摘要
主要研究了红外图像中运动点目标的检测及跟踪问题。在复杂背景下,根据小目标在红外影像中容易丢失的特性,利用trous小波变换对图像非抽取(变换后图像数据未损失)的优点对红外图像进行了背景抑制与增强。通过聚类分割算法分割出了可疑目标,并采用八邻域分析算法准确跟踪并提取出了运动小目标。试验结果表明,本文算法在对红外序列图像中的运动目标进行检测与跟踪时具有较强的实用价值。
The detection and tracking of moving point targets in infrared images are studied mainly. Background suppression and enhancement are carried out for the infrared images with complex back- ground. These processing are implemented by utilizing the advantages of Atrous wavelet transform according to the feature that small targets are easy to be lose in infrared images. The possible targets are segmented by using a Fisher algorithm. Then, the small moving targets are tracked and extracted accurately by using an Eight Neighboring Region Analysis Algorithm （ENRAA）. The experimental result shows that the proposed algorithm is of important practical value to the detection and tracking of moving targets in infrared image sequences.
出处
《红外》
CAS
2015年第1期35-39,共5页
Infrared
关键词
ATrous小波变换
图像分割
红外运动目标
八邻域分析
目标检测和跟踪
Atrous wavelet transform
target enhancement
image segmentation
moving infraredtarget
eight neighboring region analysis
target detection and tracking
