潜在低秩表示框架下基于卷积神经网络结合引导滤波的红外与可见光图像融合

为提高融合图像的可视性,解决传统红外与可见光图像融合算法中存在的边缘特征缺失、细节模糊的问题,提出了一种潜在低秩表示框架下基于卷积神经网络结合引导滤波的红外与可见光图像融合算法。该算法首先利用潜在低秩表示对源图像进行分解,得到源图像的低秩分量和显著分量。其次,利用卷积神经网络根据源图像的特征信息,得到权值图。再次,通过引导滤波算法对权值图进行边缘锐化,然后再将优化后的权值图分别与源图像的低秩分量和显著分量融合,得到融合图像的低秩分量和显著分量。最后,将融合图像的低秩分量和显著分量叠加,得到最终的融合图像。实验结果表明,该算法在主观评价和客观指标上均优于传统的红外与可见光图像融合算法。     

Two-scale image fusion of visible and infrared images using saliency detection

Military, navigation and concealed weapon detection need different imaging modalities such as visible and infrared to monitor a targeted scene. These modalities provide complementary information. For better situation awareness, complementary information of these images has to be integrated into a single image. Image fusion is the process of integrating complementary source information into a composite image. In this paper, we propose a new image fusion method based on saliency detection and two-scale image decomposition. This method is beneficial because the visual saliency extraction process introduced in this paper can highlight the saliency information of source images very well. A new weight map construction process based on visual saliency is proposed. This process is able to integrate the visually significant information of source images into the fused image. In contrast to most of the multi-scale image fusion techniques, proposed technique uses only two-scale image decomposition. So it is fast and efficient. Our method is tested on several image pairs and is evaluated qualitatively by visual inspection and quantitatively using objective fusion metrics. Outcomes of the proposed method are compared with the state-of-art multi-scale fusion techniques. Results reveal that the proposed method performance is comparable or superior to the existing methods.     

Fusion for visible and infrared images using visual weight analysis and bilateral filter-based multi scale decomposition

Fusion for visible and infrared images has been an important and challenging work in image analysis. Both the feature information in infrared image and abundant detail information in visible image should be preserved and enhanced in fused result. In this paper, a detail enhanced fusion algorithm through visual weight analysis based on smooth-inspired multi scale decomposition is proposed. With variable parameter, bilateral filter-based idea successfully decomposes the two source image into several scales. At each scale level, visual weight map is calculated and used for fusion. Finally, those levels are synthetized with proper weights. Using this idea, the detail information could be enhanced easily. The experimental results demonstrate the proposed approach performs better than other methods, especially in visual effect and keeping details.     

Multi-window visual saliency extraction for fusion of visible and infrared images

Fusion for visible and infrared images aims to combine the source images of the same scene into a single image with more feature information and better visual performance. In this paper, the authors propose a fusion method based on multi-window visual saliency extraction for visible and infrared images. To extract feature information from infrared and visible images, we design local-window-based frequency-tuned method. With this idea, visual saliency maps are calculated for variable feature information under different local window. These maps show the weights of people’s attention upon images for each pixel and region. Enhanced fusion is done using simple weight combination way. Compared with the classical and state-of-the-art approaches, the experimental results demonstrate the proposed approach runs efficiently and performs better than other methods, especially in visual performance and details enhancement.     

Infrared and visible image fusion method based on saliency detection in sparse domain

Infrared and visible image fusion is a key problem in the field of multi-sensor image fusion. To better preserve the significant information of the infrared and visible images in the final fused image, the saliency maps of the source images is introduced into the fusion procedure. Firstly, under the framework of the joint sparse representation (JSR) model, the global and local saliency maps of the source images are obtained based on sparse coefficients. Then, a saliency detection model is proposed, which combines the global and local saliency maps to generate an integrated saliency map. Finally, a weighted fusion algorithm based on the integrated saliency map is developed to achieve the fusion progress. The experimental results show that our method is superior to the state-of-the-art methods in terms of several universal quality evaluation indexes, as well as in the visual quality.     

