,副教授。E-mail:zhao_tongzhou@126.com引文格式:吴泽俊,赵彤洲. 基于区域显著性与稳定性的小目标检测方法[J]. 武汉工程大学学报,2020,42(3):332-337.
更新日期/Last Update: 2020-07-09