基于轮廓特征的红外与可见光图像配准方法研究

红外光与可见光处于不同波段,其图像间的相关性较小.传统的基于特征的图像配准方法(如利用角点、边缘点等),在特征点选择时容易造成误匹配,这是由于有时特征点间的距离比较近造成的.针对此问题,本文提出了一种基于图像轮廓特征的红外与可见光图像配准方法.首先通过设置目标过滤器来提取明显的轮廓,再利用部分Hausdorff距离对轮廓进行匹配,计算出匹配轮廓对的面积和质心,并以此作为配准依据来对两种不同的图像进行配准.然后通过实验证明该方法的配准精度更高且克服了特征点误匹配的难点,这就可以解决刚性变换中红外与可见光图像间的配准问题.     

改进配准测度的SUFT红外图像快速配准算法

为方便电路板卡故障诊断,实现红外图像快速、有效配准,提出一种基于SUFT(Speeded-Up Robust Features)和相似四边形的红外图像快速配准算法。该算法首先对红外图像进行特征点检测,生成SUFT特征点描述子;然后采用欧氏距离进行相似性度量,提取粗匹配特征点对,再利用相似四边形进行精匹配,去除误配准点对;最后依据精匹配点对求解变换模型参数,实现红外图像的配准。实验表明,改进后的算法能有效剔除误匹配点对,提高配准精度,配准结果较理想,与同类算法相比耗时较短。因此该算法具有快速性、稳定性等优点,且配准精度较高,有很好的实用价值。     

基于角点和Hu矩不变量的可见光和红外图像自动配准方法

针对红外图像与可见光图像的自动配准问题,提出了一种基于图像角点特征和透视变换模型的方法.首先采用自适应阈值对红外与可见光图像进行分割,然后利用Harris因子分别在分割后的红外和可见光图像上检测角点.通过分析角点邻域在原始图像上的相关性实现角点的粗匹配.接着通过RANSAC算法对角点进行细匹配,删除outliers,再...     

基于多尺度红外与可见光图像配准研究

利用尺度空间理论对多分辨率的红外与可见光图像配准算法进行研究,提出利用红外与可见光图像的多尺度特征点及边缘作为配准的特征,利用特征尺度确定用于相似度匹配的子图像大小,使用LTS-Hausdorff(least trimmed square Hausdorff)距离判断子图像的相似性。利用尺度空间理论及多尺度下图像的特征能更加全面的对图像进行描述。在利用多尺度特征获取到匹配对后,再利用随机一致性检测对匹配对进行提纯并获取空间变换的参数,然后使用该参数对红外与可见光图像进行配准与融合。实验结果表明,基于多尺度的图像配准方法,能有效对红外与可见光图像进行配准。     

基于斜率一致性的电气设备红外与可见光图像配准方法

针对电气设备同一场景间红外与可见光图像间难以 匹配的问题,提出了一种基于斜率一致性的图像配准方法。首先通 过基于多方向结构元素、不同权值的数学形态学边缘检测算法分别提取红外与可见光图像的 边缘,得到粗边缘图像; 然后通过SURF算法检测两幅边缘图像的特征点,根据正确的匹配点对之间斜率一致性的先 验知识,进行特征点匹配; 最后通过最小二乘法求得仿射变换模型参数实现两幅图像的配准。实验结果表明,本文方法 有效提高了匹配点对的正 确率,特征点的定位也更加精确,能够对电气设备红外和可见光图像实现高精度的配准 。     

一种基于深度和局部特征的分布式光电图像配准方法北大核心CSCD

针对分布式光电成像系统采集的红外和可见光图像在配准时易受噪声影响,配准精度不高问题,提出一种基于卷积神经网络深度特征和RIFT局部特征的图像配准算法。首先基于改进的AVIRnet提取待配准红外和可见光图像的卷积深度特征,利用深度特征进行初匹配,得到初步的空间关系;然后在重叠图像区域内提取RIFT特征点;最后对局部特征点进行修正,得到最终的匹配点对,估算出精确的变换矩阵。实验结果表明:本文方法通过深度特征和局部特征两次匹配,对非线性辐射差异具有不变性,满足了分布式光电红外和可见光图像配准的精度要求。     

