基于暗原色先验的单幅图像快速去雾算法

针对雾天环境下图像清晰度降低以及色调偏移问题,提出一种基于暗原色先验的单幅图像快速去雾算法。首先使用灰度开运算代替最小值滤波得到粗略暗通道图,根据方差标记出雾天图像各个景深突变区的位置,并对突变区的暗原色值进行细化求解;其次求解出透射率的粗略估计并使用引导滤波来进行优化;然后使用一种自适应的容差机制对天空等明亮区域的透射率进行动态修正;最后利用大气散射模型复原出无雾图像。实验结果表明,与几种典型的图像去雾算法相比,所提算法具有较快的处理速度,同时得到的复原图像细节突出、色彩丰富。     

消除halo效应和色彩失真的去雾算法

目的 雾天条件下采集的图像存在低对比度和低场景可见度的问题,传统的去雾算法易产生halo效应和色彩失真问题。为此,结合大气散射光特性提出一种基于相对总变差的图像复原方法。方法 首先从大气散射光与纹理信息无关的角度出发,利用相对总变差分离图像主结构和图像纹理信息准确估计大气耗散函数,通过引入一个自适应保护因子来避免复原图像的色彩失真问题,最后由大气散射模型计算复原图像并进行图像的亮度调整,得到一幅清晰无雾的图像。结果 通过与经典的去雾算法比较,表明该方法可以有效避免halo效应和天空颜色失真等不足,并且在图像的深度突变处也能得到很好的去雾效果。结论 实验表明该算法的场景适应能力较强,时间复杂度与图像的大小成线性关系,相比于前人的算法在计算速度上有一定的提高。     

Estimation of minimum color channel using difference channel in single image Dehazing

Single image dehazing (SID) solves the atmospheric scattering model (ATSM). The ill-defined nature of the SID makes it a challenging problem. The transmission is the prime parameter of ATSM. Hence, accurate transmission is essential for quality of SID. The existing methods of SID estimate the transmission based on priors with strong assumptions (such as dark channel prior). These methods do not recover original colors, structure and visibility due to wrong transmission under invalidity of these assumptions. Therefor, the difference channel (DCH) is proposed to estimate accurate transmission. The DCH non-linearly translates the minimum channel of hazy image into minimum channel of haze-free image, which is used to compute the value of transmission. The DCH is based on an observation that difference of maximum and minimum color channel of the hazy image is negatively correlated with depth. The proposed method is able to recover the details from hazy image in the form of structure, edges, corners, colors and visibility due to the DCH. The accuracy and robustness of the proposed method is proved by comparing the results with known dehazing methods based on qualitative and quantitative analysis using benchmark data sets.

     

基于转换域与自适应伽马校正的去雾算法

针对暗通道先验算法中存在的光晕效应以及天空区域偏色等问题,提出一种基于转换域与自适应伽马校正的图像去雾算法。首先通过将大气散射模型转换至对数域,结合暗通道先验理论提出对数域正相关关系;再利用高斯函数拟合正相关,从而得到粗级透射率;然后将有雾图像转换至HSV色彩空间,提取亮度分量构造自适应伽马校正因子,对粗级透射率进行修正,并使用交叉双边滤波操作实现透射率的进一步优化;最后结合大气散射模型与改进的局部大气光,实现无雾图像的有效复原。仿真实验表明,与几种经典算法相比,该算法复原结果去雾彻底且细节丰富,具有较好的色彩保真度,更接近真实场景。     

A component-driven distributed framework for real-time video dehazing

Traditional dehazing techniques, as a well studied topic in image processing, are now widely used to eliminate the haze effects from individual images. However, the state-of-the-art dehazing algorithms may not provide sufficient support to video analytics, as a crucial pre-processing step for video-based decision making systems (e.g., robot navigation), due to poor coherence and low processing efficiency of the present algorithms. This paper presents a new framework, particularly designed for video dehazing, to output coherent results in real time, with two novel techniques. Firstly, we decompose the dehazing algorithms into three generic components, namely transmission map estimator, atmospheric light estimator and haze-free image generator. They can be simultaneously processed by multiple threads in the distributed system, such that the processing efficiency is optimized by automatic CPU resource allocation based on the workloads. Secondly, a cross-frame normalization scheme is proposed to enhance the coherence among consecutive frames, by sharing the parameters of atmospheric light from consecutive frames in the distributed computation platform. The combination of the above three components enables our framework to generate highly consistent and accurate dehazing results in real-time, by using only 5 PCs connected by Ethernet.

