One color contrast enhanced infrared and visible image fusion method
-
摘要: 针对红外与可见光彩色融合图像中目标与背景间的低对比度的问题,提出一种基于HSI空间颜色对比度增强的红外和可见光图像融合方法.首先对输入的可见光与红外图像进行直方图均衡和中值滤波加强处理,然后对加强的红外图像模糊阈值分割得到红外目标,最后把分割的红外目标图像和加强的可见光和红外图像在HSI空间的三通道线性融合和色彩传递,为了增强目标与背景间的颜色对比度,在色彩传递阶段, H通道的色彩传递方程中引入一个比例因子.实验结果表明：与其他算法相比,该方法得到的彩色融合图像热目标和低温物体与背景间的颜色对比度明显加强,同时背景的细节信息呈现白天类似的自然彩色,更加符合人眼视觉感知.Abstract: Focus on color fusion for infrared and visible images with low contrast between target and background issues, a contrast enhancement method for infrared and visible image was presented based on HSI color space. Firstly, the contrast of infrared and visible images was enhanced using local histogram equalization and median filter, then the infrared target was extracted from the enhanced infrared image after fuzzy threshold segmentation. Finally, the two enhanced images and the segmentation infrared target were fused into the three components of a HSI image in terms of a simple linear fusion strategy and color transfer. To enhance the color contrast between the target and the background, a scaling factor was introduced into the transferring equation in the H channel during color transfer process. The experimental results show that, compared with other algorithms, the color fusion images of hot target and color contrast between low temperature object and background abtained by the presented method enhance obviously. At the same time, the details of visible images are endowed with natural color similar to that of the light color images during the day, which is more confortable to the human's visual perception.
-
Key words:
- color contrast enhancement /
- image fusion /
- HSI space /
- color transfer
-
[1] Toet A. Applying daytime colors to multiband nightvision imagery[C]//SPIE, 2003: 168-178. [2] [3] Toet A. Natural color mapping for multiband nightvision imagery[J]. Information Fusion, 2003, 4(2): 155-166. [4] [5] [6] Wang L X, Shi S M, Jin W Q, et al, Color fusion algorithm for visible and infrared images based on color transfer in YUV color space[C]//SPIE, 2007: 1781-1787. [7] Zheng Y, Essock E A. A local-coloring method for night-vision colorization utilizing image analysis and fusion[J].Information Fusion, 2008, 9(2): 186-199. [8] [9] Yin S F, Cao L C, Ling Y S, et al. One contrast enhancement method for color night vision[J]. Infrared Physics Technology, 2010, 53(4): 146-150. [10] [11] [12] Qian X Y, Wang Y J, Wang B F. Effective contrast enhancement method for color night vision[J]. Infrared Physics and Technology, 2012, 55(1): 130-136. [13] Qian X Y, Wang Y J, Wang B F. Color contrast enhancement for color night vision based on color mapping[J]. Infrared Physics and Technology, 2013, 57(6): 36-41. [14] [15] Jiang Yiming, Wang Keyong. Infrared image segmentation algorithm of tank[J]. Infrared and Laser Engineering, 2007, 56(4): 1481-1485. (in Chinese) [16] [17] [18] Cheng Guo, Zuo Hongfu. The image adaptive thresholding by index of fuzziness[J]. Acta Automatic Sinica, 2003, 29(5): 386-390. (in Chinese) [19] [20] Jang J H, Ra J B. Psehdo-color image based on intensity-hue- saturation[C]//Proceedings of IEEE International Conference on Multisensor Fusion and Itegration for Intelligent Systems, 2008: 1066-1071. [21] Cheng Zhengyun, Wang Xia, Zou Xiaofeng, et al. Polarimetric and milti-spectral image fusion based on HIS color system and wavelet transform[J]. Acta Photonica Sinica, 2010, 39(1): 1710-1712. (in Chinese) -
点击查看大图
计量
- 文章访问数: 202
- HTML全文浏览量: 23
- PDF下载量: 318
- 被引次数: 0
下载:
