基于光流法的多分辨率电子稳像算法

针对动载体摄像系统中视频序列受载体姿态运动及抖动的干扰而出现的不稳定现象,提出一种基于光流算法的多分辨率电子稳像算法。首先,通过划定有效的运动估算区域取代对整帧图像的计算以降低计算量;然后,利用基于光流算法的多分辨率分层运动估计快速并精确地计算出包含平移、旋转以及缩放运动的相邻帧间仿射变换参数;最后,采用固定帧补偿算法,利用求得的仿射变换参数,对图像进行运动补偿,消除或减轻图像序列帧间的随机抖动,达到稳像的目的。实验结果表明,针对包含运动目标的动态场景,该算法可以精确地检测出视频序列帧间平移、旋转以及缩放等复杂的抖动,水平和垂直方向的稳像精确度小于1pixel,保证视频序列的稳定输出,可应用于目标跟踪系统中。     

Fast 3D video stabilization using ROI-based warping

With the rapid development of portable digital video equipment, such as camcorders, digital cameras and smart phones, video stabilization techniques for camera de-shaking are strongly required. The cutting-edge video stabilization techniques provide outstanding visual quality by utilizing 3D motion, while early video stabilization is based on 2D motion only. Recently, a content-preserving warping algorithm has been acknowledged as state-of-the-art thanks to its superior stabilization performance. However, the huge computational cost of this technique is a serious burden in spite of its excellent performance. Thus, we propose a fast video stabilization algorithm that provides significantly reduced computational complexity over the state-of-the-art with the same stabilization performance. First, we estimate the 3D information of the feature points in each input frame and define the region of interest (ROI) based on the estimated 3D information. Next, if the number of feature points in the ROI is sufficient, we apply the proposed ROI-based pre-warping and content-preserving warping sequentially to the input frame. Otherwise, conventional full-frame warping is applied. From intensive simulation results, we find that the proposed algorithm reduces computational complexity to 14% of that of the state-of-the-art method, while keeping almost equivalent stabilization performance.     

基于联合相机路径的红外视频稳像算法

针对由于视差变化而导致的红外视频稳像技术难题,文中提出了一种基于联合相机路径的红外视频稳像算法,该算法主要包括:预处理、联合相机路径求解、多路径优化、运动补偿四个步骤。首先,要对红外图像进行直方图均衡化、特征点提取和匹配处理、预映射。接着,要将每帧图像分为m×n个网格单元,利用基于网格的映射运动表征,将每一帧中对应网格得到的局部单应性矩阵进行相乘得到联合相机路径。然后,对联合相机路径采用“多路径优化”策略进行平滑处理。最后,利用平滑后路径进行运动补偿稳定视频。实验结果表明,该方法能有效地处理由于视差而引起的非线性运动,相比传统的稳像算法效果更好,当特征点存在部分遮挡时,也能取得不错的稳像效果。     

Moving Target Tracking Based on LogGabor Wavelet and Mean-shift Algorithm

Tracking moving target from image or video sequence is a hot research topic in computer vision.An algorithm based on LogGabor wavelet and Mean-shift has been proposed for moving target tracking under fixed camera setting and complicated environment.Phase coherency of LogGabor wavelet facilitates to extract the edge of moving target and check noise.According to the edge detection,the starting location of Mean-shift can be estimated using the target center coordinate.Eventually,a real-time moving target can be extracted by doing iterative matching pursuit,and experimental results proved the effectiveness of the method proposed.     

一种基于空间关系的抗抖动红外多点目标关联算法

针对在摄像机发生抖动时拍摄的红外图像的多点目标关联问题,提出了新的算法,采用了基于特征三角形的多点目标关联算法.根据目标间的相对位置关系,利用特征三角形对相邻两帧的图像进行配准,消除由于背景运动和摄像机抖动引起的目标整体的平移、旋转和缩放.然后根据配准后的结果,采用改进的最近邻法对目标进行关联.试验仿真结果表明:算法精度和稳定性明显高于依靠位置和灰度等信息的传统算法,特别是对于在摄像头抖动情况下拍摄的红外多点目标关联具有较高的正确率.     

基于跟踪微分器的波门跟踪算法的研究

针对目标自动跟踪系统对目标跟踪算法实时性和精确性要求高的特点,提出了一种基于跟踪微分滤波器的运动目标跟踪方法.该算法利用跟踪微分器预测目标中心在下一帧体现在图像中可能出现的位置,以该位置为波门目标检测的中心,减少了目标的搜索范围,缩短了算法的运算时间.仿真结果表明,该方法具有不依赖于目标运动模型,实时性好,精确性高等优...     

