针对透明物体逆光图像对比度低、可视质量差、部分区域过度曝光、边缘信息模糊等问题,提出了一种改进MSRCR(Multi-Scale Retinex with Color Restoration)的透明物体逆光图像增强算法。首先,在MSRCR算法的基础上添加最小可觉差的倒数作...针对透明物体逆光图像对比度低、可视质量差、部分区域过度曝光、边缘信息模糊等问题,提出了一种改进MSRCR(Multi-Scale Retinex with Color Restoration)的透明物体逆光图像增强算法。首先,在MSRCR算法的基础上添加最小可觉差的倒数作为光照分量的调节因子,解决图像的色偏问题,得到准确清晰的透明物体边缘信息;然后,利用自适应对比度增强算法对原图像进行处理,得到亮度适中,对比度高的图像;最后,将两幅图像按亮度均值比例进行拉普拉斯金字塔融合,并进行线性拉伸。将该算法应用于安瓿瓶视觉尺寸测量,结果表明:改进MSRCR的透明物体逆光图像增强算法,能有效解决MSRCR算法的色偏问题,突显透明物体边缘细节信息,并保留亮度增强效果,将安瓿瓶的尺寸误差由0.35 mm降低到0.1mm,提高了透明物体尺寸测量精度。展开更多
为实现田间环境下对玉米苗和杂草的高精度实时检测,本文提出一种融合带色彩恢复的多尺度视网膜(Multi-scale retinex with color restoration,MSRCR)增强算法的改进YOLOv4tiny模型。首先,针对田间环境的图像特点采用MSRCR算法进行图像...为实现田间环境下对玉米苗和杂草的高精度实时检测,本文提出一种融合带色彩恢复的多尺度视网膜(Multi-scale retinex with color restoration,MSRCR)增强算法的改进YOLOv4tiny模型。首先,针对田间环境的图像特点采用MSRCR算法进行图像特征增强预处理,提高图像的对比度和细节质量;然后使用Mosaic在线数据增强方式,丰富目标检测背景,提高训练效率和小目标的检测精度;最后对YOLOv4tiny模型使用K-means++聚类算法进行先验框聚类分析和通道剪枝处理。改进和简化后的模型总参数量降低了45.3%,模型占用内存减少了45.8%,平均精度均值(Mean average precision,mAP)提高了2.5个百分点,在Jetson Nano嵌入式平台上平均检测帧耗时减少了22.4%。本文提出的PruneYOLOv4tiny模型与Faster RCNN、YOLOv3tiny、YOLOv43种常用的目标检测模型进行比较,结果表明:PruneYOLOv4tiny的mAP为96.6%,分别比Faster RCNN和YOLOv3tiny高22.1个百分点和3.6个百分点,比YOLOv4低1.2个百分点;模型占用内存为12.2 MB,是Faster RCNN的3.4%,YOLOv3tiny的36.9%,YOLOv4的5%;在Jetson Nano嵌入式平台上平均检测帧耗时为131 ms,分别是YOLOv3tiny和YOLOv4模型的32.1%和7.6%。可知本文提出的优化方法在模型占用内存、检测耗时和检测精度等方面优于其他常用目标检测算法,能够为硬件资源有限的田间精准除草的系统提供可行的实时杂草识别方法。展开更多
针对雾霾天气下交通信号灯定位准确率较低、图像增强时出现图像亮度不均匀的问题,该文提出一种基于改进的带色彩恢复的多尺度视网膜增强(Multi-Scale Retinex with Color Restoration,MSRCR)的雾霾天气下信号灯识别算法。首先利用改进的...针对雾霾天气下交通信号灯定位准确率较低、图像增强时出现图像亮度不均匀的问题,该文提出一种基于改进的带色彩恢复的多尺度视网膜增强(Multi-Scale Retinex with Color Restoration,MSRCR)的雾霾天气下信号灯识别算法。首先利用改进的MSRCR算法对有雾图像进行预处理,校正图像亮度并丰富图像细节;再利用最大稳定极值区域(Maximally Stable Extremal Regions,MSER)算法以及信号灯的背板信息确定信号灯的位置;最后将定位区域转换至HSV空间进行信号灯识别。结果表明,该方法能够在雾霾条件下有效地定位及识别交通信号灯。展开更多
针对低光照图像整体对比度低、细节显示不够清晰的问题,提出一种结合自适应伽马(Gamma)变换和带颜色恢复的多尺度Retinex(multi-scale Retinex with color restoration,MSRCR)算法的低光照图像增强方法。首先,为了动态地拉伸图像灰度值...针对低光照图像整体对比度低、细节显示不够清晰的问题,提出一种结合自适应伽马(Gamma)变换和带颜色恢复的多尺度Retinex(multi-scale Retinex with color restoration,MSRCR)算法的低光照图像增强方法。首先,为了动态地拉伸图像灰度值范围和提高图像对比度,进行RGB到HSV的颜色空间转换,采用多尺度融合方法提取图像的光照分量,并结合Gamma校正曲线实现图像自适应Gamma变换,提升图像的对比度;其次,针对自适应Gamma增强后的图像亮度较低的问题,采用MSRCR算法进一步提升图像亮度,并结合小波重构方法融合自适应Gamma变换后的图像和MSRCR增强后的图像;最后,由于小波重构后的图像局部存在过曝、过饱和的缺陷,结合基于模拟退火的自适应融合方法,将自适应Gamma变换后的图像和小波重构后的图像进行融合,得到最终的增强图像。所提方法既提高了低光照图像的对比度,使图像更有质感,又提升了图像的整体亮度,使暗部区域细节更加清晰;同时,弥补了MSRCR算法易出现色偏、颜色失真的缺陷。将所提方法应用于LOL低光照图像数据集,并与经典的图像增强算法进行对比。实验结果表明,所提方法使图像质量平均提高70%,图像结构相似性(structural similarity,SSIM)指数平均提高30%,图像信息熵平均提高20%,不仅提升了图像的对比度和亮度,而且避免了过曝、色偏、颜色失真等问题的出现。展开更多