     

基于大气面纱优化和透射率修正的图像去雾

基于中值滤波的图像去雾算法不能有效去除细小边缘处的雾,且天空区域容易出现颜色失真问题。因此,提出了一种基于大气面纱优化和透射率修正的单幅图像去雾算法。首先基于阈值分割提取天空区域,并降低各颜色通道最小值图像中对应区域的灰度值,然后使用加权引导滤波得到优化后的大气面纱,从而得到较为准确的透射率,最后由大气散射模型得到复原图像。相比于其他算法,该算法在优化大气面纱的同时修正了透射率,在边缘处的去雾效果更加明显,同时解决了天空区域的色彩失真问题。     

AIDEDNet: anti-interference and detail enhancement dehazing network for real-world scenes

The haze phenomenon seriously interferes the image acquisition and reduces image quality. Due to many uncertain factors, dehazing is typically a challenge in image processing. The most existing deep learning-based dehazing approaches apply the atmospheric scattering model (ASM) or a similar physical model, which originally comes from traditional dehazing methods. However, the data set trained in deep learning does not match well this model for three reasons. Firstly, the atmospheric illumination in ASM is obtained from prior experience, which is not accurate for dehazing real-scene. Secondly, it is difficult to get the depth of outdoor scenes for ASM. Thirdly, the haze is a complex natural phenomenon, and it is difficult to find an accurate physical model and related parameters to describe this phenomenon. In this paper, we propose a black box method, in which the haze is considered an image quality problem without using any physical model such as ASM. Analytically, we propose a novel dehazing equation to combine two mechanisms: interference item and detail enhancement item. The interference item estimates the haze information for dehazing the image, and then the detail enhancement item can repair and enhance the details of the dehazed image. Based on the new equation, we design an anti-interference and detail enhancement dehazing network (AIDEDNet), which is dramatically different from existing dehazing networks in that our network is fed into the haze-free images for training. Specifically, we propose a new way to construct a haze patch on the flight of network training. The patch is randomly selected from the input images and the thickness of haze is also randomly set. Numerous experiment results show that AIDEDNet outperforms the state-of-the-art methods on both synthetic haze scenes and real-world haze scenes.     

基于优化透射率的快速去雾方法

针对恢复后图像产生光晕和求大气光值时存在大量计算负担的情况,提出了一种的基于优化透射率的快速图像去雾新方法.采用直方图均衡化和双边滤波透射率修正机制来消除图像的光晕效应.此外,为了减少预估大气光值的计算负担,在大气模型的基础上,优化了大气光值的快速估计方法,使大气光值估计值更加准确.其次,为了改善去雾之后图片颜色暗淡的...     

暗原色先验与NL-CTV模型相结合的图像去雾方法

鉴于暗原色先验算法能复原不同雾浓度和场景深度的图像,而基于非局部算子概念的NL-CTV（Non-Local Color Total Variation）模型能较好地保持图像边缘和纹理等特征,融合暗原色先验与NL-CTV模型,提出了一种新型单幅彩色图像去雾模型。通过暗原色先验得到精确的大气光强度和大气传输函数,然后推导包含大气光强度和大气传输函数的非局部能量泛函,再通过引入辅助变量和Bregman迭代参数,为其设计相应的快速split Bregman算法来求解该模型。将该算法与He算法、暗原色先验和Retinex算法的实验结果进行分析比较,从而验证了该模型不论从视觉上,还是客观数据上都要优于其他两种算法。     

基于暗原色先验的快速单幅图像去雾算法

针对基于暗原色先验理论的单幅图像去雾算法中,由于某些场景下的雾天图像存在大面积明亮区域（如天空、水面或者偏白色物体等）不满足暗原色先验假设,从而导致去雾处理效果不好的问题。基于暗原色先验理论,提出了一种改进的单幅图像去雾算法。首先利用统计截断的方法估计出大气光值;然后对暗通道图进行中值滤波得到粗略估计的透射率图,并对明亮区域的透射率图进行自适应校正处理;最后将这些参数带入大气散射成像模型完成去雾处理。实验结果显示,相较于原算法而言,所提算法可以准确地选取出天空区域的像素点对大气光进行估计,有效降低明亮区域的色彩失真。通过不同算法对不同室外场景下采集的雾天图像的去雾效果的对比可知,所提算法在对明亮区域的处理上更加合理,可以较好地处理一些带有光源的图像,恢复出的图像具有很好的细节保持,视觉效果显著提高。所提算法对含有大面积明亮区域的雾天图像具有很好的增强处理效果,可以为图像分割、语义检索、智能分析等图像处理工作提供有效的预处理手段,对于交通监管、视频监控、行车视频记录、视觉导航等研究领域具有重要的意义。     

