为了提高夜间疲劳驾驶检测的准确率,在现有低光增强算法Zero-DCE(Zero-Reference Deep Curve Estimation)的基础上,提出改进Zero-DCE的低光增强算法。首先,引入上下采样结构,减少噪声影响。同时,引入注意力门控机制,提高网络对图像中人...为了提高夜间疲劳驾驶检测的准确率,在现有低光增强算法Zero-DCE(Zero-Reference Deep Curve Estimation)的基础上,提出改进Zero-DCE的低光增强算法。首先,引入上下采样结构,减少噪声影响。同时,引入注意力门控机制,提高网络对图像中人脸区域的敏感性,有效提高网络的检测率。然后,针对噪声相关问题,提出改进的核选择模块。进一步,使用MobileNet的深度可分离卷积替换Zero-DCE的标准卷积,提高网络的检测速度。最后,通过人脸关键点检测网络和分类网络,判断驾驶员的疲劳状态。实验表明,在夜间环境下,相比现有的疲劳驾驶检测算法,文中算法在人脸检测的准确率和眼睛状态的识别率上都有所提升,取得较令人满意的检测效果。展开更多
Automated object detection has received the most attention over the years.Use cases ranging from autonomous driving applications to military surveillance systems,require robust detection of objects in different illumi...Automated object detection has received the most attention over the years.Use cases ranging from autonomous driving applications to military surveillance systems,require robust detection of objects in different illumination conditions.State-of-the-art object detectors tend to fare well in object detection during daytime conditions.However,their performance is severely hampered in night light conditions due to poor illumination.To address this challenge,the manuscript proposes an improved YOLOv5-based object detection framework for effective detection in unevenly illuminated nighttime conditions.Firstly,the preprocessing strategies involve using the Zero-DCE++approach to enhance lowlight images.It is followed by optimizing the existing YOLOv5 architecture by integrating the Convolutional Block Attention Module(CBAM)in the backbone network to boost model learning capability and Depthwise Convolutional module(DWConv)in the neck network for efficient compression of network parameters.The Night Object Detection(NOD)and Exclusively Dark(ExDARK)dataset has been used for this work.The proposed framework detects classes like humans,bicycles,and cars.Experiments demonstrate that the proposed architecture achieved a higher Mean Average Precision(mAP)along with a reduction in model size and total parameters,respectively.The proposed model is lighter by 11.24%in terms of model size and 12.38%in terms of parameters when compared to baseline YOLOv5.展开更多
Several 2-D displacement sensing methods are reviewed. As to the crossdiffraction grating, there is no absolute zero-reference. In regards to the optical fiber method,the output signal is affected greatly by the quali...Several 2-D displacement sensing methods are reviewed. As to the crossdiffraction grating, there is no absolute zero-reference. In regards to the optical fiber method,the output signal is affected greatly by the quality of the reflecting surface and it is hard to gethigh resolution. Considering the concentric-circle gratings, the displacement can only be gainedwith complicated calculating of the experiment data. Compared with the advantages and limitations ofthe methods above, a novel 2-D zero-reference mark is especially proposed and demonstrated. Thiskind of mark has an absolute zero-reference when used in pair, and the experimental result is simpleto dispose. By superimposing a pair of specially coded 2-D marks, the correct alignment position ofthe two marks can be detected by the maximum output of the sharp intensity peak. And each slope ofthe peak is of good linearity which can be used to achieve high resolution in positioning andalignment in two dimensions. Design and fabrication of such 2-D zero-reference marks are introducedin detail. The experiment results are agreed with the theoretical ones.展开更多
Unmanned aerial vehicle (UAV) target tracking tasks can currently be successfully completed in daytime situations with enough lighting, but they are unable to do so in nighttime scenes with inadequate lighting, poor c...Unmanned aerial vehicle (UAV) target tracking tasks can currently be successfully completed in daytime situations with enough lighting, but they are unable to do so in nighttime scenes with inadequate lighting, poor contrast, and low signal-to-noise ratio. This letter presents an enhanced low-light enhancer for UAV nighttime tracking based on Zero-DCE++ due to its ad-vantages of low processing cost and quick inference. We developed a light-weight UCBAM capable of integrating channel information and spatial features and offered a fully considered curve projection model in light of the low signal-to-noise ratio of night scenes. This method significantly improved the tracking performance of the UAV tracker in night situations when tested on the public UAVDark135 and compared to other cutting-edge low-light enhancers. By applying our work to different trackers, this search shows how broadly applicable it is.展开更多
