基于曲线拟合的视频稳像方法

根据人眼的视觉特性,提出一种基于曲线拟合的视频稳像方法。使用图像背景特征点对摄像机的全局运动进行估计,利用曲线拟合的方法计算出摄像机的抖动分量,并将曲线拟合的结果作为摄像机的主观运动方向,对其摄像机的抖动运动分量进行补偿,使图像位移矢量达到最小,以有效减少运动补偿后引起的图像信息丢失。对抖动角度在20°内移动摄像机拍摄的视频进行稳像处理,实验结果表明,该方法稳像后视频的抖动角度小于2°,视频图像信息的损失小于5%,具有较好的稳像效果,并且在稳像后保证了视频帧内容的完整性。     

Computing occluding and transparent motions

Computing the motions of several moving objects in image sequences involves simultaneous motion analysis and segmentation. This task can become complicated when image motion changes significantly between frames, as with camera vibrations. Such vibrations make tracking in longer sequences harder, as temporal motion constancy cannot be assumed. The problem becomes even more difficult in the case of transparent motions.A method is presented for detecting and tracking occluding and transparent moving objects, which uses temporal integration without assuming motion constancy. Each new frame in the sequence is compared to a dynamic internal representation image of the tracked object. The internal representation image is constructed by temporally integrating frames after registration based on the motion computation. The temporal integration maintains sharpness of the tracked object, while blurring objects that have other motions. Comparing new frames to the internal representation image causes the motion analysis algorithm to continue tracking the same object in subsequent frames, and to improve the segmentation.     

摄像机运动情况下的运动对象检测

在监控应用中,由于场景是已知的,因此可以使用背景减去法检测运动对象.当摄像机进行扫描和倾斜运动时,需要使用多个图像帧才能完整地表示监控场景.如何组织和索引这些背景帧属于摄像机跟踪问题.提出一种无需摄像机标定的背景帧索引和访问方法.这一方法需要使用图像配准技术估计图像初始运动参数.提出一种屏蔽外点的图像配准算法,综合利用线性回归和稳健回归快速估计初始运动参数.为了快速计算连续帧之间的运动参数,提出一种基于四参数模型的优化算法.利用非参数背景维护模型抑制虚假运动象素.室内和户外实验结果表明本文方法是有效的.     

Motion tracking with an active camera

This paper describes a method for real-time motion detection using an active camera mounted on a pan/tilt platform. Image mapping is used to align images of different viewpoints so that static camera motion detection can be applied. In the presence of camera position noise, the image mapping is inexact and compensation techniques fail. The use of morphological filtering of motion images is explored to desensitize the detection algorithm to inaccuracies in background compensation, Two motion detection techniques are examined, and experiments to verify the methods are presented. The system successfully extracts moving edges from dynamic images even when the pan/tilt angles between successive frames are as large as 3     

适用于旋转摄像下目标检测的图像补偿

目的 摄像机旋转扫描条件下的动目标检测研究中,传统的线性模型无法解决摄像机旋转扫描运动带来的图像间非线性变换问题,导致图像补偿不准确,在动目标检测时将引起较大误差,造成动目标虚假检测。为解决这一问题,提出了一种面阵摄像机旋转扫描条件下的图像补偿方法,其特点是能够同时实现背景运动补偿和图像非线性变换补偿,从而实现动目标的快速可靠检测。方法 首先进行图像匹配,然后建立摄像机旋转扫描非线性模型,通过参数空间变换将其转化为线性求解问题,采用Hough变换实现该方程参数的快速鲁棒估计。解决摄像机旋转扫描条件下获取的图像间非线性变换问题,从而实现图像准确补偿。在此基础上,可以利用帧间差分等方法检测出运动目标。结果 实验结果表明,在摄像机旋转扫描条件下,本文方法能够同时实现图像间的背景运动补偿和非线性变换补偿,可以去除大部分由于立体视差效应（parallax effects）产生的匹配错误。并且在实验中,本文方法处理速度可以达到50帧/s,满足实时性要求。结论 在面阵摄像机旋转扫描的条件下,相比于传统的基于线性模型的图像补偿方法,本文方法能够快速、准确地在背景补偿的基础上同时解决图像间非线性变换问题,从而更好地提取出运动目标,具有一定的实用价值。     

