Extraction of small target based on local extreme convergence

Wang Enguo; Gao Yinhan; Su Chengzhi; Liu Yanyan

Automatic detection of small targets in the complex context is still not perfect, an algorithm was proposed that used all paths converging to the same limit point to describe the small target area. The starting points of the path were screened based on the image gradient features. A path starting from the starting point along the gradient direction of steepest descent converged to a local minimum point, and all the paths that converge in the same path constituted an independent core region. The difference was analyzed in the target features between the focus independent core region and noise independent region, and the gray average ratio of the target features inside and outside was used for the independent core area filtering, the focus of the core area was obtained. The region of the target core was obtained by polymerizing the independent core region. The experiments show that the algorithm can automatically detect the focus target, and compared with existing algorithms, it increases the degree of automation of the small object extraction, have a strong robustness.

1. College of Instrumentation & Electrical Engineering,Jilin University,Changchun 130061,China;

2. Changchun University of Science and Technology,College of Mechanical and Electric Engineering of Changchum University of Science and Technolgoy,Changchun 130022,China

Received Date: 2013-08-10

Rev Recd Date: 2013-09-25

Publish Date: 2014-04-25

Key words:

Abstract: Automatic detection of small targets in the complex context is still not perfect, an algorithm was proposed that used all paths converging to the same limit point to describe the small target area. The starting points of the path were screened based on the image gradient features. A path starting from the starting point along the gradient direction of steepest descent converged to a local minimum point, and all the paths that converge in the same path constituted an independent core region. The difference was analyzed in the target features between the focus independent core region and noise independent region, and the gray average ratio of the target features inside and outside was used for the independent core area filtering, the focus of the core area was obtained. The region of the target core was obtained by polymerizing the independent core region. The experiments show that the algorithm can automatically detect the focus target, and compared with existing algorithms, it increases the degree of automation of the small object extraction, have a strong robustness.

HTML

Reference (15)

[1]	Wu Yiquan, Shen Yi, Gang Tie, et al. Thresholding for small target image based on2-D symmetric Tsallis cross entropy[J]. Chinese Journal of Scientific Instrument, 2011, 32(10): 2163-2167.(in Chinese) 吴一全, 沈毅, 刚铁, 等. 基于二维对称Tsallis 交叉熵的小目标图像阈值分割[J]. 仪器仪表学报, 2011, 32 (10): 2163-2167.
[2]
[3]	Yang Chunling, Wang Jianlai, Wang Changhui. Small target identification method based on the infrared multi-spectral image [J]. Infrared and Laser Engineering, 2010, 39 (4): 772-776. (in Chinese) 杨春玲, 王暕来, 王昶辉. 红外多谱段小目标识别方法[J]. 红外与激光工程, 2010, 39(4): 772-776.
[4]
[5]
[6]	Wu Yiquan, Wu Jiaming, Zhan Bichao. An effective method of threshold selection for small object image [J]. Acta Armamentarii, 2011, 32(4): 469-475. (in Chinese) 吴一全, 吴加明, 占必超. 一种可有效分割小目标图像的阈值选取方法[J]. 兵工学报, 2011, 32(4): 469-475.
[7]	Xu Qinghan, Jin Lizuo, Fei Shumin. Small infrared target detection via supervised feature learning [J]. Journal of Southeast University (Natural Science Edition), 2011, 41(5): 1008-1012. (in Chinese) 许庆晗, 金立左, 费树岷. 采用监督特征学习的红外小目标检测[J]. 东南大学学报( 自然科学版), 2011, 41 (5): 1008-1012.
[8]
[9]	Wei Changan, Jiang Shouda. Infrared small target detection algorithm based on morphological reconstruction operator and tracking [J]. Acta Electronica Sinica, 2009, (4): 850-853. (in Chinese) 魏长安, 姜守达. 基于形态重构与跟踪的红外小目标检测算法[J]. 电子学报, 2009, (4): 850-853.
[10]
[11]	Wu Yiquan, Ji Shouxin, Yin Danyan. Infrared small target detection based on dual-tree complexwavelet transform and independent component analysis [J]. Acta Armamentarii, 2010, 31(11): 1431-1437. (in Chinese) 吴一全, 纪守新, 尹丹艳. 双树复小波和独立分量分析的红外小目标检测[J]. 兵工学报, 2010, 31(11): 1431-1437.
[12]
[13]	Liu Jin, Ji Hongbing. Detection method for small targets in the IR image based on the variable weighted pipeline filter[J]. Journal of Xidian University, 2007, 34(5): 743-747. (in Chinese) 刘靳, 姬红兵. 基于移动式加权管道滤波的红外弱小目标检测[J]. 西安电子科技大学学报, 2007, 34(5): 743-747.
[14]
[15]	Han Yusheng, Yuan Guanglin, Li Congya, et al. Design and implement of pipeline filter algorithm based on across linker[J]. Infrared and Laser Engineering, 2006, 35: 202-206. (in Chinese) 韩裕生, 衰广林, 李从牙, 等. 基于十字链表的管道滤波算法设计与实现[J]. 红外与激光工程, 2006, 35: 202-206.

Extraction of small target based on local extreme convergence

Abstract

References

Proportional views

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Related

Proportional views