A progressive framework for rotary motion deblurring

The rotary motion deblurring is an inevitable procedure when the imaging seeker is mounted in the rotating missiles.Traditional rotary motion deblurring methods suffer from ringing artifacts and noise,especially for large blur extents.To solve the above problems,we propose a progressive rotary motion deblurring framework consisting of a coarse deblurring stage and a refinement stage.In the first stage,we design an adaptive blur extents factor(BE factor)to balance noise suppression and details reconstruction.And a novel deconvolution model is proposed based on BE factor.In the second stage,a triplescale deformable module CNN(TDM-CNN)is designed to reduce the ringing artifacts,which can exploit the 2D information of an image and adaptively adjust spatial sampling locations.To establish a standard evaluation benchmark,a real-world rotary motion blur dataset is proposed and released,which includes rotary blurred images and corresponding ground truth images with different blur angles.Experimental results demonstrate that the proposed method outperforms the state-of-the-art models on synthetic and real-world rotary motion blur datasets.The code and dataset are available at https://github.com/JinhuiQin/RotaryDeblurring.

Camera Independent Motion Deblurring in Videos Using Machine Learning

In this paper, we will be looking at our efforts to find a novel solution for motion deblurring in videos. In addition, our solution has the requirement of being camera-independent. This means that the solution is fully implemented in software and is not aware of any of the characteristics of the camera. We found a solution by implementing a Convolutional Neural Network-Long Short Term Memory (CNN-LSTM) hybrid model. Our CNN-LSTM is able to deblur video without any knowledge of the camera hardware. This allows it to be implemented on any system that allows the camera to be swapped out with any camera model with any physical characteristics.

Parameter Estimation for Blur Image Combining Defocus and Motion Blur using Cepstrum Analysis

The degraded parameters recognition is very important for the restoration of blurred images. There are two common types of blurs for most camera systems. One is the defocus blur due to the optical system's defocus phenomenon and the other is the motion blur due to the relative movement between the objectives and the camera. Compared with the recognition for the blurred image with only one blur model, the parameter estimation for the picture combining defocus and motion blur models is a more complicated mission. A method was proposed for computer to estimate the parameters of defocus blur and motion blur in cepstrum area simultaneously. According to characters of both blur models in the frequency domain, an adjustment approach was suggested in the frequency area and then convert to the cepstrum field to increase the accuracy of measurement.

Blind-restoration-based blind separation method for permuted motion blurred images

A novel single-channel blind separation algorithm for permuted motion blurred images is proposed by using blind restoration in this paper. Both the motion direction and the length of the point spread function （PSF） are estimated by Radon transformation and extrema a detection. Using the estimated blur parameters, the permuted image is restored by performing the L-R blind restoration method. The permutation mixing matrices can be accurately estimated by classifying the ringing effect in the restored image, thereby the source images can be separated. Simulation results show a better separation efficiency for the permuted motion blurred image with various permutation operations. The proposed algorithm indicates a better performance on the robustness against Gaussian noise and lossy JPEG compression.

3D Reconstruction for Motion Blurred Images Using Deep Learning-Based Intelligent Systems

The 3D reconstruction using deep learning-based intelligent systems can provide great help for measuring an individual’s height and shape quickly and accurately through 2D motion-blurred images.Generally,during the acquisition of images in real-time,motion blur,caused by camera shaking or human motion,appears.Deep learning-based intelligent control applied in vision can help us solve the problem.To this end,we propose a 3D reconstruction method for motion-blurred images using deep learning.First,we develop a BF-WGAN algorithm that combines the bilateral filtering(BF)denoising theory with a Wasserstein generative adversarial network(WGAN)to remove motion blur.The bilateral filter denoising algorithm is used to remove the noise and to retain the details of the blurred image.Then,the blurred image and the corresponding sharp image are input into the WGAN.This algorithm distinguishes the motion-blurred image from the corresponding sharp image according to the WGAN loss and perceptual loss functions.Next,we use the deblurred images generated by the BFWGAN algorithm for 3D reconstruction.We propose a threshold optimization random sample consensus(TO-RANSAC)algorithm that can remove the wrong relationship between two views in the 3D reconstructed model relatively accurately.Compared with the traditional RANSAC algorithm,the TO-RANSAC algorithm can adjust the threshold adaptively,which improves the accuracy of the 3D reconstruction results.The experimental results show that our BF-WGAN algorithm has a better deblurring effect and higher efficiency than do other representative algorithms.In addition,the TO-RANSAC algorithm yields a calculation accuracy considerably higher than that of the traditional RANSAC algorithm.

