基于超像素暗通道和自动色阶优化的图像去雾算法

针对暗通道先验(dark channel prior, DCP)复原图像中的光晕现象、明亮区域色彩失真、环境光估计不准确等问题,提出了基于超像素暗通道和自动色阶优化的单幅图像去雾算法。首先,由改进的White Patch Retinex算法增强图像并计算精确环境光。接着,在传统暗通道去雾算法中引入超像素图像分割和引导滤波算法,使透射率估计的稳健性与精确性得以提升。然后,采用自适应容差对明亮区域的透射率进行补偿,有效抑制明亮区域色彩失真问题。最后,以自动色阶优化算法提高图像对比度。将本文去雾算法与其他算法从主观和客观两个维度进行比较,实验结果表明：采用不同算法对不同浓度的自然雾图进行对比实验,信息熵提高0.2 bit,峰值信噪比(peak signal-to-noise ratio,PSNR)提高0.8 dB,运行效率提高。该算法对不同浓度含雾图像具有良好的适应性,复原图像色彩真实、纹理清晰、细节丰富,去雾效果良好。     

基于改进暗通道和自适应容差的图像去雾算法

传统暗通道去雾算法计算的透射率图存在块效应,易造成复原图像白边现象,同时图像中天空、白云等明亮区域不适用暗通道原理,易引起去雾图像失真。本文结合引导滤波和自适应容差机制提出了一种基于多尺度暗通道和自适应容差的去雾算法,可有效避免以上问题。首先,计算3种不同尺寸滤波窗口下的透射率初估计,并对估计结果进行有效融合;接着,通过引导滤波对透射率进行细化,以获得鲁棒性和准确性更好的多尺度透射率图;然后,引入自适应容差策略对图像中明亮区域的透射率进行修正;最后,由于暗通道去雾图像整体亮度偏暗,因此对去雾图像的亮度和对比度进行亮度补偿。实验结果表明,采用不同算法对不含和少量天空区域的图像去雾,信息熵约提高0.2 bit/symbol,平均梯度约提高0.5,PSNR约提高8 dB。对较多和大量天空区域图像去雾,PSNR约提高3 dB,SSIM约提高0.1。较好地实现了去雾图像细节清晰、颜色可靠且明亮区域去雾效果良好等要求。     

基于暗原色先验与反图像的图像去雾算法

讨论了暗原色先验去雾算法的原理,指出其有去雾时在天空等明亮区域色彩失真的缺陷。针对这个缺陷提出了改进方法,该方法通过估算反图像的透射率修正透射率图以避免色彩失真。该算法可弥补传统算法在明亮区域透射率估算值较低导致色彩失真的不足。实验结果表明该算法有效。     

一种快速的单幅图像去雾算法

为了解决基于暗原色先验的单幅图像去雾算法运行效率低,以及去雾后在图像的明亮灰白区域存在图像色彩失真的问题,提出一种快速有效的单幅图像去雾算法.该算法基于HSI色彩空间进行粗略的透射率以及大气光的估计;然后,用导向滤波对粗略的透射率进行平滑,再利用阈值法对灰白明亮区域的透射率进行修正,得到最终的透射率;最后,进行色彩调整得到复原图像.实验结果表明,本文算法具有很高的运行效率,能有效提高复原图像的清晰度和对比度.     

结合区域生长与容差机制的暗通道去雾算法

针对传统的暗通道先验算法在处理带有大面积天空区域的有雾图像时出现明显的块效应、色彩失真和亮度偏低等问题,提出了一种结合区域生长与容差机制的去雾算法。首先通过灰度图腐蚀求出暗通道;接着利用种子区域生长法分割出天空区域,并把天空区域的平均灰度值作为大气光值估计;然后结合大气散射模型得到粗略的透视率,并采用改良的容差机制和引导滤波对透视率进行修正和细化;最后,引入Retinex法对图像进行后处理,进一步调整色彩和亮度。实验结果表明,本文提出的去雾算法对带有天空区域的图像去雾效果明显,天空区域的色彩有了显著改善,图像整体清晰明亮。     

