A comprehensive benchmark analysis for sand dust image reconstruction

Recently, numerous sand dust removal algorithms have been proposed. To our best knowledge, however, most methods evaluated their performance in a no-reference way using few selected real-world images from the internet. It is unclear how to quantitatively analyze the performance of the algorithms in a supervised way. Moreover, due to the absence of large-scale datasets, there are no well-known sand dust reconstruction report algorithms up till now. To bridge the gaps, we presented a comprehensive perceptual study and analysis of real-world sandstorm images, then constructed a Sand-dust Image Reconstruction Benchmark(SIRB) for training Convolutional Neural Networks(CNNs) and evaluating the algorithm’s performance. We adopted the existing image transformation neural network trained on SIRB as the baseline to illustrate the generalization of SIRB for training CNNs. Finally, we conducted a comprehensive evaluation to demonstrate the performance and limitations of the sandstorm enhancement algorithms, which shed light on future research in sandstorm image reconstruction.     

基于多尺度级联网络的水下图像增强方法

针对水下图像由于光吸收、后向散射等因素导致的严重色偏、细节丢失等问题,该文提出一种基于多尺度级联网络的水下图像增强方法。针对单一网络特征利用不全面导致的图像梯度消失问题,该方法通过级联多尺度原始图像与相应的特征图像,以获得更优异的细节保持效果,并实现从较浅层到较深层快速预测残差的能力。此外,引入联合密集网络块和递归块,通过特征重用有效解决多尺度网络参数过多的问题。为有效解决单一损失造成的图像细节恢复不均的问题,提出Charbonnier和结构相似度 (SSIM) 联合损失函数。经仿真实验分析,所提网络在处理水下图像严重色偏、细节丢失等方面都取得了显著的效果。     

基于视觉特性的非线性多尺度彩色图像增强

[目的]针对图像在低光照下的亮度和对比度偏低的问题,提出一种基于视觉特性的非线性多尺度彩色图像增强算法.[方法]该算法将彩色图像从RGB色彩空间转化到HSI色彩空间,保持H分量不变,对S分量进行指数拉伸,对Ⅰ分量利用视觉系统模型和非线性映射方法实现图像对比度增强,再通过自适应的亮度调整增加图像的全局亮度.最后将HSI色彩空间转化到RGB色彩空间,从而实现对彩色图像自适应增强.[结果]通过对低光照彩色图像进行增强测试,其测试结果表明,[结论]该算法能够自适应地调整图像的全局亮度,增加图像的局部细节对比度,并保持其原色彩,提升彩色图像在低光照下的视见度.     

Underwater image enhancement based on conditional generative adversarial network

Underwater images play an essential role in acquiring and understanding underwater information. High-quality underwater images can guarantee the reliability of underwater intelligent systems. Unfortunately, underwater images are characterized by low contrast, color casts, blurring, low light, and uneven illumination, which severely affects the perception and processing of underwater information. To improve the quality of acquired underwater images, numerous methods have been proposed, particularly with the emergence of deep learning technologies. However, the performance of underwater image enhancement methods is still unsatisfactory due to lacking sufficient training data and effective network structures. In this paper, we solve this problem based on a conditional generative adversarial network (cGAN), where the clear underwater image is achieved by a multi-scale generator. Besides, we employ a dual discriminator to grab local and global semantic information, which enforces the generated results by the multi-scale generator realistic and natural. Experiments on real-world and synthetic underwater images demonstrate that the proposed method performs favorable against the state-of-the-art underwater image enhancement methods.     

基于注意力的多尺度水下图像增强网络

水下图像往往会因为光的吸收和散射而出现颜色退化与细节模糊的现象,进而影响水下视觉任务。该文通过水下成像模型合成更接近水下图像的数据集,以端到端的方式设计了一个基于注意力的多尺度水下图像增强网络。在该网络中引入像素和通道注意力机制,并设计了一个多尺度特征提取模块,在网络开始阶段提取不同层次的特征,通过带跳跃连接的卷积层和注意力模块后得到输出结果。多个数据集上的实验结果表明,该方法在处理合成水下图像和真实水下图像时都能有很好的效果,与现有方法相比能更好地恢复图像颜色和纹理细节。     

Orientation Diffusion or How to Comb a Porcupine

This paper addresses the problem of feature enhancement in noisy images, when the feature is known to be constrained to a manifold. As an example, we approach the orientation denoising problem via the geometric Beltrami framework for image processing. The feature (orientation) field is represented accordingly as the embedding of a two dimensional surface in the spatial-feature manifold. The resulted Beltrami flow is a selective smoothing process that respects the feature constraint. Orientation diffusion is treated as a canonical example where the feature (orientation in this case) space is the unit circle S¹. Applications to color analysis are discussed and numerical experiments demonstrate again the power of the Beltrami framework for nontrivial geometries in image processing.     