基于可见光匹配矩阵的电气部件故障红外自动识别算法

基于红外图像差分比对法可以高效地检测并发现电气部件老化、接线松动、绝缘失效等问题,但由于红外热图像分辨率低、对比度差,直接特征匹配误点率高、匹配成功率低,提出一种基于可见光匹配矩阵的电气部件故障红外自动识别算法。首先通过固定区域截取法或手动提取特征点配准法处理可见光图像,使处理后的可见光图像与红外图像完全匹配;然后使用SURF及RANSAC算法将匹配好的待测及标准电气部件的可见光图像进行配准,并使用最小二乘法获得最优仿射变换矩阵。最后使用该匹配矩阵将待测及标准电气部件的红外热像图进行配准,进而进行差分故障判断。实验结果表明:该检测算法相较于直接差分比对法,匹配效果好、鲁棒性高,且能够实现异常区域的准确定位。     

基于相似三角形匹配的红外与可见光图像配准方法

提出了一种基于相似三角形匹配的红外与可见光图像配准方法:首先将提取出的Harris角点组成三角形,然后利用本文提出的搜索算法,从红外与可见光图像中找出一对最优的相似三角形,并利用相似三角形的性质,计算出相关的匹配点,最后通过RANSAC算法拟合出配准参数,对图像进行配准。实验结果证明:此算法与传统的基于特征点的图像配准方法相比精度更高,具有较强的鲁棒性,可以解决刚体变换下红外与可见光图像配准的问题。     

基于传感器参数和感兴趣区域的图像配准算法研究

通过对光电成像型反舰导弹的成像过程分析,提出一种基于传感器参数和感兴趣区域的图像配准方法。红外和可见光图像配准时的变换模型为仿射变换,首先通过传感器参数的调整实现空间分辨率的配准,将仿射变换简化为刚体变换;然后用海天线提取算法提取出感兴趣区域,对感兴趣区域用形态学边缘检测方法求取目标的轮廓中心,并以此为控制点消除图像间的平移变化,实现图像的完全配准;最后利用均方根误差原则对算法的配准效果进行评估。仿真实验表明,该算法快速、准确,配准精度满足目标识别的要求,可以较好地解决异类传感器弱小目标图像配准的难题。     

基于显著性检测的不同视角下红外与可见光图像融合

融合红外图像的热源目标和可见光图像的清晰背景可以实现低照度条件下与场景关联的异常行为识别。现有以特征匹配为主的融合方法,受监控场景下可见光与红外成像的尺度、视角、目标特性等差异影响,配准及融合效率及准确性受限。针对该问题,本文提出了基于显著性检测的不同视角下红外与可见光图像融合方法。通过预设热敏感目标,计算可见光与红外的视场转换模型,预先配准红外与可见光视场。使用Mask R-CNN网络提取红外图像中的行人目标显著性区域,根据视场转换模型点将每个目标区域与可见光图像局部融合。最后,通过违规入侵行为辨识为目标进行实验验证。实验表明,论文提出的融合方法能够有效地将红外图像的热敏目标信息与可见光的场景进行融合,可以准确地判断是否发生违规入侵行为。     

Spatial-domain image hiding using image differencing

A method to embed a secret image into a cover image is proposed. The method is based on the similarity among the grey values of consecutive image pixels as well as the human visual system's variation insensitivity from smooth to contrastive. A stego-image is produced by replacing the grey values of a differencing result obtained from the cover image with those of a differencing result obtained from the secret image. The process preserves the secret image with no loss and produces the stego-image with low degradation. Moreover, a pseudorandom mechanism is used to achieve cryptography. It is found from experiment that the peak values of signal-to-noise ratios of the method are high and that the resulting stego-images are imperceptible. Even when the size of the secret image is about a half of the cover image     

基于多层级图像分解的图像融合算法

不同类型的探测器在成像机理上有不同的侧重点,使得成像图像表征的信息也有所不同,导致单幅图像不能完整地反映场景的有效信息。因此,提取多源图像的互补信息,并去除其中的冗余信息,合成一幅能准确、完整表达场景的复合图像的技术成为了图像处理领域中一项非常重要的技术,图像融合正是这类问题的一种有效解决方法。针对传统多尺度分解的图像融合方法易产生噪声和信息缺失的现象,文中提出了一种基于多层级图像分解的红外与可见光图像融合算法。首先,利用加权平均曲率滤波的边缘保持特性与高斯滤波的平滑特性,构建了多层级图像分解模型。在利用该模型将源图像分解为小尺度层、大尺度层和基层等3个不同层级。然后,针对基层,采用能量属性融合策略进行融合;针对大尺度层,采用复合融合策略进行融合;针对小尺度层,采用最大值融合策略。最后,将融合后的层级进行加和,以重构出最终的融合图像。实验结果表明:文中提出的基于多层级图像分解的图像融合算法能够有效降低噪声产生的概率,同时减少了融合后的信息缺失。     