基于潜在低秩表示与复合滤波的红外与弱可见光增强图像融合方法

针对传统红外与弱可见光图像融合算法中存在的亮度与对比度低、细节轮廓信息缺失、可视性差等问题,提出一种基于潜在低秩表示与复合滤波的红外与弱可见光增强图像融合方法.该方法首先利用改进的高动态范围压缩增强方法增强可见光图像提高亮度;然后利用基于潜在低秩表示与复合滤波的分解方法分别对红外与增强后的弱可见光图像进行分解,得到相应的低频和高频层;再分别使用改进的对比度增强视觉显著图融合方法与改进的加权最小二乘优化融合方法对得到的低频和高频层进行融合;最后将得到的低频和高频融合层进行线性叠加得到最终的融合图像.与其他方法的对比实验结果表明,用该方法得到的融合图像细节信息丰富,清晰度高,具有良好的可视性.     

红外和彩色可见光图像亮度-对比度传递融合算法

以红外和彩色可见光图像为研究对象,提出了一种基于亮度-对比度传递（LCT）技术的彩色图像融合算法。首先借助灰度融合方法将红外图像与彩色可见光图像亮度分量融合,然后用LCT技术改善灰度融合结果的亮度和对比度,最后利用快速YCBCR变换融合策略在RGB空间内直接生成彩色融合图像。文中利用像素平均融合法和多分辨率融合法作为不同的灰度融合措施以分别满足高实时性和高融合质量的需求。实验结果表明,提出算法的融合结果不仅具有与输入彩色可见光图像相近的自然色彩,而且具备令人满意的亮度和对比度,即使采用运算简单的像素平均法进行灰度融合,同样可以获得良好的融合效果。     

一种基于NSCT变换的红外与可见光图像融合算法

针对红外与可见光图像融合,提出了一种基于NSCT变换的图像融合方法。对经NSCT变换的低频子带系数采用基于区域能量自适应加权的融合规则,对高频子带系数采用混合的融合方法,即对于低层,采用基于区域方差选大的融合方法,对于高层采用像素点的绝对值选大的融合方法。实验结果表明,该融合算法可以获得更多的细节信息,能获得较理想的融合图像。     

Image fusion algorithm based on redundant-lifting NSWMDA and adaptive PCNN

Pyramid decomposition in the NSCT transformation is a band-pass filtering process in the frequency domain where different scales of images are orthogonal. However, from the perspective of the image content, correlation is likely to exist between the fused images, and this kind of decomposition makes images of different scales contain redundant information, as a result of which the fused image may not capture the subtle information from the original images. In order to overcome the above-mentioned problem, an effective image fusion method based on redundant-lifting non-separable wavelet multi-directional analysis (NSWMDA) and adaptive pulse coupled neural network (PCNN) has been proposed. The original images are firstly decomposed by using the NSWMDA into several sub-bands in order to retain texture detail and contrast information of the images, and then adaptive PCNN algorithm is applied on the high-frequency directional sub-bands to extract the high-frequency information. The low-frequency sub-bands are evaluated by weighted average based on Gaussian kernel with a chosen maximum fusion rule. Results from experiments show that the proposed method can make the fused image maintains more texture details and contrast information.     

一种基于区域特性的红外与可见光图像融合算法

提出了一种基于区域分割和à trous小波变换的红外与可见光图像融合算法.首先,对红外与可见光图像进行区域分割及区域关联,并按关联映射图所划分区域提取红外与可见光图像的的能量信息及梯度信息;然后,对红外与可见光图像进行多尺度à trous小波变换分解,分解后的低频部分按照文中所提出的区域能量比和区域清晰比指标进行区域融合,高频部分采用绝对值取大算子进行融合;最后进行重构得到融合图像.结果表明,该算法既可保持可见光图像的光谱信息,又可有效获取红外图像的热目标信息.     

基于多任务卷积神经网络的红外与可见光多分辨率图像融合

红外与可见光图像融合一直是图像领域研究的热点,融合技术能弥补单一传感器的不足,为图像理解与分析提供良好的成像基础。因生产工艺以及成本的限制,红外探测器的分辨率远低于可见光探测器,并在一定程度上因源图像分辨率的差异阻碍了实际应用。针对红外与可见光图像分辨率不一致的问题,提出了用于红外图像超分辨率重建与融合的多任务卷积网络框架,应用于多分辨率图像融合。在网络结构方面,首先设计了双通道网络分别提取红外与可见光特征,使算法不受源图像分辨率的限制;其次提出了特征上采样模块,先用双线性插值方法增加像素个数,再通过多层感知器精细化拟合像素平滑空间与高频空间的映射关系,无需重新训练模型即可实现任意尺度的红外图像上采样;接着将线性注意力引入网络,学习特征空间位置间的非线性关系,抑制无关信息并增强网络对全局信息的表达。在损失函数方面,提出了梯度损失,保留红外与可见光图像中绝对值较大的滤波器响应值,并计算该值与重建的融合图像响应值的Frobenius范数,无需理想的融合图像作为真值监督网络学习就能生成融合图像;此外,在梯度损失、像素损失的共同作用下对多任务模型进行优化,可以同时重建融合图像和高分辨率红外图像...     