融合深度学习与多尺度Retinex的水下图像增强方法

针对水下图像纹理模糊和色偏严重等问题,提出了一种融合深度学习与多尺度导向滤波Retinex的水下图像增强方法。首先,将陆上图像采用纹理和直方图匹配法进行退化,构建退化水下图像失真的数据集并训练端到端卷积神经网络(convolutional neural network,CNN) 模型,利用该模型对原始水下图像进行颜色校正,得到色彩复原后的水下图像;然后,对色彩复原图像的亮度通道,采用多尺度Retinex(multi-scale Retinex,MSR) 方法得到纹理增强图像;最后,融合色彩复原图像中的颜色分量和纹理增强图像得到最终水下增强图像。本文利用仿真水下图像数据集和真实水下图像对提出方法进行性能测试。实验结果表明,所提方法的均方根误差、峰值信噪比、CIEDE2000和水下图像质量评价指标分别为0.302 0、17.239 2 dB、16.878 4和4.960 0,优于5种对比方法,增强后的水下图像更加真实自然。本文方法在校正水下图像颜色失真的同时,能有效提升纹理清晰度和对比度。     

结合多尺度深度学习网络和Retinex理论的低光照图像增强算法

针对低光照增强任务缺乏参考图像及现有算法存在的色彩失真、纹理丢失、细节模糊、真值图像获取难等问题,本文提出了一种基于Retinex理论与注意力机制的多尺度加权特征低光照图像增强算法。该算法通过基于Unet架构的特征提取模块对低光照图像进行多尺度的特征提取,生成高维度的多尺度特征图;建立注意力机制模块凸显对增强图像有利的不同尺度的特征信息,得到加权的高维特征图;最后反射估计模块中利用Retinex理论建立网络模型,通过高维特征图生成最终的增强图像。设计了一个端到端的网络架构并利用一组自正则损失函数对网络模型进行约束,摆脱了参考图像的约束,实现了无监督学习。最终实验结果表明本文算法在增强图像的对比度与清晰度的同时维持了较高的图像细节与纹理,具有良好的视觉效果,能够有效增强低光照图像,视觉质量得到较大改善;并与其他多种增强算法相比,客观指标PSNR和SSIM得到了提高。     

基于改进的MSRCR-CLAHE融合的水下图像增强算法

针对海洋复杂成像环境导致的水下图像出现颜色衰退、对比度低等问题,提出一种改进的带色彩恢复的多尺度视网膜（Multi-Scale Retinex with Color Restore,MSRCR）与限制对比度自适应直方图均衡化（Contrast Limited Adaptive Histogram Equalization,CLAHE）多尺度融合的水下图像增强算法。首先,采用带有导向滤波的MSRCR算法解决水下图像颜色衰退的问题;其次,采用带有Gamma校正的CLAHE算法以提高水下图像的对比度;最后,对经过改进的MSRCR和CLAHE处理后的图像进行多尺度融合以获得细节增强后的水下图像。实验结果表明,和其他算法相比,文中算法的峰值信噪比（Peak Signal to Noise Ratio,PSNR）平均提高了9.3914、结构相似性（Structural Similarity Index Measure,SSIM）平均提高了0.3013、水下图像评价指标（Underwater Image Quality Evaluation,UIQE）平均提高了4.7047,能实现水下图像的有效增强...     