结合精确大气散射图计算的图像快速去雾

提出一种基于精确大气散射图的单幅图像快速去雾算法.首先基于大气散射光的特性,充分利用双边滤波保边缘的平滑特性,估测大气散射光和图像局部对比度,并通过引入像素值与平均灰度值的比较,得出更加准确的大气散射图,然后根据大气散射模型复原雾天图像.通过对获得的结果图像进行色调调整和局部去噪的优化处理,得到一幅视觉上较真实的清晰无雾图像.通过与几种典型的图像去雾算法比较,表明本文算法对于远景和深度发生突变的位置可以获得更好的去雾效果.同时,本文算法的时间复杂度与图像大小成线性关系,并且由于本文算法可以并行运行,因此可以进一步采用GPU加速,从而使得本文算法可以满足实时应用的需求.     

混合先验与加权引导滤波的图像去雾算法

目的 图像去雾是降低雾、霾、沙等低能见度成像环境对图像的退化影响,提高图像信息获取质量的过程。为了消除先验盲区,同时进一步提高去雾图像边缘细节的清晰度,提出一种混合先验与加权引导滤波的图像去雾算法。方法 首先改进大气光值估计方法,提高大气光值估计的准确性。然后利用混合先验理论求取双约束区域的大气透射率,一定程度上消除了先验盲区,提高了去雾算法的鲁棒性。最后利用加权引导滤波算法优化透射率图,提高了图像边缘细节的清晰度。结果 本文以通用去雾测试图像和小型无人机拍摄的雾天图像作为实验对象,通过对比分析4种组合步骤算法的复原效果,验证本文各步骤改进方法的合理性与整体算法的优越性。实验结果表明：混合先验理论改善了暗原色先验在明亮区域的失真现象和颜色衰减先验对浓雾处理上的不足,取得了较好的视觉效果;加权引导滤波改善了图像边缘模糊的现象,使复原后的图像边缘细节更加清晰;相较传统算法,本文算法视觉效果更好,去雾图像边缘细节更加明显,综合评价指标均值提升幅度较大。结论 针对有雾图像复原,通过理论分析和实验验证,说明了本文各步骤的改进具有一定的优越性,所提的算法具有较强的鲁棒性。     

视觉信息损失先验的图像分层去雾方法

目的 针对自然场景下含雾图像呈现出低对比度和色彩失真的问题,提出一种基于视觉信息损失先验的图像去雾算法,将透射图预估转化成求解信息损失函数最小值的目标规划问题。方法 首先通过输入图像的视觉特性将图像划分成含雾浓度不同的3个视觉区域。然后根据含雾图像的视觉先验知识构造视觉信息损失函数,通过像素值溢出映射规律对透射率取值范围进行约束,采用随机梯度下降法求解局部最小透射率图。最后将细化后的全局透射率图代入大气散射模型求解去雾结果。结果 结合现有的典型去雾算法进行仿真实验,本文算法能够有效地复原退化场景的对比度和清晰度,相比于传统算法,本文算法在算法实时性方面提升约20%。结论 本文算法在改善中、浓雾区域去雾效果的同时,提升了透射图预估的效率,对改善雾霾天气下视觉成像系统的能见度和鲁棒性具有重要意义。     

Fast image dehazing using guided joint bilateral filter

In this paper, we propose a new fast dehazing method from single image based on filtering. The basic idea is to compute an accurate atmosphere veil that is not only smoother, but also respect with depth information of the underlying image. We firstly obtain an initial atmosphere scattering light through median filtering, then refine it by guided joint bilateral filtering to generate a new atmosphere veil which removes the abundant texture information and recovers the depth edge information. Finally, we solve the scene radiance using the atmosphere attenuation model. Compared with exiting state of the art dehazing methods, our method could get a better dehazing effect at distant scene and places where depth changes abruptly. Our method is fast with linear complexity in the number of pixels of the input image; furthermore, as our method can be performed in parallel, thus it can be further accelerated using GPU, which makes our method applicable for real-time requirement.     

