Real-time speckle image processing

The laser dynamic speckle is an optical phenomenon produced when a laser light is reflected from an illuminated surface undergoing some kind of activity. It allows a non-destructive process for the detection of activities that are not easily observable, such as seed viability, paint drying, bacterial activities, corrosion processes, food decomposition, fruit bruising, etc. The analysis of these processes in real time makes it possible to develop important practical applications of commercial, biological and technological interest. This paper presents a new digital system based on granular computing algorithms to characterize speckle dynamics within the time domain. The selected platform to evaluate the system is Field Programmable Gate Array (FPGA) technology. The obtained minimum clock periods and latencies enable speckle image processing with real-time constraints with a maximum throughput of about thousand 512 × 512 fps.     

Real-time content-aware image resizing

Content-aware image resizing is a kind of new and effective approach for image resizing, which preserves image content well and does not cause obvious distortion when changing the aspect ratio of images. Recently, a seam based approach for content-aware image resizing was proposed by Avidan and Shamir. Their results are impressive, but because the method uses dynamic programming many times, it is slow. In this paper, we present a more efficient algorithm for seam based content-aware image resizing, which searches seams through establishing the matching relation between adjacent rows or columns. We give a linear algorithm to find the optimal matches within a weighted bipartite graph composed of the pixels in adjacent rows or columns. Therefore, our method is fast (e.g. our method needs only about 100 ms to reduce a 768 × 1024 image’s width to 1/3 while Avidan and Shamir’s method needs 12 s). This supports immediate image resizing whereas Avidan and Shamir’s method requires a more costly pre-processing step to enable subsequent real-time processing. A fast method such as the one proposed will be also needed for future real-time video resizing applications.     

实时单幅图片高光去除算法

单幅图片的高光去除是一个非常具有挑战性的课题。综述以往多数方法,一般需要进行图像分割等预处理,或者要求用户进行交互输入。采用的方法是从高光图片的颜色统计规律出发,发现了最大漫反射色度局部平滑这一特性;然后估计镜面反射像素最大漫反射色度,由基于线性模型对最大色度的值进行扩散传播,从图像中的漫反射像素传播到镜面反射像素;最后求出图像中每个像素的漫反射分量。与传统方法相比较,这种高光去除的方法效果较好,而且非常简单,适合并行,可以满足实时应用需要。     

Real-time deep satellite image quality assessment

A method for deep satellite image quality assessment based on no-reference satellite images is proposed. We design suitable deep convolutional neural networks, which are named satellite image quality assessment of deep convolutional neural networks (SIQA-DCNN) and SIQA-DCNN++. These sophisticated methods can remove various distorted satellite images in real-time remote sensing. The novelty of this method lies in the objective assessment and restoration of the deep model which understands various distorted satellite images in high- and low-resolution problems. The activation function has a lower computational time and ensures the deactivation of noise by making the mean activators close to zero. Our methods are also effective for transfer learning, which can be used to adequately investigate satellite image classification in deep satellite image quality assessment. Using Spearman’s rank order correlation coefficient (SROCC) and linear correlation coefficient (LCC) evaluations, we demonstrated that our methods show better performance than other algorithms, with more than 0.90 of SROCC and LCC values compared to the full-reference and no-reference satellite image in MODIS/Terra and USGS datasets. Regarding computational complexity, we obtained better performance in operational function times. As compared to other methods, SIQA-DCNN and SIQA-DCNN++ also reduced computational time by more than 40 and 56%, respectively, when applied to the USGS dataset, and by more than 46 and 60% respectively, when applied to the MODIS/Terra dataset.     

LabVIEW应用于实时图像采集及处理系统

本文在LabVIEW和NI-IMAQ Vision软件平台下,利用通用图像采集卡开发一种图像实时采集处理虚拟仪器系统。通过调用动态链接库驱动通用图像采集卡完成图像采集,采集图像的帧速率达到25帧每秒。利用NI-IMAQ Vision视频处理模块,进行图像处理,以完成光电探测器的标定。该系统具有灵活性强、可靠性高、性价比高等优点。     

Real-time image restoration for iris recognition systems.

In the field of biometrics, it has been reported that iris recognition techniques have shown high levels of accuracy because unique patterns of the human iris, which has very many degrees of freedom, are used. However, because conventional iris cameras have small depth-of-field (DOF) areas, input iris images can easily be blurred, which can lead to lower recognition performance, since iris patterns are transformed by the blurring caused by optical defocusing. To overcome these problems, an autofocusing camera can be used. However, this inevitably increases the cost, size, and complexity of the system. Therefore, we propose a new real-time iris image-restoration method, which can increase the camera's DOF without requiring any additional hardware. This paper presents five novelties as compared to previous works: 1) by excluding eyelash and eyelid regions, it is possible to obtain more accurate focus scores from input iris images; 2) the parameter of the point spread function (PSF) can be estimated in terms of camera optics and measured focus scores; therefore, parameter estimation is more accurate than it has been in previous research; 3) because the PSF parameter can be obtained by using a predetermined equation, iris image restoration can be done in real-time; 4) by using a constrained least square (CLS) restoration filter that considers noise, performance can be greatly enhanced; and 5) restoration accuracy can also be enhanced by estimating the weight value of the noise-regularization term of the CLS filter according to the amount of image blurring. Experimental results showed that iris recognition errors when using the proposed restoration method were greatly reduced as compared to those results achieved without restoration or those achieved using previous iris-restoration methods.     