基于暗原色优化算法的去雾研究

针对基于传统的暗原色先验去雾算法中,由于某些场景下的雾天图像存在大面积明亮区域无法满足暗原色先验的假设,导致去雾效果不佳。文中就此问题提出了一种改进的去雾算法,基于McCartnet的理论建立大气散射模型,根据暗通道理论粗略估计透射率,之后引入容差参数并设置阈值,重新计算明亮区域的透射率,从而实现对明亮区域透射率的自校正。针对于复原图像色彩较暗的问题,采用改进的线性亮度调整方法来调节图像的亮度。实验结果显示,相较于原算法而言,改进算法可以有效的对大气光值进行估计,降低明亮区域的色彩失真,复原的图像可以保持足够的亮度,同时不丢失图像的细节,视觉效果显著提高。     

基于暗原色与逆暗原色融合的含明亮区域图像去雾

针对暗原色先验模型对于图像明亮区域不适应,暗原色估计偏大,导致透射率估计偏小,出现色彩失真现象,本文介绍一种新的暗原色修正方法。提出一种逆暗原色概念,将雾化图像的暗原色与逆暗原色进行融合处理得到一种新的修正暗原色,从而获得比较真实的明亮区域透射率,有效消除了明亮区域的色彩失真。以有效细节强度、色调还原程度、结构信息及综合测评作为图像质量评价指标,与目前流行算法进行对比实验,本文算法的色调还原程度指标平均值提高41.1%,综合测评指标平均值提高48.7%。实验结果表明,本文算法在改善明亮区域色彩失真及提高去雾图像总体质量方面优于目前流行算法。     

改进的基于暗原色先验的图像去雾算法

分析讨论了原暗原色先验去雾算法原理,指出其不足之处并推导出改进方法.通过引入一种容差机制,算法能更有效地处理不满足暗原色先验的明亮区域,纠正了这类区域错误估计的透射率,从而克服原算法在处理这些区域时产生的色彩失真.实验结果表明,这样的修改切实可行,恢复图像消除了色彩失真,视觉效果得以显著提高.     

基于改进暗通道算法的红外图像去雾

针对暗通道先验去雾算法在滤波窗口较小时得到的去雾后图像存在颜色失真、对引入因子的选择及明亮区域透射率的计算存在误差、去雾后图像的抗噪性能较弱等问题,提出基于受限光值与透射率修正的图像去雾算法。首先对大气光值A设定阈值上限;其次通过建立引入因子与结构相似度的对应关系以获得最佳引入因子;并在引入容差机制的基础上进一步提出透射率优化方法;最后在所提去雾算法基础上融入高斯滤波算法,并调整去雾图像亮度以提升可视化效果。仿真结果表明,运用所提算法得到的图像PSNR值、SSIM值、Entropy值相对于改进前分别平均提升9.9964 dB、8.57%、0.3732,验证了所提算法的有效性与优越性。     

改进暗通道窗口与透射率修正的图像去雾

雾霾天气下,航拍设备无法准确获取图像信息,为解决此问题,提出一种改进暗通道窗口与透射率修正的图像去雾算法。首先,用超像素分割有雾图像得到景深一致的局部窗口,在每个窗口内计算暗通道,同时根据大气光特性结合超像素进行大气光估计;然后,通过引导滤波细化透射率,并建立自适应容差机制来修正图像明亮区域的透射率;最后,反演大气散射模型还原清晰图像。实验结果证明,该算法所得结果图像细节清晰、颜色自然,且能处理多类雾天图像,鲁棒性更好,与经典算法相比具有显著优势。     

基于天空约束暗通道先验的图像去雾

针对现有暗通道图像去雾算法存在的天空色彩失真,景物边缘光晕效应等问题,本文提出了基于暗通道理论的改进去雾算法.由于暗原色先验理论不适用于天空区域,本文将引导滤波用于天空区域的细化分割,准确估计包含天空区域图像的大气光照强度,解决了天空色彩失真问题;其次,利用中值滤波得到详细边缘信息,进而得到更为清晰的透射率,有效抑制了景物边缘光晕问题;最后针对去雾后图像偏暗的问题,在HSV空间对亮度分量V通道进行增强处理.实验结果表明,针对带雾图像,本文算法能够有效地去雾,改善天空区域色彩失真以及景物边缘光晕问题.     