Fusion method of infrared and visible images based on neighborhood characteristic and regionalization in NSCT domain

On fusing infrared and visible image, the traditional fusion method cannot get the better image quality. Based on neighborhood characteristic and regionalization in NSCT (Nonsubsampled Contourlet Transform) domain, the fusion algorithm was proposed. Firstly, NSCT was adopted to decompose infrared and visible images at different scales and directions for the low and high frequency coefficients, the low frequency coefficients which were fused with improving regional weighted fusion method based on neighborhood energy, and the high-frequency coefficients were fused with multi-judgment rule based on neighborhood characteristic regional process. Finally, the coefficients were reconstructed to obtain the fused image. The experimental results show that, compared with the other three related methods, the proposed method can get the biggest value of IE (information entropy), MI(VI,F) (mutual information from visible image), MI(VI,F) (mutual information from infrared image), MI (sum of mutual information), and Q^AB/F (edge retention). The proposed method can leave enough information in the original images and its details, and the fused images have better visual effects.     

A fusion algorithm for infrared and visible images based on RDU-PCNN and ICA-bases in NSST domain

The aim of infrared and visible image fusion is to enhance the feature in infrared image and preserve abundant detail information in visible image. Based on the fact that the human sense system accepts external stimulation only when the stimulus intensity is greater than a certain value and the reaction of neuronal cells have obvious regional characters, an image fusion algorithm based on region dual-channel unit-linking pulse coupled neural networks (RDU-PCNN) and independent component analysis (ICA) bases in non-subsampled shearlet transform (NSST) domain for infrared and visible images is proposed. RDU-PCNN we constructed has obvious regional characters and much lower computational costs. We trained ICA-bases using a number of images that the content and statistical properties are similar with the fusion images but applied it as low-frequency ICA-bases, which can reduce calculation complexity. Experimental results demonstrate that the proposed method can significantly improved the fusion quality and need less computational costs.     

基于小波包变换的红外与可见光图像融合

针对红外与可见光图像特点,提出一种基于小波包变换的融合算法。该算法先对源图像进行小波包分解,得到低频分量和各带通方向子带分量,并对不同分量采用不同的融合规则进行融合处理,得到各融合系数,然后经小波包重构获得融合图像。该方法可提取源图像细节信息,取得较好的融合效果。     

基于区域分割和Counterlet变换的图像融合算法

提出了一种基于区域分割和Contourlet变换的图像融合算法。首先,对各源图像做区域分割,并利用区域能量比和区域清晰比的概念来度量和提取区域信息;然后,对各源图像进行多尺度非子采样Contourlet分解,分解后的高频部分采用绝对值取大算子进行融合,低频部分则采用基于区域的融合规则和算子进行融合;最后进行重构得到融合图像。对红外与可见光图像进行了融合实验,并与基于像素的àtrous小波变换和Contourlet变换的融合效果进行了比较。结果表明,采用本文算法的融合图像既保留了可见光图像的光谱信息,又继承了红外图像的目标信息,其熵值高于基于像素的融合方法约10%,交叉熵仅为基于像素的融合方法的1%左右。     

基于伪维格纳分布的图像融合

提出了一种基于伪维格纳分布(PWVD)的融合方法.利用一维N像素的滑动窗口在各个方向上对各待融合图像进行伪维格纳变换,选择均方根最大的方向为各待融合网像的PWVD分解方向,分解形成待融合图像不同频段的能量谱图,然后,针对各待融合不同频段的能量谱图,融合原则足高频段取区域能量最大,低频段取能量方差最大,形成具有不同频段的融合能量谱网,最后,对能量谱网进行PWVD逆变换,形成融合图像.对红外与可见光图像、多聚焦图像、电子计算机X射线断层扫描(CT)图像与磁共振(MR)图像和红外与合成孔径雷达(SAR)图像进行了融合实验,并对融合图像和待融合图像进行了信息熵对比.实验结果表明,采用本文算法的融合图像保留了待融合图像的绝大部分信息.     