Real-time image processing on a custom computing platform

The authors explore the utility of custom computing machinery for accelerating the development, testing, and prototyping of a diverse set of image processing applications. We chose an experimental custom computing platform called Splash-2 to investigate this approach to prototyping real time image processing designs. Custom computing platforms are emerging as a class of computers that can provide near application specific computational performance. We developed a real time image processing system called VTSplash, based on the Splash-2 general-purpose platform. Splash-2 is an attached processor featuring programmable processing elements (PEs) and communication paths. The Splash-2 system uses arrays of RAM based field programmable gate arrays (FPGAs), crossbar networks, and distributed memory to accomplish the needed flexibility and performance tasks. Such platforms let designers customize specific operations for function and size, and data paths for individual applications     

基于形态非抽样小波的实时图像融合方法

提出一种适合实时图像融合的形态非抽样小波(MUDW)变换,该变换采用膨胀和腐蚀操作的平均值作为分解过程中的分析算子,以相邻尺度图像之间的差作为细节图像,使尺度刻画更精细,细节描述更准确;采用随尺度增加而大小递增的结构元素,使尺度间差异更大,应用于图像融合可得到更好的图像融合效果。相比现有的实时图像融合方法,因为膨胀和腐蚀操作的便捷性,所以具有更高的实时性。通过实验证明了该方法具有良好的多尺度分解特性,取得了更好的融合效果;进一步在重构时设立增强因子能显著增强融合图像的效果。因此,在实时图像融合上具有较强的应用价值。     

视频移动终端实时定点与缩放

针对在移动终端自由缩放查看视频细节的需求,提出移动终端的视频图像定点与缩放系统,包含手势识别与越界纠正技术,详细给出了系统框架和系统流程。手势识别给出了单指拖动和双指缩放的检测与坐标转换计算方法,而后对变换参数的取值进行越界纠正和边界限定。系统架构包含视频解码、画面绘制、同步交互,在系统流程及其实现中分别由三个线程并行承载以提高效率。测试结果分析表明,该系统在保留传统视频播放方式上加入了定点与缩放,在播放效率相比传统视频播放方式的损失平均仅占14%的同时,交互响应时间控制在6ms内,最大限度消除了交互引起的画面闪烁和跳帧。系统在资源有限的移动终端上实现了视频播放的实时定点与缩放,有广阔的应用前景,应用价值高。     

Real-time image segmentation for visual inspection of pharmaceutical tablets

Visual appearance is an important quality factor of pharmaceutical tablets. Due to the vast quantities of produced tablets and high-quality requirements, pharmaceutical companies are interested in employing automated systems for real-time visual tablet inspection with the speeds of up to 100 tablets per second. Such systems require reliable tablet manipulation, illumination, image acquisition, tablet image analysis, classification, and sorting system. Tablet image segmentation, in which each tablet image is partitioned into the tablet region and background, is the first and very important step in tablet image analysis. It this paper, we propose a novel real-time segmentation method for grey-level images that is based on border tracking. The proposed method was designed to be accurate, robust, and computationally undemanding. The performances of the method were objectively assessed on a large number of simulated and real tablet images. The obtained results indicated high reliability, accuracy, and speed. The 100% reliability was obtained for segmentation of real images of pharmaceutical tablets, while the segmentation times were no more than 1.5 ms or 15% of the whole time available for tablet image analysis. As such, the proposed method proved feasible for real-time visual quality inspection of pharmaceutical tablets. Based on just a few assumptions that are usually fulfilled, the method may be a valuable segmentation tool for many other visual quality inspection applications.     

Real-time motion estimation for image and video processing applications

This contribution focuses on different topics that are covered by the special issue titled “Real-Time Motion Estimation for image and video processing applications” and which incorporate GPUS, FPGAs, VLSI systems, DSPs, and Multicores, among other platforms. The guest editors have solicited original contributions, which address a wide range of theoretical and practical issues related to high-performance motion estimation image processing including, but not limited to: real-time matching motion estimation systems, real-time energy-based motion estimation systems, gradient-based motion estimation systems, optical flow estimation systems, color motion estimation systems, multi-scale motion estimation systems, optical flow and motion estimation systems, analysis or comparison of specialized architectures for motion estimation systems and real-world applications.     

Real-time patch-based medical image modality propagation by GPU computing

The synthesis of patient data of a certain medical image modality by applying an image processing pipeline starting from other modality is receiving a lot of interest recently, as it allows to save acquisition time and sometimes avoid radiation to the patient. An example of this is the creation of computerized tomography volumes from magnetic resonance imaging data, which can be useful for several applications such as electromagnetic simulations, cranial morphometry and attenuation correction in PET/MR systems. We present a fast patch-based algorithm for this purpose, implemented using graphics processing unit computing techniques and gaining up to \(\times\)15.9 of speedup against a multicore CPU solution and up to about \(\times\)75 against a single core CPU solution.     

