从移动背景红外序列图像中检测运动目标
Detecting Moving Objects from Infrared Image Sequence on Displacing Background
-
摘要: 该文提出了一种从背景移动红外图像中自动检测运动目标的算法。该算法首先采用图像灰度互相关度量的匹配算法对连续的6帧序列进行配准,用第1帧和第4帧配准,第2帧和第5帧配准,第3帧和第6帧配准,然后用配准后的图像对分别做差分运算,再将3个差分图像按像素相乘,在运动目标处得到了非常尖锐的相关峰。这为进一步自动跟踪目标提供了一个跟踪窗口的中心点。实验结果验证了该方法的有效性。Abstract: An approach to detecting moving objects from infrared image sequence on displacing background is proposed in this paper. First the correlation matching technique is used for registering five pictures with the sixth one. Then the registered images are processed to calculate the image differences between the first and fourth, the second and fifth, the third and sixth. After these difference images are multiplied, a very high correlation peak is obtained. Using this method a central point for tracking window can be provided. The experimental results illustrate that this approach is available to this situation.
-
Milan Sonka, Vaclav Hlavac, Roger Boyle. Image Processing,Analysis, and Machine Vision[M]. A Division of Thomson Asia Pte Led, USA, 1999:679-721.[2]Horn B K P, Schunck B G. Determining optical flow[J].Artificial Intelligence.1981, 17 (1-3):185-204[3]Heiz F, Bouthemy P. Multimodal estimation of discontinuous optical flow using Markov random fields [J].IEEE Trans. on Pattern Analysis and Machine Intelligence.1993, 15(12):1217-1232[4]Sayrol E, Gasull A. Motion estimation using higher order statistics [J].IEEE Trans. on Image Processing.1996, 5(6):1077-1083[5]GonzalezRC,WoodsRE著,阮秋琦,阮宇智译.数字图像处理(第二版)[M].北京:电子工业出版社,2003:507-514.[6]Dubuisson M P, Jain A K. Contour extraction of moving objects in complex outdoor scenes [J].International Journal of Computer Vision.1995, 14(1):83-105
计量
- 文章访问数: 2369
- HTML全文浏览量: 88
- PDF下载量: 743
- 被引次数: 0