During the recognition and localization process of green apple targets,problems such as uneven illumination,occlusion of branches and leaves need to be solved.In this study,the multi-scale Retinex with color restorati...During the recognition and localization process of green apple targets,problems such as uneven illumination,occlusion of branches and leaves need to be solved.In this study,the multi-scale Retinex with color restoration(MSRCR)algorithm was applied to enhance the original green apple images captured in an orchard environment,aiming to minimize the impacts of varying light conditions.The enhanced images were then explicitly segmented using the mean shift algorithm,leading to a consistent gray value of the internal pixels in an independent fruit.After that,the fuzzy attention based on information maximization algorithm(FAIM)was developed to detect the incomplete growth position and realize threshold segmentation.Finally,the poorly segmented images were corrected using the K-means algorithm according to the shape,color and texture features.The users intuitively acquire the minimum enclosing rectangle localization results on a PC.A total of 500 green apple images were tested in this study.Compared with the manifold ranking algorithm,the K-means clustering algorithm and the traditional mean shift algorithm,the segmentation accuracy of the proposed method was 86.67%,which was 13.32%,19.82%and 9.23%higher than that of the other three algorithms,respectively.Additionally,the false positive and false negative errors were 0.58%and 11.64%,respectively,which were all lower than the other three compared algorithms.The proposed method accurately recognized the green apples under complex illumination conditions and growth environments.Additionally,it provided effective references for intelligent growth monitoring and yield estimation of fruits.展开更多
针对海上图像利用带色彩恢复的多尺度Retinex算法(multi-scale Retinex with color restoration,MSRCR)不能有效去除雾及存在颜色纠偏过度问题,提出了一种基于全局亮度自适应均衡化的海上图像改进MSRCR算法。该算法首先计算海上雾天图...针对海上图像利用带色彩恢复的多尺度Retinex算法(multi-scale Retinex with color restoration,MSRCR)不能有效去除雾及存在颜色纠偏过度问题,提出了一种基于全局亮度自适应均衡化的海上图像改进MSRCR算法。该算法首先计算海上雾天图像的取反图;其次对原图像和取反后图像进行MSRCR运算;然后利用全局亮度自适应直方图均衡化处理,并将处理后的亮度与经MSRCR处理后的反射分量进行低频信号线性叠加;最后计算叠加后图像的均值和标准差,并采用自适应拉伸图像灰度实现图像色彩对比度的提升。实验证明该算法处理后的图像,前景突出、细节清晰、色彩丰富,对于海上图像除雾具有一定的意义。展开更多