一种内容完整的视频稳定算法

设计了一种基于可靠特征集合匹配的内容完整的视频稳定算法。为了避免运动前景上的特征点参与运动估计,由经典的KLT(Kanade-Lucas-Tomasi)算法提取特征点,而后基于特征有效性判定规则对特征点集合进行有效性验证以提高特征点的可靠性。利用通过验证的特征点对全局运动进行估计,得到精确的运动参数并据此对视频图像进行运动补偿。对于运动补偿造成的无定义区,首先计算当前帧的定义区与相邻帧的光流,以此为向导腐蚀无定义区;利用拼接的方法,填充仍为无定义区的像素。实验结果表明该算法对于前景物体运动具有较好的鲁棒性并能够生成内容完整的稳定视频序列。     

Automatic feature point extraction and tracking in image sequences for arbitrary camera motion

An automatic egomotion compensation based point correspondence algorithm is presented. A basic problem in autonomous navigation and motion estimation is automatically detecting and tracking features in consecutive frames, a challenging problem when camera motion is significant. In general, feature displacements between consecutive frames can be approximately decomposed into two components: (i) displacements due to camera motion which can be approximately compensated by image rotation, scaling, and translation; (ii) displacements due to object motion and/or perspective projection. In this paper, we introduce a two-step approach: First, the motion of the camera is compensated using a computational vision based image registration algorithm. Then consecutive frames are transformed to the same coordinate system and the feature correspondence problem is solved as though tracking moving objects for a stationary camera. Methods of subpixel accuracy feature matching, tracking and error analysis are introduced. The approach results in a robust and efficient algorithm. Results on several real image sequences are presented.The support of the Advanced Research Projects Agency (ARPA Order No. 8459) and the U.S. Army Engineer Topographic Laboratories under Contract DACA 76-92-C-0009 is gratefully acknowledged.     

一种图像序列自动分割新方法

该文提出了一种固定场景下的图像序列自动分割的新方法。该方法分为两个阶段。在第一个阶段中,巧妙地采用形态学处理方法获得当前帧的运动区域,然后用当前帧对背景进行更新,经过数十帧的迭代,自动提取出初始背景;第二阶段对每帧作如下操作:首根据当前帧与背景的差分图像的直方图提取出噪声参数,并利用该参数求出对差分图像分割的双阈值,从而实现运动目标分割,最后再利用分割结果对背景进行自动更新。试验结果表明,用该方法进行分割不但效果好,而且速度快。     

Spatial-Feature Parametric Clustering Applied to Motion-Based Segmentation in Camouflage

In this paper we present an algorithm which forms the preprocessing stage of a system for automatically classifying Amazon forest monkeys captured on video in their natural habitat. The work is motivated by a desire to automatically monitor animal populations in natural forest environments. The method applies a graph-theoretical clustering approach to spatial and motion fields to automatically segment monkeys moving in the foreground from trees and other vegetation in the background. The algorithm is described as follows: First a d'Alembertian of a spatial–temporal Gaussian filter is convolved with a sequence of image frames to obtain an image of temporal zero crossings. Subsequently, the magnitude of the visual motion vector in the image plane is estimated at each pixel of the image of temporal zero crossings and spatial-motion-based graph-theoretical clustering is applied to the resulting velocity image. The clustered pixels are then backprojected into the original color image for each subsequent frame to obtain a segmented image sequence. By applying a threshold to the velocity image, motion due to background vegetation and camera movement can be rejected, while segments extracted from animals are retained. This is extremely important for our application as the recognizer relies on color features that are extracted from the monkeys' fur. Experimental results are presented which show that the approach can successfully extract patches of monkey skin from video shot with a simple hand held camera.     

基于特征跟踪和网格路径运动的视频稳像算法

针对手持移动设备拍摄的抖动视频问题,提出了一种基于特征跟踪和网格路径运动的视频稳像算法。通过SIFT算法提取视频帧的特征点,采用KLT算法追踪特征点,利用RANSAC算法估计相邻帧间的仿射变换矩阵,将视频帧划分为均匀的网格,计算视频的运动轨迹,再通过极小化能量函数优化平滑多条网格路径。最后由原相机路径与平滑相机路径的关系,计算相邻帧间的补偿矩阵,利用补偿矩阵对每一帧进行几何变换,从而得到稳定的视频。实验表明,该算法在手持移动设备拍摄的抖动视频中有较好的结果,其中稳像后视频的PSNR平均值相比原抖动视频PSNR值大约提升了11.2 dB。与捆绑相机路径方法相比约提升了2.3 dB。图像间的结构相似性SSIM平均值大约提升了59%,与捆绑相机路径方法相比约提升了3.3%。     

A General Framework for the Selection of World Coordinate Systems in Perspective and Catadioptric Imaging Applications

