Improvement to projection detection of slowly moving point target in infrared image sequences

被引：0

作者：

Chen, Fei ^{[1
]}

Jing, Zhong-Liang ^{[1
]}

Li, Jian-Xun ^{[1
]}

机构：

[1] Inst. of Aerosp. Info. and Control, Sch. of Electron. and Info. Technol., Shanghai Jiaotong Univ., Shanghai 200030, China

来源：

Hongwai Yu Haomibo Xuebao/Journal of Infrared and Millimeter Waves | 2003年 / 22卷 / 02期

关键词：

Automatic target recognition - Color image processing - Signal to noise ratio;

D O I：

暂无

中图分类号：

学科分类号：

摘要：

The infrared image background is obtained by morphological filtering, and the infrared images are normalized using the estimated noise mean and variance in a local window. Composite frame is formed by normalized image data, and target detection is performed on the composite frame. Thus, target and noise statistics in a composite frame are obtained. Considering the different distribution of noise and target intensity, the projection algorithm is further modified to improve its signal-to-noise ratio. Simulation of real infrared images proved that the modified projection algorithm can successfully detect targets with SNR equaling 2.

引用

页码：96 / 100