Image restoration algorithm based on compensated transmission and adaptive haze concentration coefficient

Aiming at the drawbacks of traditional dark channel prior,which was prone to distortion and Halo effects in the bright areas,a haze image restoration algorithm based on compensated transmission and adaptive haze concentration coefficient was proposed.First of all,a Gaussian function was used to fit the attenuation relationship between the haze and haze-free image,and the compensation transmission was set to correct the initial transmission.Then the characteristics of haze was analyzed,the concept of brightness entropy was introduced and the bright channel operation was performed to acquire entropy value with pixel by pixel.Combined with the Gaussian pyramid to extract texture features,the haze distribution map was obtained.An adaptive transformation was established to seek the haze concentration coefficient and get the accurate transmission.Finally,the recovery results were restored by improved atmospheric light value and atmospheric scattering model.Experimental results show that the recovered image has better color and detail,the degree of dehazing is thorough,the brightness is appropriate,and the effect is clear and natural.     

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.     

暗原色先验自适应图像去雾方法

针对传统暗原色先验去雾算法存在的亮区域色彩失真、去雾参 数人工设定等问题,提出了一种基于暗原色先验改进的自适应图像去雾方法。首先,提出快 速OSTU法对雾霾图像亮暗区域进行自适应分割,并分区域获取亮暗区域的暗原色值;其次, 根据亮区域分布情况,对不同区域大气光强进行自适应估计;接着,通过分析雾霾图像直方 图特征,提出采用灰度集中度法自适应计算去雾系数;然后,运用色阶自适应调整方法进行 输出图像的色彩调整;最后,通过开展对比实验,验证了本文算法的优越性。主客观 评价结果表明:本文方法无需人为设定去雾参数,具有较好的 鲁棒性,可适用于多种浓度、 各种场景雾霾图像的去雾处理,获取的图像清晰、色彩自然,对比度高。     

Image defogging algorithm based on guided filtering and adaptive tolerance

Aiming at the problem of distortion of dark channel algorithm in defogging the sky region,an improved image defogging algorithm based on the guided filtering and adaptive tolerance mechanism was proposed.Firstly,the fitted transmissivity graphs were calculated for the windows with different sizes.Then,the transmissivity was further refined by the guided filtering technique.After that,the transmissivity in sky area was revised by an adaptive tolerance mechanism.Finally,the restored image was converted from RGB space to HSV space,and thus the brightness and contrast of the images could be color compensated.Experimental results show that the proposed algorithm restores the images effectively and obtain preferable defogging results with regard to the processing of bright areas such as the sky areas.     

Pre-processing for single image dehazing

Existing single image haze removal algorithms could suffer from noise amplification in sky regions and possible color distortion in restored images due to noise in haze images. In this paper, a simple pre-processing tool is introduced for single image haze removal so as to reduce the effect of noise in the restored image. The input image is first decomposed into base and detail layers by using a weighted guided image filter (WGIF). The airlight and transmission map are estimated from the base layer. In order to restore the objects close to the camera well, the decomposition of haze image is adaptive to the value of the transmission map. If the transmission map of a pixel is small, it is decomposed into two layers, otherwise, not decomposed. Since the noise is included in the detail layer, the base layer is amplified in the final image if the haze image is decomposed. Experiments show that the proposed pre-processing tool can indeed be applied to improve the state-of-the-art haze removal algorithms.     

基于暗原色先验的嵌入式图像增强系统

针对彩色直方图均衡化算法颜色易失真的缺点,提出了一种基于暗原色先验的快速图像增强算法。首先求取全局暗原色图,然后估计透过率图和大气光成分图,最后根据大气散射模型恢复出图像中所有像素的灰度值。结合实际应用,以高性能DSP芯片TMS320DM6437作为中央处理器,结合现场可编程门阵列FPGA构成外围电路逻辑控制,搭建了嵌入式高速图像增强处理平台。基于该平台用真实图像验证了本文提出的算法。实验结果表明,本系统在提高色彩和对比度的同时,有效地还原了场景中物体的颜色,获得了较好的增强效果,同时算法运行时间少,能够满足工程项目的要求。