An imaging system with a single effective viewpoint is called a central projection system. The conventional perspective camera is an example of central projection system. A catadioptric realization of omnidirectional vision combines reflective surfaces with lenses. Catadioptric systems with an unique projection center are also examples of central projection systems. Whenever an image is acquired, points in 3D space are mapped into points in the 2D image plane. The image formation process represents a transformation from ³ to ², and mathematical models can be used to describe it. This paper discusses the definition of world coordinate systems that simplify the modeling of general central projection imaging. We show that an adequate choice of the world coordinate reference system can be highly advantageous. Such a choice does not imply that new information will be available in the images. Instead the geometric transformations will be represented in a common and more compact framework, while simultaneously enabling newer insights. The first part of the paper focuses on static imaging systems that include both perspective cameras and catadioptric systems. A systematic approach to select the world reference frame is presented. In particular we derive coordinate systems that satisfy two differential constraints (the compactness and the decoupling constraints). These coordinate systems have several advantages for the representation of the transformations between the 3D world and the image plane. The second part of the paper applies the derived mathematical framework to active tracking of moving targets. In applications of visual control of motion the relationship between motion in the scene and image motion must be established. In the case of active tracking of moving targets these relationships become more complex due to camera motion. Suitable world coordinate reference systems are defined for three distinct situations: perspective camera with planar translation motion, perspective camera with pan and tilt rotation motion, and catadioptric imaging system rotating around an axis going through the effective viewpoint and the camera center. Position and velocity equations relating image motion, camera motion and target 3D motion are derived and discussed. Control laws to perform active tracking of moving targets using visual information are established.     

分裂合并运动分割的多运动视觉里程计方法

目的 视觉里程计（visual odometry,VO）仅需要普通相机即可实现精度可观的自主定位,已经成为计算机视觉和机器人领域的研究热点,但是当前研究及应用大多基于场景为静态的假设,即场景中只有相机运动这一个运动模型,无法处理多个运动模型,因此本文提出一种基于分裂合并运动分割的多运动视觉里程计方法,获得场景中除相机运动外多个运动目标的运动状态。方法 基于传统的视觉里程计框架,引入多模型拟合的方法分割出动态场景中的多个运动模型,采用RANSAC（random sample consensus）方法估计出多个运动模型的运动参数实例;接着将相机运动信息以及各个运动目标的运动信息转换到统一的坐标系中,获得相机的视觉里程计结果,以及场景中各个运动目标对应各个时刻的位姿信息;最后采用局部窗口光束法平差直接对相机的姿态以及计算出来的相机相对于各个运动目标的姿态进行校正,利用相机运动模型的内点和各个时刻获得的相机相对于运动目标的运动参数,对多个运动模型的轨迹进行优化。结果 本文所构建的连续帧运动分割方法能够达到较好的分割结果,具有较好的鲁棒性,连续帧的分割精度均能达到近100%,充分保证后续估计各个运动模型参数的准确性。本文方法不仅能够有效估计出相机的位姿,还能估计出场景中存在的显著移动目标的位姿,在各个分段路径中相机自定位与移动目标的定位结果位置平均误差均小于6%。结论 本文方法能够同时分割出动态场景中的相机自身运动模型和不同运动的动态物体运动模型,进而同时估计出相机和各个动态物体的绝对运动轨迹,构建出多运动视觉里程计过程。     

Robust global motion estimation and novel updating strategy for sprite generation

A new global motion estimation technique for sprite coding systems is presented. The proposed system can accurately register frames to a sprite without referencing to the sprite. This allows the motion estimation process to be performed in an environment independent of the quality of the sprite. The frame having the highest resolution of the scene is determined and all other frames can be projected on to the space of this chosen frame such that information loss due to decimation can be avoided. The static sprite is strategically updated, according to the major camera motion during decoding, to alleviate the problem of error propagation from the sprite image. Experimental results indicate that the proposed technique is very accurate and robust, which makes it suitable for MPEG-4 sprite coding     

Outward-looking circular motion analysis of large image sequences

This work presents a novel and simple method of analyzing the motion of a large image sequence captured by a calibrated outward-looking video camera moving on a circular trajectory for large-scale environment applications. Previous circular motion algorithms mainly focus on inward-looking turntable-like setups. They are not suitable for outward-looking motion where the conic trajectory of corresponding points degenerates to straight lines. The circular motion of a calibrated camera essentially has only one unknown rotation angle for each frame. The motion recovery for the entire sequence computes only one fundamental matrix of a pair of frames to extract the angular motion of the pair using Laguerre's formula and then propagates the computation of the unknown rotation angles to the other frames by tracking one point over at least three frames. Finally, a maximum-likelihood estimation is developed for the optimization of the whole sequence. Extensive experiments demonstrate the validity of the method and the feasibility of the application in image-based rendering.     