A biprocessor-oriented vision-based target tracking system

The design and realization of a vision-based target tracking system is proposed. The objective is to derive the orientation of a pan-tilt camera fitting a drone in order to track a target and to maintain its position in the middle of the image. Image data and drone attitude are the only information available for the camera control to be achieved correctly. This embedded system requires low-cost hardware for surveillance or attack drone applications: a digital signal processor for the image processing, and a microcontroller for the camera control. To ensure real-time video operation, an algorithmic solution integrating a successive-step and multi-block search method is implemented, thus allowing complex target displacements. The microcontroller uses this information to manage the camera orientation. Experiments have been conducted in real, conditions and acceptable target tracking results have been obtained on the prototype hardware     

基于Harris图像拼接的全景视频稳像算法

对于背景变换和抖动分量比较小的视频序列,传统稳像算法不能直接适用,本文提出一种基于Harris图像拼接的全景稳像算法。首先采用Prewitt算子提取出图像的边缘信息,在此基础上进行分区的Harris特征点检测;然后结合NCC（normalized cross correlation）算法与RANSAC（random sample consensus）算法实现图像间的特征点精确匹配,接着利用加权平均融合的方法进行图像融合;最后对融合后的全景图像进行剪裁,完成图像补偿,输出稳定的视频序列。实验结果表明:改进的Harris算法提高了算法效率以及正确特征点数量,并且本文稳像算法实时性较好,能够有效消除视频抖动并输出稳定的视频序列。     

基于多路摄像的视频运动目标智能分析系统

为实现对视频运动目标落点的准确定位与参数分析,并满足其实时性要求,研发了基于多路视频图像的运动目标智能分析系统。该系统综合利用图像预处理和判读技术,在改进ViBe和Mean-Shift等相关算法的基础上,对视频图像进行连续的实时滤波、目标检测和定位以实现对目标参数的智能分析。同时,提出了基于多路视频信息定位目标落点算法和多摄像机协同调度技术。实验结果表明,该系统具有精度高、实时性强等特点,具有较高的实用价值。     

Efficient fog removal from video

In this paper, a framework of real-time video processing for fog removal using uncalibrated single camera system is proposed. Intelligent use of temporal redundancy present in video frames paves the way for real-time implementation. Any fog removal algorithm for images acquired with uncalibrated single camera system can be extended to video using the proposed framework. For the purpose of real-time implementation, several fog removal algorithms for images are investigated and few top ranking algorithms in speed and quality are chosen. Simulation results confirm that proposed framework reduces the computation per frame significantly. Proposed fog removal framework has a wide application in navigation, transportation, and other industries.     

改进的KCF红外空中目标跟踪方法

针对红外空中目标跟踪中遮挡导致的跟丢问题,结合核相关滤波跟踪算法(KCF)无法跟踪尺度的缺点,提出一种基于KCF的红外空中目标跟踪方法。该方法借助KCF估计的目标位置,增加Sobel算子提取目标扩展区域的边缘信息,从而获取目标尺度并进行二次定位。然后,判断目标是否受遮挡或跟丢,采用帧差法重新检测目标,确保目标的持续跟踪。在7个视频序列上对所提的算法进行了实验,结果显示,所提算法能够有效计算尺度,验证了多种环境下跟踪的有效性。平均跟踪速度达到44 f/s,能够满足实时性要求。因此,本文提出的方法对于红外空中目标的跟踪具有一定的实用意义。     

基于粒子群算法和卡尔曼滤波的运动目标跟踪算法

针对目前一些常用的运动目标跟踪算法存在跟踪精度不高、实时性低、对遮挡问题处理不佳等问题,提出一种粒子群算法与卡尔曼滤波相结合的新的运动目标跟踪方法。利用卡尔曼滤波预测目标中心在下一帧图像中的位置,从而极大减少了搜索范围,并以该位置为中心建立目标搜索区域。然后以目标的灰度统计特征对目标模板和候选区域进行匹配,确保跟踪准确性。为了有效减少搜索匹配次数、提高实时性,利用粒子群算法在搜索区域找到和目标模板最相似的区域,从而找到最优中心位置,并以该位置作为卡尔曼滤波的观测值,进行下一帧跟踪。仿真实验结果表明新算法显著提高了跟踪的实时性、精确性,并对部分遮挡能较好地处理。     

Design and verification of on-chip debug circuit based on JTAG

An on-chip debug circuit based on Joint Test Action Group (JTAG) interface for L-digital signal processor (L- DSP) is proposed, which has debug functions such as storage resource access, central processing unit (CPU) pipeline control, hardware breakpoint/ observation point, and parameter statistics. Compared with traditional debug mode, the proposed debug circuit completes direct transmission of data between peripherals and memory by adding data test-direct memory access (DT-DMA) module, which improves debug efficiency greatly. The proposed circuit was designed in a 0-18 μm complementary metal-oxide-semiconductor ( CMOS) process with an area of 167 234.76 μm² and a power consumption of 8.89 mW. And the proposed debug circuit and L-DSP were verified under a field programmable gate array (FPGA). Experimental results show that the proposed circuit has complete     

Real-time hand tracking based on YOLOv4 model and Kalman filter

Aiming at the shortcomings of current gesture tracking methods in accuracy and speed, based on deep learning You Only Look Once version 4 (YOLOv4) model, a new YOLOv4 model combined with Kalman filter rea-time hand tracking method was proposed. The new algorithm can address some problems existing in hand tracking technology such as detection speed, accuracy and stability. The convolutional neural network (CNN) model YOLOv4 is used to detect the target of current frame tracking and Kalman filter is applied to predict the next position and bounding box size of the target according to its current position. The detected target is tracked by comparing the estimated result with the detected target in the next frame and, finally, the real-time hand movement track is displayed. The experimental results validate the proposed algorithm with the overall success rate of 99.43%     