结合暗通道先验与Hessian 正则项的图像去雾

在雾天拍摄户外图像,其对比度和可见度均受到严重的影响。目前图像去雾方法 通常依赖于准确的透射率图,而二阶的Hessian 正则项具有保留精细结构同时抑制阶梯伪影的 能力,可提高图像的对比度和可见度。为此采用暗通道先验方法获得有雾图像大气光值初始透 射率图,提出一种结合Hessian 正则项的二阶变分模型来细化初始透射率图及去雾图像。利用 交替方向乘子法(ADMM),通过引入辅助变量,使拉格朗日乘子不断更新迭代,直到能量方程 收敛,输出去雾图像。采用LIVE Image Defogging 有雾图像数据库进行了仿真实验。通过对去 除薄雾和浓雾效果图的视觉质量和定量的评估,表明该方法得到的去雾图像清晰自然,纹理细 节保持效果较好。     

改进多尺度卷积神经网络的单幅图像去雾方法

针对当前已有的去雾方法容易造成天空区域存在光晕以及色彩失真的现象，提出了一种多尺度卷积结合大气散射模型的单幅图像去雾算法。将原始有雾图像与三个不同尺度的卷积核进行卷积，经过一系列特征学习后得到粗略的传播图，然后使用引导滤波器对其进行优化，得到精细化后的传播图。利用粗传播图和有雾图像计算出全局大气光。根据大气散射模型反推出无雾清晰图像。实验结果表明，该方法对天空区域的处理更加自然，在图像的纹理细节以及颜色失真上有较好的效果。     

Aerial image dehazing using a deep convolutional autoencoder

Aerial images and videos are extensively used for object detection and target tracking. However, due to the presence of thin clouds, haze or smoke from buildings, the processing of aerial data can be challenging. Existing single-image dehazing methods that work on ground-to-ground images, do not perform well on aerial images. Moreover, current dehazing methods are not capable for real-time processing. In this paper, a new end-to-end aerial image dehazing method using a deep convolutional autoencoder is proposed. Using the convolutional autoencoder, the dehazing problem is divided into two parts, namely, encoder, which aims extract important features to dehaze hazy regions and decoder, which aims to reconstruct the dehazed image using the down-sampled image received from the encoder. In this proposed method, we also exploit the superpixels in two different scales to generate synthetic thin cloud data to train our network. Since this network is trained in an end-to-end manner, in the test phase, for each input hazy aerial image, the proposed algorithm outputs a dehazed version without requiring any other information such as transmission map or atmospheric light value. With the proposed method, hazy regions are dehazed and objects within hazy regions become more visible while the contrast of non-hazy regions is increased. Experimental results on synthetic and real hazy aerial images demonstrate the superiority of the proposed method compared to existing dehazing methods in terms of quality and speed.

     

改进的暗原色先验理论视频去雾算法研究

针对暗原色先验算法出现的边缘残雾、天空区域彩色失真、去雾后图像偏暗以及实时性差等问题,提出了一种基于点暗原色先验和引导滤波的视频去雾算法。采用逐点式最小值滤波来消除块效应,并利用四叉树法来快速准确地估计大气光值,结合直方图均衡化技术来增强图像,改善视觉效果,同时利用图像采样技术和引导滤波优化算法提高速度。实验结果显示,该算法的去雾图像清晰,运算量小,适用范围广,鲁棒性好,适合实时视频去雾。     

结合天空区域识别的单幅图像去雾方法

针对现有图像去雾方法易于在天空区域引入负面视觉效果的缺陷,提出一个结合天空区域识别的单幅图像去雾方法;提出一个新的天空区域特征先验知识,并利用所提先验将雾天降质图像分割为天空与非天空区域;基于天空区域对大气光进行估计,并利用暗通道先验和导向全变分模型对非天空区域的透射率进行估计,从而基于大气散射模型获得去雾处理后的图像;使用一种邻域自适应的Retinex方法克服了去雾处理后图像偏暗的问题。对比实验证明,所提方法相比现有的类似方法具备更好的有效性及鲁棒性。     

暗通道先验图像去雾的大气光校验和光晕消除

目的 针对暗通道先验图像去雾方法中存在的大气光误判以及光晕效应等问题,提出一种基于大气光校验和光晕消除策略的改进算法。方法 首先,采用基于支持向量机的大气光校验方法对候选大气光的有效性进行判断,剔除太阳光、车灯等高光区域的干扰;然后,采用基于块偏移的精细透射率计算方法获得边缘保持的透射率,极大地抑制了无雾图像中光晕像素的数量;最后,采用基于导向滤波的光晕像素检测和校正方法进一步消除了残留的少量光晕像素。结果 本文算法有效抑制了大气光的误判现象,大大消除了光晕效应,提升了无雾图像的细节可辨认度,最终获得的无雾图像细节丰富、颜色深度感饱满。结论 本文算法在无雾图像的可见度增强等诸多方面超越了已有的方法,在视频监控、交通监管和目标识别等领域具有较大实用价值。