循环侧抑制网络的红外图像预处理FPGA实现研究

在红外成像预处理中,循环侧抑制网络具有很好的增强图像边缘反差、突出边框的功能。由于循环侧抑制网络处理运算的复杂性,如何实时实现循环侧抑制网络的红外图像预处理成为关键问题。根据简化的循环侧抑制网络处理算法,并结合硬件计算特点,提出一种适合于硬件实现循环侧抑制网络的并行处理结构,采用流水线设计方式在FPGA中实时实现。试验证明：该算法在FPGA内具有与视频流同步的实时性,达到了增强反差、突出边框的效果。用于图像目标实时跟踪系统时,极大地提高了目标的跟踪精度和稳定性。     

Motion deblurring using edge map with blurred/noisy image pairs

Motion deblurring methods using blurred/noisy image pairs usually include denoising process of the noisy image. Because both remaining noise and distorted fine details in the denoised image cause an error on deblurring, we propose an algorithm using an edge map of the noisy image to retain sharp edge information while neglecting noise in any smooth region that does not contain information about the motion that occurred during the exposure. In addition, the blur kernel is efficiently estimated by employing the fast total variation regularization method for the gradients of blurred and noisy images only on edge regions. For latent image restoration, another fidelity term is added, which compares the gradients of the noisy and estimated latent images on edge regions to preserve the fine details of the noisy image. To model a sparse distribution of real-world image gradients, a deconvolution method imposing hyper-Laplacian priors based on an alternating minimization scheme is also derived to restore a latent image efficiently. Experimental results show that the peak signal-to-noise ratios of the restored images against the original latent images have been increased by 11.1% on average, when compared to the existing algorithms using an image pair.     

基于照射_反射模型和有界运算的多谱段图像增强

根据多尺度照射_反射模型, 结合广义有界运算模型和引导滤波, 能够有效地解决多谱段降质图像的增强问题. 算法采用自适应的引导滤波核函数作为环绕函数, 估计反映图像整体结构的不同尺度的低频照射分量; 利用有界广义对数比(general log-radio, GLR)模型加法代替Retinex理论中的对数变换运算; 再由GLR模型减法去除照射分量, 将不同尺度的反射分量从原始图像中分割出来; 对不同尺度反射分量的有效信息采用有界GLR模型乘法和加法进行融合, 有效地避免光晕伪影现象及越界现象的发生, 得到多尺度反射分量图像, 即最终的增强图像. 通过对可见光波段的低照度图像和雾霾图像、红外图像、X光医学图像四组多谱段降质图像实验分析, 以对比度和信息熵作为评价指标, 与同类算法进行了图像增强效果的定性和定量对比, 结果表明本文算法增强后的图像纹理和边缘细节更加丰富、对比度更高、视觉效果更佳, 可广泛地应用于多种图像增强领域.     

彩色图像边缘检测及其在图像融合中的应用

提出了一种新的基于小波变换的彩色图像边缘检测方法,运用噪声和微弱边缘的识别以及动态双域值的选取,使得检测出来的边缘定位精度高,抑制噪声性能好。利用基于区域特征的信息融合策略,比较待融合图像的边缘点的值和区域能量特征值,选择特征突出者对应的原始图像区域组成融合结果。实验结果表明,该算法可以良好地保留两幅图像的细节信息,得到高质量的融合图像。     

多尺度条件卷积的OCT视网膜图像降噪研究

散斑噪声存在于光学相干层析成像(OCT)中,影响OCT图像质量.在使用OCT设备诊断各种常见眼科疾病时,高质量的OCT图像是极为重要的.利用深度神经网络对OCT图像进行降噪处理,使图像在保留空间结构细节的基础上能展示更多的信息.提出了一种基于残差学习网络的新型OCT图像降噪网络-CMCNN,其具有多尺度、多权重和多层次...     