基于区域检测与非下采样轮廓波变换的红外与彩色可见光图像融合

针对灰度图像融合的分辨率低及现有的彩色图像融合方法融合的图像色彩不自然、不符合人的视觉感受的特点,在此提出一种基于Snake模型的区域检测和非下采样轮廓波变换(NSCT)的红外与彩色可见光图像融合的方法。首先对彩色可见光图像进行亮度、色度和饱和度(IHS)颜色空间变换提取亮度分量,并用Snake模型对红外图像的目标区域进行检测;然后对亮度分量和目标替换的红外图像应用NSCT分解,对所得到的高频系数采用像素点"绝对值和取大"、低频系数采用基于"亮度重映射技术"的加权融合规则进行融合;通过对融合系数进行NSCT逆变换获得融合图像的亮度分量,最后运用颜色空间逆变换得到融合图像。实验结果表明,所提出的融合方法既能保持可见光图像的高分辨率和自然色彩,又能准确保留红外图像中检测出的目标信息,获得视觉效果较好、综合指标较优的融合图像。     

具有紧支撑正交非张量积小波的图像融合

提出了基于一种新的小波——具有紧支撑、正交性、伸缩矩阵为[^2 0 ^0 2]的非张量积小波的图像融合方法。首先根据非张量积小波理论,利用Daubechies构造的单变量滤波器构造出基于四通道的不可分的小波滤波器组,用此滤波器组对参加融合的图像进行分解,然后对低频部分采用取均值、高频部分采用系数绝对值取大的融合算法对分解子图进行融合,最后重构。并采用熵、交叉熵、互信息、均方根误差和峰值信噪比等指标对该方法进行了客观评价。对可见光图像与红外图像、远红外图像与近红外图像、遥感图像、多聚焦图像和其它多类图像的融合实验结果证明本方法有较好的融合效果,其融合性能与采用同样融合算法的张量积db2小波的融合方法的融合性能相当。     

Infrared and visible image fusion based on visual saliency map and weighted least square optimization

The goal of infrared (IR) and visible image fusion is to produce a more informative image for human observation or some other computer vision tasks. In this paper, we propose a novel multi-scale fusion method based on visual saliency map (VSM) and weighted least square (WLS) optimization, aiming to overcome some common deficiencies of conventional methods. Firstly, we introduce a multi-scale decomposition (MSD) using the rolling guidance filter (RGF) and Gaussian filter to decompose input images into base and detail layers. Compared with conventional MSDs, this MSD can achieve the unique property of preserving the information of specific scales and reducing halos near edges. Secondly, we argue that the base layers obtained by most MSDs would contain a certain amount of residual low-frequency information, which is important for controlling the contrast and overall visual appearance of the fused image, and the conventional “averaging” fusion scheme is unable to achieve desired effects. To address this problem, an improved VSM-based technique is proposed to fuse the base layers. Lastly, a novel WLS optimization scheme is proposed to fuse the detail layers. This optimization aims to transfer more visual details and less irrelevant IR details or noise into the fused image. As a result, the fused image details would appear more naturally and be suitable for human visual perception. Experimental results demonstrate that our method can achieve a superior performance compared with other fusion methods in both subjective and objective assessments.     

基于伪魏格纳分布分解的合成孔径雷达图像目标与阴影分割

在二维魏格纳分布的框架内,针对魏格纳变换的交叉项问题和计算量大的问题,提出了合成孔径雷达图像局部伪魏格纳变换的目标和目标阴影的分割方法.首先,将合成孔径雷达图像进行二维伪魏格纳变换,得到各像素点的二维能量谱图|然后提取各像素点的二维能量谱图对应位置值形成多个不同频段的与原图像同大小的能量谱图|最后,对不同频段的能量谱图采用不同的处理方法后,将各能量谱图相加处理后形成区域标识图像,最终得到原图像的目标和目标阴影分割图像.本文利用该方法对MSTAR切片图像进行了分割试验,并对分割图像与频谱最大值距离或方位分割算法和基于双参量CFAR与隐马尔科夫联合分割算法进行了分割图像对比度对比.实验结果表明,采用本文算法的合成孔径雷达分割图像,对比度明显提高,且保留了目标图像细节.