该文主要对Zero-DCE (zero-reference deep curve estimation)图像增强网络进行改进.针对图像在每层卷积过后,图像内容细节随之丢失和噪声问题.提出改进网络结构,卷积层保留图像的主要内容,增加反卷积层则用来补偿细节信息.另外通过传...该文主要对Zero-DCE (zero-reference deep curve estimation)图像增强网络进行改进.针对图像在每层卷积过后,图像内容细节随之丢失和噪声问题.提出改进网络结构,卷积层保留图像的主要内容,增加反卷积层则用来补偿细节信息.另外通过传递卷积层的特征图到反卷积层,有助于解码器拥有更多的图像细节信息,从而得到更好的干净图像.此外引进残差网络,对输入噪声图像和输出干净图像做差用于学习一个残差,在降噪的同时也提升了图像清晰度.最后通过图像质量评估方法 PSNR (peak signal to noise ratio)和SSIM (structural similarity index)以及傅里叶变换进行测试分析,结果表明提出的改进结构可以增加图像的细节信息并达到降噪效果.展开更多
文摘为了提高夜间疲劳驾驶检测的准确率,在现有低光增强算法Zero-DCE(Zero-Reference Deep Curve Estimation)的基础上,提出改进Zero-DCE的低光增强算法。首先,引入上下采样结构,减少噪声影响。同时,引入注意力门控机制,提高网络对图像中人脸区域的敏感性,有效提高网络的检测率。然后,针对噪声相关问题,提出改进的核选择模块。进一步,使用MobileNet的深度可分离卷积替换Zero-DCE的标准卷积,提高网络的检测速度。最后,通过人脸关键点检测网络和分类网络,判断驾驶员的疲劳状态。实验表明,在夜间环境下,相比现有的疲劳驾驶检测算法,文中算法在人脸检测的准确率和眼睛状态的识别率上都有所提升,取得较令人满意的检测效果。
文摘Automated object detection has received the most attention over the years.Use cases ranging from autonomous driving applications to military surveillance systems,require robust detection of objects in different illumination conditions.State-of-the-art object detectors tend to fare well in object detection during daytime conditions.However,their performance is severely hampered in night light conditions due to poor illumination.To address this challenge,the manuscript proposes an improved YOLOv5-based object detection framework for effective detection in unevenly illuminated nighttime conditions.Firstly,the preprocessing strategies involve using the Zero-DCE++approach to enhance lowlight images.It is followed by optimizing the existing YOLOv5 architecture by integrating the Convolutional Block Attention Module(CBAM)in the backbone network to boost model learning capability and Depthwise Convolutional module(DWConv)in the neck network for efficient compression of network parameters.The Night Object Detection(NOD)and Exclusively Dark(ExDARK)dataset has been used for this work.The proposed framework detects classes like humans,bicycles,and cars.Experiments demonstrate that the proposed architecture achieved a higher Mean Average Precision(mAP)along with a reduction in model size and total parameters,respectively.The proposed model is lighter by 11.24%in terms of model size and 12.38%in terms of parameters when compared to baseline YOLOv5.
基金This project is supported by National Natural Science Foundation of China(No.50335050, No.50275140)Specialized Research Foundation for Doctoral Program of Higher Education (SRFDP) of China(No. 20030358020).
文摘Several 2-D displacement sensing methods are reviewed. As to the crossdiffraction grating, there is no absolute zero-reference. In regards to the optical fiber method,the output signal is affected greatly by the quality of the reflecting surface and it is hard to gethigh resolution. Considering the concentric-circle gratings, the displacement can only be gainedwith complicated calculating of the experiment data. Compared with the advantages and limitations ofthe methods above, a novel 2-D zero-reference mark is especially proposed and demonstrated. Thiskind of mark has an absolute zero-reference when used in pair, and the experimental result is simpleto dispose. By superimposing a pair of specially coded 2-D marks, the correct alignment position ofthe two marks can be detected by the maximum output of the sharp intensity peak. And each slope ofthe peak is of good linearity which can be used to achieve high resolution in positioning andalignment in two dimensions. Design and fabrication of such 2-D zero-reference marks are introducedin detail. The experiment results are agreed with the theoretical ones.
文摘Unmanned aerial vehicle (UAV) target tracking tasks can currently be successfully completed in daytime situations with enough lighting, but they are unable to do so in nighttime scenes with inadequate lighting, poor contrast, and low signal-to-noise ratio. This letter presents an enhanced low-light enhancer for UAV nighttime tracking based on Zero-DCE++ due to its ad-vantages of low processing cost and quick inference. We developed a light-weight UCBAM capable of integrating channel information and spatial features and offered a fully considered curve projection model in light of the low signal-to-noise ratio of night scenes. This method significantly improved the tracking performance of the UAV tracker in night situations when tested on the public UAVDark135 and compared to other cutting-edge low-light enhancers. By applying our work to different trackers, this search shows how broadly applicable it is.
文摘该文主要对Zero-DCE (zero-reference deep curve estimation)图像增强网络进行改进.针对图像在每层卷积过后,图像内容细节随之丢失和噪声问题.提出改进网络结构,卷积层保留图像的主要内容,增加反卷积层则用来补偿细节信息.另外通过传递卷积层的特征图到反卷积层,有助于解码器拥有更多的图像细节信息,从而得到更好的干净图像.此外引进残差网络,对输入噪声图像和输出干净图像做差用于学习一个残差,在降噪的同时也提升了图像清晰度.最后通过图像质量评估方法 PSNR (peak signal to noise ratio)和SSIM (structural similarity index)以及傅里叶变换进行测试分析,结果表明提出的改进结构可以增加图像的细节信息并达到降噪效果.