MPPC low-level-light imaging enhancement algorithm based on sub-window box filtering北大核心CSCD

针对多像素光子计数器(MPPC)进行微光成像时,图像受光照不足和噪声影响出现的图像亮度低、对比度差、边缘模糊等问题,提出一种基于子窗口盒式滤波的自适应微光图像处理算法。为了减少算法运行时间的同时突出图像的边缘细节信息,利用子窗口盒式滤波器对图像进行分层得到基础层和细节层;对基础层图像采用自适应阈值直方图均衡化拉伸对比度,细节层图像采用自适应增益控制方式进行增强;根据基础层图像中有效灰度值个数占总灰度的比值自适应确定融合系数,将基础层图像与细节层图像融合得到增强后图像。通过微光实验平台设置3组不同照度的微光环境进行实验仿真,验证了本文算法在保持边缘信息和增强细节方面获得了更好的效果。实验结果表明本文算法在标准差、信息熵、平均梯度等客观评价方面优于改进前算法,提升了微光图像的成像效果。     

基于图像复原的高光谱图像前向像移补偿

为了提高高光谱图像空间维的图像分辨力,针对航空遥感器成像时由前向像移造成的图像模糊提出了像移补偿方法。分析了航空遥感器前向像移造成图像模糊的退化机制,对运动模糊图像进行了预处理;估计了点扩散函数和噪声功率,使用改进的维纳滤波算法对图像进行复原并以绝对平均误差、峰值信噪比作为评价标准进行了实验。在估计出模糊图像点扩散函数和噪声功率的情况下得到的结果显示:与传统的维纳滤波复原算法相比,改进的维纳滤波复原算法的图像绝对平均误差降低了9.31%,峰值信噪比提高了13.98%,表明提出的算法能够有效改善高光谱图像的像质。     

Mixed noise removal algorithm of EBAPS image under low illumination condition based on FPGA北大核心CSCD

In order to solve the problem that single median filtering and gaussian filtering algorithm is not effective in suppressing impulse noise and poisson noise simultaneously in low illumination image, and the edge detail protection is insufficient, an open and close mix-median-gaussian (OCMMG) filtering algorithm based on field programmable gate array (FPGA) was proposed. Firstly, the minimum four-direction difference was used to detect the anomaly degree of each pixel point, the weight was allocated according to the threshold of pulse noise discrimination, and the first step was filtering. Then, the four-direction edge detection algorithm was used to extract image edges, and the second step was filtered according to the set edge confidence characterization value. Finally, the images collected by electron bombarded active pixel sensor (EBAPS) under the condition of 1×10−3 lx illumination were processed by FPGA in real time. The experimental results show that the FPGA processing results are consistent with the software simulation processing results. Compared with the median filtering and gaussian filtering algorithm, the peak signal-to-noise ratio (PSNR) of the algorithm is improved by 3.23% and 16.34%, the structural similarity is improved by 14.66% and 33.86%, and the edge retention index is improved by 0.49% and 4.21%, respectively, which can effectively remove the mixed noise of EBAPS image and meet the real-time requirements. © 2022 Editorial office of Journal of Applied Optics. All rights reserved.     

Gaussian mixture model-based gradient field reconstruction for infrared image detail enhancement and denoising

Infrared images are characterized by low signal-to-noise ratio and low contrast. Therefore, the edge details are easily immerged in the background and noise, making it much difficult to achieve infrared image edge detail enhancement and denoising. This article proposes a novel method of Gaussian mixture model-based gradient field reconstruction, which enhances image edge details while suppressing noise. First, by analyzing the gradient histogram of noisy infrared image, Gaussian mixture model is adopted to simulate the distribution of the gradient histogram, and divides the image information into three parts corresponding to faint details, noise and the edges of clear targets, respectively. Then, the piecewise function is constructed based on the characteristics of the image to increase gradients of faint details and suppress gradients of noise. Finally, anisotropic diffusion constraint is added while visualizing enhanced image from the transformed gradient field to further suppress noise. The experimental results show that the method possesses unique advantage of effectively enhancing infrared image edge details and suppressing noise as well, compared with the existing methods. In addition, it can be used to effectively enhance other types of images such as the visible and medical images.     