文摘针对透明物体逆光图像对比度低、可视质量差、部分区域过度曝光、边缘信息模糊等问题,提出了一种改进MSRCR(Multi-Scale Retinex with Color Restoration)的透明物体逆光图像增强算法。首先,在MSRCR算法的基础上添加最小可觉差的倒数作为光照分量的调节因子,解决图像的色偏问题,得到准确清晰的透明物体边缘信息;然后,利用自适应对比度增强算法对原图像进行处理,得到亮度适中,对比度高的图像;最后,将两幅图像按亮度均值比例进行拉普拉斯金字塔融合,并进行线性拉伸。将该算法应用于安瓿瓶视觉尺寸测量,结果表明:改进MSRCR的透明物体逆光图像增强算法,能有效解决MSRCR算法的色偏问题,突显透明物体边缘细节信息,并保留亮度增强效果,将安瓿瓶的尺寸误差由0.35 mm降低到0.1mm,提高了透明物体尺寸测量精度。
文摘为实现田间环境下对玉米苗和杂草的高精度实时检测,本文提出一种融合带色彩恢复的多尺度视网膜(Multi-scale retinex with color restoration,MSRCR)增强算法的改进YOLOv4tiny模型。首先,针对田间环境的图像特点采用MSRCR算法进行图像特征增强预处理,提高图像的对比度和细节质量;然后使用Mosaic在线数据增强方式,丰富目标检测背景,提高训练效率和小目标的检测精度;最后对YOLOv4tiny模型使用K-means++聚类算法进行先验框聚类分析和通道剪枝处理。改进和简化后的模型总参数量降低了45.3%,模型占用内存减少了45.8%,平均精度均值(Mean average precision,mAP)提高了2.5个百分点,在Jetson Nano嵌入式平台上平均检测帧耗时减少了22.4%。本文提出的PruneYOLOv4tiny模型与Faster RCNN、YOLOv3tiny、YOLOv43种常用的目标检测模型进行比较,结果表明:PruneYOLOv4tiny的mAP为96.6%,分别比Faster RCNN和YOLOv3tiny高22.1个百分点和3.6个百分点,比YOLOv4低1.2个百分点;模型占用内存为12.2 MB,是Faster RCNN的3.4%,YOLOv3tiny的36.9%,YOLOv4的5%;在Jetson Nano嵌入式平台上平均检测帧耗时为131 ms,分别是YOLOv3tiny和YOLOv4模型的32.1%和7.6%。可知本文提出的优化方法在模型占用内存、检测耗时和检测精度等方面优于其他常用目标检测算法,能够为硬件资源有限的田间精准除草的系统提供可行的实时杂草识别方法。
文摘针对雾霾天气下交通信号灯定位准确率较低、图像增强时出现图像亮度不均匀的问题,该文提出一种基于改进的带色彩恢复的多尺度视网膜增强(Multi-Scale Retinex with Color Restoration,MSRCR)的雾霾天气下信号灯识别算法。首先利用改进的MSRCR算法对有雾图像进行预处理,校正图像亮度并丰富图像细节;再利用最大稳定极值区域(Maximally Stable Extremal Regions,MSER)算法以及信号灯的背板信息确定信号灯的位置;最后将定位区域转换至HSV空间进行信号灯识别。结果表明,该方法能够在雾霾条件下有效地定位及识别交通信号灯。
文摘针对低光照图像整体对比度低、细节显示不够清晰的问题,提出一种结合自适应伽马(Gamma)变换和带颜色恢复的多尺度Retinex(multi-scale Retinex with color restoration,MSRCR)算法的低光照图像增强方法。首先,为了动态地拉伸图像灰度值范围和提高图像对比度,进行RGB到HSV的颜色空间转换,采用多尺度融合方法提取图像的光照分量,并结合Gamma校正曲线实现图像自适应Gamma变换,提升图像的对比度;其次,针对自适应Gamma增强后的图像亮度较低的问题,采用MSRCR算法进一步提升图像亮度,并结合小波重构方法融合自适应Gamma变换后的图像和MSRCR增强后的图像;最后,由于小波重构后的图像局部存在过曝、过饱和的缺陷,结合基于模拟退火的自适应融合方法,将自适应Gamma变换后的图像和小波重构后的图像进行融合,得到最终的增强图像。所提方法既提高了低光照图像的对比度,使图像更有质感,又提升了图像的整体亮度,使暗部区域细节更加清晰;同时,弥补了MSRCR算法易出现色偏、颜色失真的缺陷。将所提方法应用于LOL低光照图像数据集,并与经典的图像增强算法进行对比。实验结果表明,所提方法使图像质量平均提高70%,图像结构相似性(structural similarity,SSIM)指数平均提高30%,图像信息熵平均提高20%,不仅提升了图像的对比度和亮度,而且避免了过曝、色偏、颜色失真等问题的出现。