一种自适应尺度的MSR图像增强方法

针对传统多尺度Retinex增强算法不能有效增强图像不同尺度的细节特征问题,提出了一种自适应尺度的MSR增强算法,利用HSI空间中的亮度分量方差值自适应确定滤波器尺寸,在增大图像对比度、突出图像细节特征的同时保持了图像色彩的稳定性,对光照不均匀图像取得了较好的增强效果。     

结合图像分割的改进导引滤波

为了更好地对图像进行平滑同时保持边缘不模糊,设计一种新的滤波方法。对基于该方法的图像滤波、细节增强等算法进行研究。首先,根据图像的亮度和颜色对图像进行分割,将图像分成不同的区域。接着,在不同的区域进行导引滤波,得到互不交叠的多个滤波子图像。然后,将这些子图融合,得到基于分割的改进导引滤波结果。最后,利用提出的改进导引滤波方法提出一种多尺度的细节增强方法。实验结果表明,在图像光滑和细节增强方面,提出的方法都要好于传统的导引滤波:提出的方法不仅能较好的光滑图像,同时保持边缘清晰,减少了传统滤波方法在边缘处的光晕现象。     

Learning Color Names for Real-World Applications

Color names are required in real-world applications such as image retrieval and image annotation. Traditionally, they are learned from a collection of labeled color chips. These color chips are labeled with color names within a well-defined experimental setup by human test subjects. However, naming colors in real-world images differs significantly from this experimental setting. In this paper, we investigate how color names learned from color chips compare to color names learned from real-world images. To avoid hand labeling real-world images with color names, we use Google image to collect a data set. Due to the limitations of Google image, this data set contains a substantial quantity of wrongly labeled data. We propose several variants of the PLSA model to learn color names from this noisy data. Experimental results show that color names learned from real-world images significantly outperform color names learned from labeled color chips for both image retrieval and image annotation.     

Single image visibility restoration using optical compensation and pixel-by-pixel transmission estimation

Aiming at image degradation in hazy and sandstorm weather,an optical compensation color restoration and pixel-by-pixel transmissvity estimation algorithm was proposed.The blue light was absorbed by sandstorm particles.The color shift phenomenon could be eliminated by optical compensate method,which convert the sandstorm images into hazy images.Then the ratio relationship between the minimum channel and its Gaussian function as the transmissivity,and median filter was used to eliminate its texture effects.The depth of the restored transmissivity alternated obviously and the edge was well preserved,which did not need the time-consuming postprocessing operativity.Finally,the image was restored by the atmospheric scattering model.The experimental results show that recovered sandstorm image treatment is better,and the saturation of the haze image is appropriate,the bright area is more nature,and running time is faster.     

Enhancing underwater image via color correction and Bi-interval contrast enhancement

Underwater captured images often suffer from color cast and low visibility due to light is scattered and absorbed while it traveling in water. In this paper, we proposed a novel method of color correction and Bi-interval contrast enhancement to improve the quality of underwater images. Firstly, a simple and effective color correction method based on sub-interval linear transformation is employed to address color distortion. Then, a Gaussian low-pass filter is applied to the L channel to decompose the low- and high-frequency components. Finally, the low- and high-frequency components are enhanced by Bi-interval histogram based on optimal equalization threshold strategy and S-shaped function to enhancement image contrast and highlight image details. Inspired by the multi-scale fusion, we employed a simple linear fusion to integrate the enhanced high- and low-frequency components. Comparison with state-of-the-art methods show that the proposed method outputs high-quality underwater images with qualitative and quantitative evaluation well.     

改进的伽马校正与多尺度融合的水下图像增强

由于光在水下传播会发生吸收和散射,导致采集 的水下图像出现模糊、对比度低、色偏、光照不 均匀等问题。针对以上问题,提出了一种改进的伽马校正与多尺度融合的水下图像增强算法 。首先基于G 通道对R和B通道进行补偿,并对RGB 三通道进行直方图拉伸后使用灰度世界(Gray World) 算法得到颜 色校正图像;然后使用改进的伽马函数改善颜色校正后图像光照不均匀问题,得到光照均匀 图像,并进 行归一化处理;再对光照均匀图像使用限制对比度的自适应直方图均衡化(contrast limite d adaptive histogram equalization,CLAHE)算法得到对比度提升图像;最后采用多尺度融 合算法对以上得出的3幅图 片进行融合,得出增强图像。实验结果表明,提出的算法对不同水下环境的图像均有较好的处理 效果,图像质量评价指标得到明显提高。     