Real-time video photomosaics with optimized image set and GPU

We propose a real-time approach to automatically generate photomosaic videos from a set of optimized images by taking advantage of CUDA GPU acceleration. Our approach divides an input image into smaller cells—usually rectangular cells—and replaces each cell with a small image of an appropriate color pattern. Photomosaics require a large set of tile images with a variety of patterns to create high-quality digital mosaic images. Because a large database of images requires longer processing time and larger storage space for searching patterns from the database, this requirement causes problems in developing a real-time system or mobile applications that have limited resources. This paper deals with a real-time video photomosaics using genetic feature selection method for building an optimized image set and taking advantage of CUDA to accelerate pattern searching that minimizes computation cost.     

用CPLD实现嵌入式平台上的实时图像增强

提出了在嵌入式平台上用CPLD实现实时图像增强算法的解决方案,并加以实现。重点讨论了经过改进的图像增强算法以及使用CPLD实现的具体方法,介绍了所采用的嵌入式平台的总体结构。     

Real-time operation of mobile robots using linear image arrays

A vision system using a pair of Linear Image Arrays is proposed for use with mobile robots for factory environments. This vision system was developed to perform the function of guidance, navigation, and obstacle detection. Using a standard 16-bit microprocessor for all of the computing tasks, low cost, small size, and low power consumption can be obtained. Real-time operation is achieved by using line images, which provide less data than two-dimensional images. However, this results in the need for special image processing techniques. Guidance and navigation are achieved using a new technique called the difference of medians, a robust method of detecting and locating known features in line images. Obstacle detection is performed by locating feature points in thresholded images and determining the distances to these feature points by template matching. A distance map is then generated, from which obstacles can be located. the algorithms used are chosen for their efficiency, with the result that a pair of images can be analyzed in less than 0.5 s.     

基于形态学的自动浇注实时图像处理方法

分析实时浇注图像形态上的特性,提出一种基于二值图像形态学的浇注图像预处理方法.即先利用最佳阈值法.完成浇注图像的粗分割与初步去噪,然后利用图像区域连通标注算法,过滤图像中金属液液滴飞溅噪声,最后基于形态学中腐蚀、膨胀运算,选择合适结构元素对图像进行开运算,消除图像中金属液液柱干扰.该去噪方法可以提高浇口杯中金属液液位识别的准确性,能够为浇注自动控制提供良好的决策依据,符合应用要求现实可行.     

Real-time image and video processing in portable and mobile devices

Mobile handheld and battery-operated consumer electronic devices such as digital still cameras, personal media players, digital camcorders, camera phones, mobile video telephones, etc. have become very popular and their annual shipments are already in hunderds of millions of units. The ability to carry out image and video processing in real-time has been one of the major reasons for the widespread success of these devices. In this article, the typical components present in such devices and the image and video processing that are carried out are described first. Some of the emerging trends relevant to image and video processing algorithms used on these devices are highlighted next. A brief overview of system requirements and challenges for image and video processing on these devices is then provided. These requirements are driving image and video processing research in new directions.     

基于FPGA的实时图像采集与Sobel边缘检测

运用现场可编程门阵列(FPGA)的流水线和并行技术,构建灵活高速的可编程图像采集与预处理系统.利用基于QuartusⅡ提供的参数可设置宏功能模块,实现了Sobel边缘检测算法,并实时显示边缘检测后的图像,获得了很好的边缘检测效果,缩短了开发周期.     

改进YOLO v4的火焰图像实时检测

为解决火焰图像检测易被周围环境干扰、火焰特征复杂等问题,提出改进型YOLOv4火焰图像实时检测模型。改进模型的激活函数;通过K-Means聚类针对火焰图像的特征调整先验框的维度;通过改进损失函数,减少模型中不必要特征的学习;引入注意力机制(通道注意力(CAB)模块和空间注意力(SAB)模块),增强模型在通道和空间的感知力。实验结果表明,改进的YOLOv4目标检测算法的FPS可达76.7,较原来提升了1.1;检测精度和召回率为82.8%、0.78,分别比原算法提高了36.56%、0.36;损失值为0.7758,比原算法降低了1.2942。     

视频图像的车辆速度实时检测算法研究

在监控视频图像中因拍摄角度的问题,导致图像中的车道线并不是竖直的。针对在此图像中选取对应块,实现车辆速度实时检测的问题,分析了车身的特征及图像中车道线的倾斜角度,选择车灯作为对应块,选取车灯存在的候选区域;然后根据车灯的对称性强度筛选车灯带,实现车灯的准确定位,并把车灯移动的距离通过摄像机标定转换到实际坐标中,从而实现车辆速度的实时检测。实验结果证明该方法运行速度快,定位准确。因此可以广泛的应用于红绿灯路口环境中实现视频图像的车速实时检测。