Target extraction of banded blurred infrared images by immune dynamical algorithm with two-dimensional minimum distance immune field

Banded blurred Infrared image segmentation is a challenging topic since banded blurred infrared images are characterized by high noise, low contrast, and weak edges. Based on the interconnected and networked collaborative mechanism between innate immune factors and adaptive immune factors, this paper presents an immune dynamical algorithm with two-dimensional minimum distance immune field to solve this puzzle. Firstly, using the original characteristics as antigen surface molecular patterns, innate immune factors in the first layer of immune dynamical network extract banded blurred regions from the whole banded blurred infrared image region. Secondly, innate immune factors in the second layer of immune dynamical network extract new characteristics to design the complex of major histocompatibility complex (MHC) and antigen peptide. Lastly, adaptive immune factors in the last layer will extract object and background antigens from all the banded blurred image antigens, and design the optimal immune field of every adaptive immune factors. Experimental results on hand trace infrared images verified that the proposed algorithm could efficiently extract targets from images, and produce better extraction accuracy.     

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。     

基于光照-反射成像模型和形态学操作的多谱段图像增强算法

为解决多谱段降质图像增强问题,提出了一种基于光照-反射成像模型和形态学操作的多谱段图像增强算法.首先对图像饱和度使用自适应非线性拉伸函数进行拉伸,使增强后的图像色彩更加饱和、自然;接下来利用引导滤波算法提取出图像的光照分量,提出了一种基于细节特征的加权融合策略,利用光照分布特性构造了一种自适应Gamma校正函数对光照分量进行处理,并将其与利用对比度受限的自适应直方图均衡化方法处理后的光照分量以及原始光照分量进行融合;然后在反射分量校正时,构造了一种形态学操作函数来校正反射信息;最后合并光照分量和反射分量,并与处理后的饱和度分量和色调分量一起得到增强图像.采用主客观评价指标对可见光低照度图像、水下图像、高动态范围图像、沙尘暴图像、雾天图像和热红外图像6种降质多谱段图像实验结果进行分析比较,结果表明本文算法能够有效地抑制图像噪声、增强图像细节信息、改善图像视觉效果,可应用于多种图像增强领域.     

基于深度玻尔兹曼模型的红外与可见光图像融合

为了克服红外与可见光图像融合时噪声干扰及易产生伪影导致目标轮廓不鲜明、对比度低的缺点,提出一种基于深度模型分割的图像融合方法.首先,采用深度玻尔兹曼机学习红外与可见光的目标和背景轮廓先验,构建轮廓的深度分割模型,通过Split Bregman迭代算法获取最优能量分割后的红外与可见光图像轮廓;然后再使用非下采样轮廓波变换对源图像进行分解,并针对所分割的背景轮廓采用结构相似度的规则进行系数组合;最后进行非下采样轮廓波反变换重构出融合图像.数值试验证明,该算法可以有效获取目标和背景轮廓均清晰的融合图像,融合结果不但具有较高的对比度,还能抑制噪声影响,具有有效性.     

A robust edge detection method with sub-pixel accuracy

In this paper, a new edge detection approach combining gray-moments operator with smoothing spline algorithm is proposed, which is invariant to additive and multiplicative noises in the image. This approach consists of two steps: firstly, a continuous blurred edge model is obtained using the smoothing spline algorithm in the edge region detected by Sobel operator; then a gray-moment solution is derived for both the one- and two-dimensional situations using the blurred edge model. Testing of this new detection approach demonstrates more robustness against the white Gaussian noise and speckle noise, and run time very close to the gray-moment and space-moment operators. The above advantages indicate this approach is very suitable for on-line accurate detection.     

改进Canny算法的红外人脸图像边缘轮廓提取

红外人脸图像的边缘轮廓特征对于红外人脸检测、识别等相关应用具有重要价值。针对红外人脸图像边缘轮廓提取时存在伪边缘的问题,提出了一种改进Canny算法的红外人脸图像边缘轮廓提取方法。首先通过对引导滤波算法引入“动态阈值约束因子”替换原始算法中的高斯滤波,解决了原始算法滤波处理不均匀和造成红外人脸图像弱边缘特征丢失的弊端;接着对原始算法的非极大值抑制进行了改进,在原始计算梯度方向的基础上又增加了4个梯度方向,使得非极大值抑制的插值较原始算法更加精细;最后改进OTSU(大津)算法,构造灰度-梯度映射函数确定最佳阈值,解决了原始算法人为经验确定阈值的局限性。实验结果表明:提出的改进Canny算法的红外人脸轮廓提取方法滤波后的图像,相较于原始Canny算法滤波处理,信噪比性能提升了34.40%,结构相似度性能提升了21.66%;最终的红外人脸边缘轮廓提取实验的优质系数值高于对比实验的其他方法,证明改进后的算法对于红外人脸图像边缘轮廓提取具有优越性。     