基于多尺度特征结合细节恢复的单幅图像去雾方法

为提高单幅图像去雾方法的准确性及其去雾结果的细节可见性,该文提出一种基于多尺度特征结合细节恢复的单幅图像去雾方法。首先,根据雾在图像中的分布特性及成像原理,设计多尺度特征提取模块及多尺度特征融合模块,从而有效提取有雾图像中与雾相关的多尺度特征并进行非线性加权融合。其次,构造基于所设计多尺度特征提取模块和多尺度特征融合模块的端到端去雾网络,并利用该网络获得初步去雾结果。再次,构造基于图像分块的细节恢复网络以提取细节信息。最后,将细节恢复网络提取出的细节信息与去雾网络得到的初步去雾结果融合得到最终清晰的去雾图像,实现对去雾后图像视觉效果的增强。实验结果表明,与已有代表性的图像去雾方法相比,所提方法能够对合成图像及真实图像中的雾进行有效去除,且去雾结果细节信息保留完整。     

激光夜视图像分型分割算法研究

为解决以往采用关联规则挖掘算法对图像进行分割时,对于夜视图像中灰暗区域中颜色特征以及前景/背景特征的采集能力差,不能有效判定图像的多尺度分型特征,分型分割效果差的问题。研究激光夜视图像分型分割算法。先利用计盒维数估计方法计算激光夜视图像分型维数尺度,通过分型维数尺度获取激光夜视图像的多尺度分型特征值,将利用多尺度分型特征值获取的多尺度分型特征约束与图像颜色约束相结合获取多尺度分型特征数据项,融合该多尺度分型特征数据项与通过图像中相邻区域顶点颜色距离获取的光滑项,并加入自适应比重系数获取能量函数,利用最大流/最小割算法求解能量函数最小值,实现激光夜视图像的分割。实验结果表明,该算法可准确分割激光夜视图像中人物目标特征,分割10幅激光夜视图像准确率以及均匀性测度平均值均在95%以上。     

Multi-patch embedding canonical correlation analysis for multi-view feature learning

Locality-based feature learning for multi-view data has received intensive attention recently. As a result of only considering single-category local neighbor relationships, most of such the learning methods are difficult to well reveal intrinsic geometric structure information of raw high-dimensional data. To solve the problem, we propose a novel supervised multi-view correlation feature learning algorithm based on multi-category local neighbor relationships, called multi-patch embedding canonical correlation analysis (MPECCA). Our algorithm not only employs multiple local patches of each raw data to better capture the intrinsic geometric structure information, but also makes intraclass correlation features as close as possible by minimizing intraclass scatter of each view. Extensive experimental results on several real-world image datasets have demonstrated the effectiveness of our algorithm.     

典型风沙环境对电磁信号衰减的规律研究

风沙天气对人们生活有很大影响,其中一方面就是对电磁信号传播的干扰,文中通过建立基本地形模型,将风沙天气进行建模处理,加入到基本地形模型中,然后研究其电磁特征参数得到电磁模型,对比研究了在没有风沙情况下的电磁传播衰减以及不同严重程度风沙天气中的电磁传播衰减。所得规律既可以为进一步研究风沙区域电磁信号衰减问题提供技术参考,也可以由衰减情况反推出风沙天气的严重程度。     

Attention mechanism enhancement algorithm based on cycle consistent generative adversarial networks for single image dehazing

This paper proposes AMEA-GAN, an attention mechanism enhancement algorithm. It is cycle consistency-based generative adversarial networks for single image dehazing, which follows the mechanism of the human retina and to a great extent guarantees the color authenticity of enhanced images. To address the color distortion and fog artifacts in real-world images caused by most image dehazing methods, we refer to the human visual neurons and use the attention mechanism of similar Horizontal cell and Amazon cell in the retina to improve the structure of the generator adversarial networks. By introducing our proposed attention mechanism, the effect of haze removal becomes more natural without leaving any artifacts, especially in the dense fog area. We also use an improved symmetrical structure of FUNIE-GAN to improve the visual color perception or the color authenticity of the enhanced image and to produce a better visual effect. Experimental results show that our proposed model generates satisfactory results, that is, the output image of AMEA-GAN bears a strong sense of reality. Compared with state-of-the-art methods, AMEA-GAN not only dehazes images taken in daytime scenes but also can enhance images taken in nighttime scenes and even optical remote sensing imagery.