基于改进的局部反熵算子的小目标检测

doi:10.3969/j.issn.1000-436x.2013.04.007

Abstract

Abstract:

A small-target detection approach was proposed,which is based on the modified local reverse entropy operator and the improved region growing technology.The approa adopted the fact that the emergence of small target could lead to the large change of local reverse entropy.The proposed approach made use of the local reverse entropy map to suppress the small-target image background,and then adopted the improved region growing technique to effectively detect small targets.Experimental results show that the proposed approach can detect small targets accurately and quickly.

Key words: small target, local reverse entropy operator, background suppression, region growing, target segmentation

He DENG,Yan-tao WEI,Ming-wen TONG,Shao-cheng QU. Small target detection based on modified local reverse entropy operator[J]. Journal on Communications, 2013, 34(4): 60-69.

Figures/Tables 13

References 15

[1]	PORAT B , FRIENDLANDER B . A frequency domain algorithm for multi-frame detection and estimation of dim targets[J]. IEEE Transac-tions on Pattern Analysis and Machine Intelligence, 1990,12(4): 398-401.
[2]	BAI X Z , ZHOU F G . Analysis of new top-hat transformation and the application for infrared dim small target detection[J]. Pattern Recognition, 2010,43(6): 2145-2156.
[3]	POHLIG S C . Spatial-temporal detection of electro-optic moving targets[J]. IEEE Transactions on Aerospace and Electronic Systems, 1995,31(2): 608-616.
[4]	YANG L , YANG J , YANG K . Adaptive detection for infrared small target under sea-sky complex background[J]. Electronics Letters, 2004,40(17): 1083-1085.
[5]	王广君，田金文，柳健．基于局部熵的红外图像小目标检测[J]．红外与激光工程， 2000,29(4):26-29. WANG G J , TIAN J W , LIU J . Infrared small objects detection based on local entropy method[J]. Infrared and Laser Engineering, 2000,29(4):26-29.
[6]	DENG H , LIU J G , CHEN Z . Infrared small target detection based on modified local entropy and EMD[J]. Chinese Optics Letters, 2010,8(1): 24-28.
[7]	DENG H , LIU J G . Infrared small target detection based on the self-information map[J]. Infrared Physics ＆ Technology, 2011,54(2): 100-107.
[8]	HUANG K , MAO X . Detectability of infrared small targets[J]. Infrared Physics ＆ Technology, 2010,53(3): 208-217.
[9]	周冰，王永仲，孙立辉．图像局部熵用于小目标检测研究[J]．光子学报， 2008,37(2):381-387. ZHOU B , WANG Y Z , SUN L H . Study on local entropy used in small target detection[J]. Acta Photonica Sinica, 2008,37(2):381-387.
[10]	李欣，赵亦工，郭伟 . 基于复杂度的自适应门限弱小目标检测方法[J]．光子学报, 2009,38(8):2144-2149. LI X , ZHAO Y G , GUO W . Adaptive threshold detection method for dim and small target based on image complex degree[J]. Acta Photonica Sinica, 2009,38(8):2144-2149.
[11]	ZHANG Y J . A survey on evaluation methods for image segmentation[J]. Pattern Recognition, 1996,29(8): 1335-1346.
[12]	DENG H , LIU Q T , CHENG L F . Local reverse entropy and application in small targets detection[J]. Energy Procedia, 2011,13: 1956-1963.
[13]	王学伟，王春歆，张玉叶 . 点目标图像信噪比计算方法[J]．电光与控制， 2010,17(1):18-21. WANG X W , WANG C X , ZHANG Y Y . Research on SNR of point target image[J]. Electronics Optics ＆ Control, 2010,17(1):18-21.
[14]	NAKAGAWA Y , ROSENFELD A . Some experiments on variable thresholding[J]. Pattern Recognition, 1979,11(2): 191-204.
[15]	XU J , ZHANG J Q , LIANG C H . Prediction of the performa of an algorithm for the detection of small targets in infrared images[J]. Infrared Physics ＆ Technology, 2001,42(1): 17-22.

Metrics

Recommended 0

No Suggested Reading articles found!

图像	指标	方法
图像	指标	原始图像	MBPM	EMD	LREM	m LREM
图6 (a)	信噪比	2.941 7—	10.441 1	9.650 1	9.309 3	12.337 2
图6 (a)	信噪比增益	—	3.549 4	3.380 5	3.164 6	4.193 9
图6 (b)	信噪比	13.972 3	20.673 8	19.540 1	20.047 1	23.381 6
图6 (b)	信噪比增益	—	1.479 6	1.398 5	1.434 8	1.673 4
图6 (c)	信噪比	6.135 9—	21.929 4	20.120 1	22.425 9	24.595 4
图6 (c)	信噪比增益	—	3.573 9	3.279 1	3.654 9	4.008 4
图6 (d)	信噪比	8.468 0	18.732 3	17.499 8	20.762 3	22.164 1
图6 (d)	信噪比增益	—	2.212 1	2.066 6	2.451 9	2.617 4

IRGT分割过程所涉及的参数	图像
IRGT分割过程所涉及的参数	图6 (i)	图6 (j)	图6 (k)	图6 (l)
预分割阈值Th	0.005 0	0.010 0	0.005 0	0.001 0
权重系数？	0.050 0	0.200 0	0.200 0	0.200 0
种子点灰度均值μ	0.518 9	0.306 8	0.228 0	0.422 3
停止准则T	0.025 9	0.061 4	0.045 6	0.084 5

图像	方法
图像	Otsu方法	直方图方法	局部阈值方法	IRGT
图6 (i)	0.278 602	0.010 311	0.000 097	0.000 003
图6 (j)	0.533 272	0.027 882	0.000 579	0.000 191
图6 (k)	0.267 785	0.030 089	0.003 237	0.002 294
图6 (l)	0.338 961	0.017 296	0.000 793	0.000 438

Small target detection based on modified local reverse entropy operator

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 13

References 15

Related Articles 3

Metrics

Recommended 0

[1]	Fan GUO, Yongxiang ZHANG, Jin TANG, Weiqing LI. YOLOv3-A: a traffic sign detection network based on attention mechanism [J]. Journal on Communications, 2021, 42(1): 87-99.
[2]	. Small target detection based on modified local reverse entropy operator [J]. Journal on Communications, 2013, 34(4): 7-69.
[3]	Feng-chen HUANG,Min LI,Ai-ye SHI,Min TANG,Li-zhong XU. Insect visual system inspired small target detection for multi-spectral remotely sensed images [J]. Journal on Communications, 2011, 32(9): 88-95.