Transcoding with Resolution Conversion Using Super-Resolution and Irregular Sampling

In transcoding, quantization and other techniques could result in lower video output quality. To address this problem a novel super-resolution (SR) algorithm based on irregular sampling (IS) is presented in this paper. The high-resolution (HR) frame is obtained as an interpolation of one or more previous frames; the resulting interpolated frame has samples non-uniformly spaced in the areas where movement happened. To reconstruct the irregular sampled frame we use a well-known irregular sampling algorithm modified to perform in 2-D space. Moreover, because SR algorithms are in general computationally expensive, we also present a hardware feasibility study. The proposed solution does not target any specific application but we have specifically tested the algorithm in a transcoding environment. In particular, we have applied it to VC-1 to H.264 transcoding and applied down/up sampling. Experimental results show that the proposed algorithm improves video quality significantly.     

基于雾线先验的时空关联约束视频去雾算法

现有视频去雾算法由于缺少对视频结构关联约束和帧间一致性分析,容易导致连续帧去雾结果在颜色和亮度上存在突变,同时去雾后的前景目标边缘区域也容易出现退化现象。针对上述问题,该文提出一种基于雾线先验的时空关联约束视频去雾算法,通过引入每帧图像在空间邻域中具有的结构关联性和时间邻域中具有的连续一致性,提高视频去雾算法的求解准确性和鲁棒性。算法首先使用暗通道先验估计每帧图像的大气光向量,并结合雾线先验求取初始透射率图。然后引入加权最小二乘边缘保持平滑滤波器对初始透射率图进行空间平滑,消除奇异点和噪声对估计结果的影响。进一步利用相机参数刻画连续帧间透射率图的时序变化规律,对独立求取的每帧透射率图进行时序关联修正。最后根据雾图模型获得最终的视频去雾结果。定性和定量的对比实验结果表明,该算法下视频去雾结果的帧间过渡更加自然,同时对每一帧图像的色彩还原更加准确,图像边缘的细节信息显示也更加丰富。     

基于视频的车型分类算法研究

对视频图像处理中车型分类算法涉及的摄像机标定和目标分割算法进行研究。通过摄像机标定实现像素坐标到世界坐标的映射,进而准确获取车辆长度及宽度信息。建立车辆高度信息计算模型,获得车辆高度信息。对实时视频图像进行目标分割,并通过车辆长度、高度及长高比等信息实现高速公路中车型分类。经过验证,该方法能够比较准确地进行车型分类,满足实际应用要求。     

基于Opencv的运动目标的检测和跟踪

检测运动物体需要无运动物体的背景图像,所以,首先应用多帧像素平均值法提取了运动视频序列的背景图,从背景图像中分离目标像素,获取目标的质心坐标,并应用质心跟踪法以灰色图像序列为基础,对运动的目标进行实时检测和跟踪。质心跟踪法的目标位置通过质点的中心来确定,该算法计算简单,计算量小,其稳定性与精度主要取决于序列图像的分割及其阀值的确定情况。文中给出了用Opencv实现算法的具体过程和关键代码,并且设计了跟踪运动车辆的控制界面,方便了实时监控。实验结果表明,该方法可以实现视频序列中运动目标的识别,具有实时性、并能给出较好的识别效果。     

基于3DGMM的多视点视频直方图颜色校正

多视点视频在采集过程中,由于受到摄像机所处位置以及摄像机自身的参数设置等因素的影响,会造成视点间颜色的不一致,针对这一情况,提出基于三维高斯混合模型的多视点视频直方图颜色校正算法。算法首先获取源图像以及目标图像的直方图并检测直方图的峰值个数,然后结合三维高斯混合模型对源图像以及目标图像进行聚类分析,获取中心矢量,最后计算两图像中像素点距离中心矢量的最小欧几里得距离并分割图像,对源图像和目标图像的匹配区域进行直方图匹配校正。实验结果表明,该算法与传统直方图匹配算法相比,避免了校正过度的影响,校正效果较好。     

基于统计的灰度视频自适应背景建模算法

针对灰度视频的目标检测依赖先验知识、召回率低以及单一算法无法同时兼顾静态与动态背景等问题,提出一种基于统计的背景建模算法。该算法无需先验知识,根据统计信息可以准确区分静态背景和动态背景,并采取不同的检测策略提取目标。对于静态背景,采用改进的三帧差分法自适应设置阈值,可以保证较高的召回率。对于动态背景,采用改进的概率密度估计法可以有效降低虚警率。采用所提算法对光照变化以及阴影进行处理,可以进一步提升算法的性能。在公开数据集与实际采集红外数据进行验证实验。实验结果表明,所提算法在多种场景中处理灰度视频的结果比其他传统算法好,在保证准确率的同时可以极大地提升召回率,并且有效提高目标的完整性。