基金This work was supported by the National High Technology Research and Development Program of China(863 Program)[Grant number 2013AA10230402]Agricultural Science and Technology Project of Shaanxi Province[Grant number 2016NY-157]Fundamental Research Funds of Central Universities[Grant number 2452016077].The authors appreciate the above funding organizations for their financial supports.The authors would also like to thank the helpful comments and suggestions provided by all the authors cited in this article and the anonymous reviewers.
文摘During the recognition and localization process of green apple targets,problems such as uneven illumination,occlusion of branches and leaves need to be solved.In this study,the multi-scale Retinex with color restoration(MSRCR)algorithm was applied to enhance the original green apple images captured in an orchard environment,aiming to minimize the impacts of varying light conditions.The enhanced images were then explicitly segmented using the mean shift algorithm,leading to a consistent gray value of the internal pixels in an independent fruit.After that,the fuzzy attention based on information maximization algorithm(FAIM)was developed to detect the incomplete growth position and realize threshold segmentation.Finally,the poorly segmented images were corrected using the K-means algorithm according to the shape,color and texture features.The users intuitively acquire the minimum enclosing rectangle localization results on a PC.A total of 500 green apple images were tested in this study.Compared with the manifold ranking algorithm,the K-means clustering algorithm and the traditional mean shift algorithm,the segmentation accuracy of the proposed method was 86.67%,which was 13.32%,19.82%and 9.23%higher than that of the other three algorithms,respectively.Additionally,the false positive and false negative errors were 0.58%and 11.64%,respectively,which were all lower than the other three compared algorithms.The proposed method accurately recognized the green apples under complex illumination conditions and growth environments.Additionally,it provided effective references for intelligent growth monitoring and yield estimation of fruits.
文摘针对海上图像利用带色彩恢复的多尺度Retinex算法(multi-scale Retinex with color restoration,MSRCR)不能有效去除雾及存在颜色纠偏过度问题,提出了一种基于全局亮度自适应均衡化的海上图像改进MSRCR算法。该算法首先计算海上雾天图像的取反图;其次对原图像和取反后图像进行MSRCR运算;然后利用全局亮度自适应直方图均衡化处理,并将处理后的亮度与经MSRCR处理后的反射分量进行低频信号线性叠加;最后计算叠加后图像的均值和标准差,并采用自适应拉伸图像灰度实现图像色彩对比度的提升。实验证明该算法处理后的图像,前景突出、细节清晰、色彩丰富,对于海上图像除雾具有一定的意义。