Numericals for total variation-based reconstruction of motion blurred images

In this paper image with horizontal motion blur, vertical motion blur and angled motion blur are considered. We construct several difference schemes to the highly nonlinear term △↓.（△↓u/√｜△↓｜^2＋β） of the total variation-based image motion deblurring problem. The large nonlinear system is linearized by fixed point iteration method. An algebraic multigrid method with Krylov subspace acceleration is used to solve the corresponding linear equations as in [7]. The algorithms can restore the image very well. We give some numerical experiments to demonstrate that our difference schemes are efficient and robust.

Restoration of space-variant blurred image based on motion-blurred target segmentation

In imaging on moving target, it is easy to get space- variant blurred image. In order to recover the image and gain recognizable target, an approach to recover the space-variant blurred image is presented based on image segmentation. Be- cause of motion blur＇s convolution process, the pixels of observed image＇s target and background will be displaced and piled up to produce two superposition regions. As a result, the neighbor- ing pixels in the superposition regions will have similar grey level change. According to the pixel＇s motion-blur character, the target＇s blurred edge of superposition region could be detected. Canny operator can be recurred to detect the target edge which parallels the motion blur direction. Then in the segmentation process, the whole target image which has the character of integral convolution between motion blur and real target image can be obtained. At last, the target image is restored by deconvolution algorithms with adding zeros. The restoration result indicates that the approach can effectively solve the kind of problem of space-variant motion blurred image restoration.

Blind Motion Deblurring for Online Defect Visual Inspection

Online defect visual inspection (ODVI) works while the object has to be static, otherwise the relative motion between camera and object will create motion blur in images. In order to implement ODVI in dynamic scene, it developes one blind motion deblurring method whose objective is to estimate blur kernel parameters precisely. In the proposed method, Radon transform on superpixels determinated the blur angle, and the autocorrelation function based on magnitude (AFM) of the preprocessed blurred image was utilized to identify the blur length. With the projection relationship discussed in this study, it will be unnecessary to rotate the blurred image or the axis. The proposed method is of high accuracy and robustness to noise, and it can somehow handle saturated pixels. To validate the proposed method, experiments have been carried out on synthetic images both in noise free and noisy situations. The results show that the method outperforms existing approaches. With the modified Richardson– Lucy deconvolution, it demonstrates that the proposed method is effective for ODVI in terms of subjective visual quality.

基于改进维纳滤波算法的运动模糊二维码图像复原方法

针对二维码在动态工业产品检测中,容易发生运动模糊,导致识别难度加大的问题,设计了一种基于改进维纳滤波的运动模糊二维码图像复原方法。在传统的维纳滤波图像复原过程中,由于正则项K值的影响,导致复原效果存在差异,结合了遗传算法,通过自适应寻优的方法实现了K值的估计,完成了图像的复原。实验结果表明:改进算法比传统算法复原以后的图像峰值信噪比(PSNR)提高了约4 dB左右,该方法可以有效地还原出运动模糊二维码图像,提高了二维码的识别的效率。

基于运动偏移信息估计的图像去运动模糊算法

针对现有动态场景图像去运动模糊算法难以有效复原非均匀复合运动模糊的问题,通过引入相机曝光轨迹来表示模糊图像中包含的运动信息,并据此提出了一种新的运动偏移估计框架,用于对潜在清晰图像在多个离散时间点的像素运动偏移进行建模。结合估计出的运动偏移信息,提出了一种融合像素运动偏移信息的多尺度单幅图像去模糊网络框架。该框架通过可变形卷积在解码阶段对运动偏移信息进行融合,给定每一像素点不同的运动约束。经过网络的多尺度编解码结构,得到每一尺度上每一像素点的预测值,实现了端对端的模糊图像复原。在GoPro和HIDE数据集上的实验结果表明,该算法能有效改善图像质量,峰值信噪比平均提升1.9 dB,结构相似度平均提升0.03。

