地标
稳健性(进化)
人工智能
计算机视觉
计算机科学
职位(财务)
图像匹配
翻译(生物学)
模式识别(心理学)
图像配准
转化(遗传学)
图像(数学)
信使核糖核酸
经济
化学
基因
生物化学
财务
作者
Hu Zhu,Lizhen Deng,Gang Zhou,Xiaodong Bai,Gaihua Wang
出处
期刊:International Conference on Audio, Language and Image Processing
[Institute of Electrical and Electronics Engineers]
日期:2012-07-01
卷期号:: 898-902
被引量:6
标识
DOI:10.1109/icalip.2012.6376741
摘要
Automatic ground target recognition technology in downward-looking infrared imagery is challenging problems due to the complexity of real-world. A robust ground target recognition method is proposed for downward-looking infrared (DLIR) image sequences in this paper. A complete model of the proposed method is designed firstly and the principles of some key technologies are introduced as following. Perspective transformation is used to solve the projective problems of landmark translation, rotation and scale variance in real-time image sequence. The size of landmark is estimated real-timely by using flight parameters and imaging parameters for getting the model with an appropriate scale. Based on the matching results of landmark and flight parameters, target position technology is proposed to identify the position of target by using the position relation between landmark and target. Experimental results using real-world image data with complicated background showed that the proposed method not only causes high precisely locating results, but also has good robustness for target occlusion.
科研通智能强力驱动
Strongly Powered by AbleSci AI