多局部残差连接注意网络的图像去模糊

针对现有的基于卷积神经网络的图像去模糊算法存在图像纹理细节恢复不清晰的问题,提出了一种基于多局部残差连接注意网络的图像去模糊算法。首先,采用一个卷积层进行浅层特征提取;其次,设计了一种新的基于残差连接和并行注意机制的多局部残差连接注意模块,用于消除图像模糊并提取上下文信息;再次,采用一个基于扩张卷积的成对连接模块进行细节恢复;最后,利用一个卷积层重建清晰图像。实验结果表明：在GoPro数据集上的PSNR (peak signal to noise ratio)和SSIM (structure similarity)分别为31.83 dB、0.927 5,在定性和定量两方面都表明所提方法能够有效地恢复模糊图像的纹理细节,网络性能优于对比方法。     

改善光电稳瞄系统视觉效果的图像增强算法

为了改善光电稳瞄系统的视觉效果,使视频图像更加适合于人眼观察,并且有利于对目标的自动跟踪效果,将直方图均衡化处理与拉普拉斯边缘锐化处理相结合,在增强对比度的同时尽量保持边缘细节。仿真结果显示采用本文算法能够有效改善视频图像的视觉效果。     

On some applications of diffusion processes for image processing

We propose a new algorithm inspired by the properties of diffusion processes for image filtering. We show that purely nonlinear diffusion processes ruled by Fisher equation allows contrast enhancement and noise filtering, but involves a blurry image. By contrast, anisotropic diffusion, described by Perona and Malik algorithm, allows noise filtering and preserves the edges. We show that combining the properties of anisotropic diffusion with those of nonlinear diffusion provides a better processing tool which enables noise filtering, contrast enhancement and edge preserving.     

Biological image processing via Chaotic Differential Search and lateral inhibition

In this paper, we propose a hybrid biological image processing approach, which is based on Chaotic Differential Search (CDS) algorithm and lateral inhibition (LI) mechanism. We named this hybrid biological image processing approach as LI-CDS. Differential Search (DS) algorithm is a new bio-inspired optimization algorithm mimicking the migration behavior of an organism, and has been successfully used for solution of coordinate system transformation. The property of chaotic variable is integrated into DS to improve its search strategy so that it can escape from the local optimum. Furthermore, lateral inhibition mechanism, which is verified to have good effects on image edge extraction and image enhancement, is employed to pre-process images involved. In this hybrid biological image processing mechanism, our proposed LI-CDS method incorporates both advantages of chaos theory and lateral inhibition mechanism. Series of comparative experimental results by using LI-CDS, DS, CDS and Particle Swarm Optimization (PSO) demonstrate that the proposed LI-CDS performs better than the other three methods.     

基于小波变换的图像混合噪声自适应滤除算法

为同时滤除图像中的椒盐噪声和高斯噪声,提出了一种基于小波变换的混合噪声自适应滤除算法,该算法首先采用中值滤波去除椒盐噪声,然后借助边缘检测算子区将图像为分边缘与非边缘区域,进一步对非边缘区域引入改进的均值滤波器,有效削弱高斯噪声的同时保护图像边缘细节,既初步削弱高斯噪声又保护了边缘,最后采用改进的小波阈值滤波算法,对不同的小波系数采用不同的阈值函数,通过线性回归得到各最优阈值关系式。实验结果表明,该混合噪声自适应滤除算法能有效滤除椒盐噪声和高斯噪声,在图像主观质量和客观质量上均取得了较好的效果,能提高去噪图像峰值信噪比0.5~2.0 dB。