基于非局部先验红外运动模糊图像复原方法

为了实现红外运动模糊图像复原,采用了基于红外图像的非局部稀疏先验约束建模方法。通过分析红外运动模糊成像特征,在盲反卷积框架下,提出了一种基于运动信息的图像非局部稀疏先验约束建模方法,通过计算图像的运动模糊核,进而复原运动模糊图像。结果表明,所提出的基于运动信息的图像非局部稀疏先验约束方法,针对性强,能有效地复原运动幅值较大的红外运动模糊图像;概率模糊检测、结构相似度和峰值信噪比均有不同程度的提高,尤其是峰值信噪比提高接近8%,且运动幅值越大,复原结果越明显。本研究为红外成像系统的应用打下了基础。

基于深度模糊学习的牙科CBCT运动伪影校正算法

目的 针对牙科CBCT扫描中患者不自主运动导致的重建图像运动伪影问题,提出了一种基于深度模糊学习的牙科CBCT运动伪影校正算法(DMBL),以提升牙科CBCT的成像质量。方法 首先使用模糊编码模块提取运动退化特征,从而对运动导致的退化过程进行建模,然后将得到的运动退化特征输入伪影校正模块进行运动伪影去除。其中,伪影校正模块采用了图像模糊去除和图像模糊仿真的联合学习框架,可有效处理空间变化且随机的运动模式。为验证所提方法的有效性,本文分别在仿真运动数据集和临床数据集上进行对比实验。结果 仿真数据集实验结果表明,本文方法峰值信噪比提升了2.88%,结构相似性(SSIM)提升了0.89%,均方根误差(RMSE)减少了10.58%;临床数据集实验结果表明,本文方法取得了最高的专家主观图像质量评分4.417(5分制),且与对比方法结果的评分具有显著性差异(P<0.001)。结论 本文提出的DMBL算法,通过构建深度模糊联合学习网络结构,能够有效地去除牙科CBCT图像中的运动伪影,实现高质量的图像恢复。

基于光线重排的印制电路板高速扫描成像迭代去模糊方法研究

自动光学检测(automated optical inspection,AOI)相机运动速度过高,拍摄印制电路板(printed circuit board,PCB)图像会产生严重模糊。如能正确恢复因此而产生的退化,可提高相机的运动速度,进而提高AOI的检测效率。受代数迭代重建算法(algebraic reconstruction technique,ART)启发,提出一种基于光线重排的图像非盲去模糊算法。该方法在模糊核已知的情况下,基于快速迭代收缩阈值算法(fast iterative shrinkage thresholding algorithm,FISTA)迭代重建算法,运用Nestrov加速和光线重排提高了迭代收敛速度,运用数据正则抑制图像的各类加性噪声和伪影,较好地重建出原本的清晰图像。结果表明,该方法对噪声具有较好的抑制能力,对AOI相机运动曝光引起的严重模糊,较常用的传统逆滤波方法具有更好的图像恢复效果。

基于改进PSF估计的车载复杂图像复原

针对车载视频图像中同时包含局部运动模糊和全局运动模糊,现有去模糊算法难以适用且效果差等问题,提出一种基于再模糊理论的复杂车载模糊图像复原方法。根据车载视频图像的特点把图像分割为车身和非车身区域,采用改进后的模糊参数估计算法,在车身区域图像块估算出的全局运动模糊参数,对整幅图像进行全局模糊恢复;对复原前后的非车身图像进行分块处理,利用复原前后图像块结构相似度(Structural Similarity,SSIM)和局部均方差的差异性,检测和提取出局部模糊区域;对提取的模糊区域进行复原后与清晰区域拼接融合,合成清晰的图像。与现有算法对比实验分析,所提算法取得了不错的效果,且复原后图像的峰值信噪比(Peak Signal to Noise Ratio,PSNR)和SSIM表现良好。

基于YOLOv8模型和LSD算法的列车接触网腕臂识别

针对列车接触网腕臂视觉检测中存在识别精度低、速度慢及腕臂图像易模糊的问题,设计了一种基于YOLOv8模型与LSD算法的接触网腕臂检测系统。首先,引入了YOLOv8目标检测模型,搭建了一种用于检测列车腕臂位置的视觉检测平台;其次,基于HIS颜色空间和图像滤波技术,对图像进行了增强处理,提升了腕臂识别的准确度;然后,基于LSD算法,完成了对接触网腕臂线段信息的提取;最后,根据现场采集的列车接触网图像,对算法的有效性进行了腕臂正反架识别实验验证。