基于图像增强和复原的图像去雾方法研究

雾霭等天气下获得的图像存在对比度低、颜色退化、景物模糊等一系列图像退化的问题,直接影响了对图像信息的有效利用。因此,对雾天图像进行有效的去雾处理,有效改善降质图像的质量,具有一定的实际意义。分析讨论基于图像增强的多尺度Retinex算法和利用图像复原原理的基于暗原色先验理论的去雾算法,并对具有不同特点的单幅有雾图像进行去雾仿真。实验结果表明,不同理论基础的两种去雾算法各有特点,基于暗原色理论处理得到的图像去雾效果更显著,算法运行速度更快。     

Accurate image registration for MAP image super-resolution

The accuracy of image registration plays a dominant role in image super-resolution methods and in the related literature, landmark-based registration methods have gained increasing acceptance in this framework. In this work, we take advantage of a maximum a posteriori (MAP) scheme for image super-resolution in conjunction with the maximization of mutual information to improve image registration for super-resolution imaging. Local as well as global motion in the low-resolution images is considered. The overall scheme consists of two steps. At first, the low-resolution images are registered by establishing correspondences between image features. The second step is to fine-tune the registration parameters along with the high-resolution image estimation, using the maximization of mutual information criterion. Quantitative and qualitative results are reported indicating the effectiveness of the proposed scheme, which is evaluated with different image features and MAP image super-resolution computation methods.     

Fast image reconstruction network in image stitching

Compared with the traditional feature-based image stitching algorithm, the free-view image stitching algorithm based on deep learning has the advantages of fast stitching speed and good effect. However, these algorithms still cannot achieve real-time splicing speed. For the image reconstruction stage, we redesign a new fast image reconstruction network. This network is designed based on ShuffleNet, and the new network structure and loss function will reduce the time required for image reconstruction. In addition, this network can also reduce the performance loss after the network is lightweight. It is proved by experiments that the fast image reconstruction network can realize real-time high-resolution free-view image reconstruction.     

Prototype image constraints for set-theoretic image restoration

Constraints based on prototype images are developed and used in set-theoretic image restoration. A prototype can be obtained as a result of applying a predetermined operator to the observed image. In this case, the operator and the bound, which limits the variation of the restored image from the prototype, are the two defining quantities of a prototype constraint. General guidelines for rigorously estimating the defining bound of a prototype constraint under certain simplifying conditions are discussed. The authors provide two examples of prototype constraints where the prototypes are obtained by the Wiener filtering operator and a local averaging operator. The projection onto convex sets algorithm using the prototype constraints is applied to both monochrome and color images degraded by out-of-focus blur at different noise levels. The results show significant improvement over the Wiener restoration in reducing the restoration artifacts     

Underwater image enhancement with image colorfulness measure

Due to the absorption and scattering effects of the water, underwater images tend to suffer from many severe problems, such as low contrast, grayed out colors and blurring content. To improve the visual quality of underwater images, we proposed a novel enhancement model, which is a trainable end-to-end neural model. Two parts constitute the overall model. The first one is a non-parameter layer for the preliminary color correction, then the second part is consisted of parametric layers for a self-adaptive refinement, namely the channel-wise linear shift. For better details, contrast and colorfulness, this enhancement network is jointly optimized by the pixel-level and characteristic-level training criteria. Through extensive experiments on natural underwater scenes, we show that the proposed method can get high quality enhancement results.     

Dual-branch deep image prior for image denoising

In this work, we propose a two-stage denoising approach, which includes generation and fusion stages. Specifically, in the generation stage, we first split the expanding path of the UNet backbone of the standard DIP (deep image prior) network into two branches, converting it into a Y-shaped network (YNet). Then we adopt the initial denoised images obtained with DAGL (dynamic attentive graph learning) and Restormer methods together with the given noisy image as the target images. Finally, we utilize the standard DIP on-line training routine to generate two complementary basic images, whose image quality is quite improved, with the help of a novel automatic iteration termination mechanism. In the fusion stage, we first split the contracting path of the standard UNet network into two branches for receiving the two basic images generated in the previous stage, and obtain a fused image as the final denoised image in a fully unsupervised manner. Extensive experimental results confirm that our method has a significant improvement over the standard DIP or other unsupervised methods, and outperforms recently proposed supervised denoising models. The noticeable performance improvement is attributed to the proposed hybrid strategy, i.e., we first adopt the supervised denoising methods to process the common content of images substantially, then utilize the unsupervised method to fine-tune the specific details. In other words, we take full advantage of the high performance of the supervised methods and the flexibility of the unsupervised methods.