Method for predicting motion artifacts of plasma display panels

A simulation method is proposed to predict the motion artifacts of plasma display panels （PDPs）. The method simulates the behavior of the human vision system when perceiving moving objects. The simulation is based on the measured temporal light properties of the display for each gray level and each phosphor. Both the effect of subfield arrangement and phosphor decay are involved. A novel algorithm is proposed to improve the calculation speed. The simulation model manages to predict the appearance of the motion image perceived by a human with a still image. The results are validated by a set of perceptual evaluation experiments. This rapid and accurate prediction of motion artifacts enables objective characterization of the PDP performance in this aspect.

一种基于生成对抗网络的人脸运动模糊去除方法

拍摄人像时,由于摄影器材震动或人物移动等原因,图像会出现运动模糊情况,严重影响了画面品质。而在影像跟踪或门禁识别等场景中,若画面出现运动模糊,可能导致目标无法识别,使得定位、辨认、追踪等任务失败。因此,去除运动模糊对于人脸识别应用有着至关重要的作用。文章针对人脸图像的运动模糊问题,提出一种基于生成对抗网络的人脸运动模糊去除方法,在编解码结构中引入多个跳跃连接,将卷积过程中提取的特征引入反卷积过程,同时通过全局跳跃连接,提高对特征信息的复用,并降低学习复杂度,最后调整损失函数权重,得到模糊图像到修复图像的端到端网络。实验结果表明,该方法在消除人脸运动模糊方面有较好的效果,对人脸的轮廓等细节的恢复也有很好的改善作用。

基于改进核相关滤波的桥吊负载摆角实时检测方法

在基于视觉的桥吊负载摆角检测过程中,负载快速运动使相机采集的图像产生运动模糊,进而导致摆角检测精度降低。为了准确、实时获取负载摆角信息,提出一种基于改进核相关滤波的摆角检测方法。将轨迹预测引入负载跟踪中,避免负载由于快速运动而逃离搜索窗口;设计尺度自适应策略,进一步提高跟踪性能;结合负载运动速度和响应峰值梯度更新自适应学习率,及时适应目标的特征变化。对兴趣区内的图像进行灰度增强处理,降低运动模糊对检测精度的影响,根据三角形外接圆定理获取标识物的圆心及半径,并结合起重机工作空间建立负载摆角测量模型。实验结果表明,所提出方法在检测准确性和实时性上均优于其他方法,检测误差不高于3像素,处理速度不低于35帧/s。

消除或减轻CBCT常见伪影的可行化探讨与研究

随着锥形束计算机断层成像(CBCT)在医学影像领域的广泛应用,其伪影问题日益引起关注。伪影对CBCT图像的质量和诊断准确性产生不利影响,因此寻求有效的方法消除或减轻伪影对于提高CBCT影像质量具有重要意义。本文简要介绍了锥形束CT的工作原理和常见伪影类型,针对每种伪影类型,分析了其产生机制和影响因素,同时提出消除或减轻CBCT常见伪影的可行方法,提出未来的研究应致力于深入理解伪影的形成机制,开发更加精确有效的消除或减轻伪影的方法。旨在为优化CBCT图像质量,提高临床应用时的影像诊断准确性和可靠性提供参考。

基于DeblurGAN的运动模糊图像盲复原算法研究

DeblurGAN方法利用条件生成对抗网络解决了端到端的图像去模糊问题,但存在图像边缘细节恢复不足以及鲁棒性不高的问题,针对此问题,提出一种基于DeblurGAN的运动模糊图像盲复原方法。在生成网络中,采用多尺度卷积核神经网络提取特征,并使用级联空洞卷积扩大神经元的感受野;采用自适配归一化方法代替原来生成器中使用的实例归一化方法。其次,引入了梯度图像L1损失,结合对抗损失和感知损失,将其作为图像去模糊的正则约束,使得生成图像的边缘特征更加清晰。实验结果表明,提出方法复原的图像峰值信噪比数值较DeblurGAN算法高出5.4%,结构相似性指标高出1%;在主观上清晰化效果较好,且消除了网格效应。