Dynamic image stabilization precision test system based on the Hessian matrix

Dynamic image stabilization precision of an optical image-stable device is a key technical indicator.Therefore,a fast dynamic image stabilization precision test system for an optical image-stable device is developed.A large-aperture collimator with a designed cross divisional board is used to simulate the infinity goal.The image-stable device is installed on the motion simulator with six degrees of freedom which is used to simulate the moving state of the device.The CCD camera installed behind the eyepiece lens of the image-stable device acquires images rapidly and in real time.The local energy maxima center of the cross light spot can be acquired accurately through the proposed algorithm using the Hessian matrix.In addition,to deal with the CCD non-uniformity,an adaptive non-uniformity correction algorithm based on bi-dimensional empirical mode decomposition is provided.The actual test results for the proposed method show that the test error of dynamic image stabilization is less than 0.7,and the time for the frame image acquisition and processing is less than 10 ms,which demonstrates the effectiveness of the test system.     

A psychophysical study of improvements in motion‐image quality by using high frame rates

Abstract— The ideal frame rate for the highest motion‐image quality with respect to blur and jerkiness is presented. In order to determine the requirements for avoiding these impairments, motion images from a high‐speed camera and computer graphics were combined with a high‐speed display to perform a psychophysical evaluation. The camera, operating at 1000 fps, and image processing were used to simulate various frame rates and shutter speeds, and a 480‐Hz CRT display was used to present motion images simulating various frame rates and time characteristics of the display. Subjects were asked to evaluate the difference in quality between motion images at various frame rates. A frame rate of 480 fps was chosen to be an appropriate reference frame rate that, as a first estimation, enables coverage up to the human‐dynamic‐resolution (HDR) limit based on another experiment using real moving charts. The results show that a frame rate of 120 fps provides good improvement compared to that of 60 fps, and that the maximum improvement beyond which evaluation is saturated is found at about 240 fps for representative standard‐resolution natural images.     

Motion Panoramas

In this paper we describe a method for analysing video sequences and for representing them as mosaics or panoramas. Previous work on video mosaicking essentially concentrated on static scenes. We generalize these approaches to the case of a rotating camera observing both static and moving objects where the static portions of the scene are not necessarily dominant, as it has been often hypothesized in the past. We start by describing a robust technique for accurately aligning a large number of video frames under unknown camera rotations and camera settings. The alignment technique combines a feature‐based method (initialization and refinement) with rough motion segmentation followed by a colour‐based direct method (final adjustment). This precise frame‐to‐frame alignment allows the dynamic building of a background representation as well as an efficient segmentation of each image such that moving regions of arbitrary shape and size are aligned with the static background. Thus a motion panorama visualizes both dynamic and static scene elements in a geometrically consistent way. Extensive experiments applied to archived videos of track‐and‐field events validate the approach. Copyright © 2004 John Wiley & Sons, Ltd.     

基于相机姿势全局运动估计及改进修复算法的视频稳定技术

在视频稳定的过程中,由于摄像机的运动,造成图像的扭曲.针对这种情况,提出一种基于相机姿势的全局运动估计,同时为了克服图像拼接后,部分区域像素丢失的问题,使用改进后调和模型来修复缺少的像素.算法首先提取特征不变量,然后基于这些特征不变量去估计摄像机的运动矢量,相乘各帧间的运动矢量,可以得到每一帧参考第一帧的运动矢量.运用这个矢量可以很好地计算出没有扭曲的图像.运用计算出的图像与视频帧进行拼接,可以很好的解决图像的扭曲的问题.然而,图像拼接完成后可能导致部分区域像素缺少,为了填充缺少像素,算法使用了改进的调和模型来修复缺少区域.实验结果表明,基于相机姿势的全局运动估计可以很好的解决图像扭曲的问题,同时改进的调和模型可以高效的完成对图像的修复.     

一种压缩域中的快速运动目标提取算法

论文提出了一种工作于MPEG压缩域的快速运动目标提取算法。算法以通过部分解码得到的运动向量和亮度分量的直流DCT系数作为输入,提取P帧的运动目标。首先采用鲁棒性回归分析估计全局运动,标记出与全局运动不一致的宏块,得到运动块的分布;然后将运动向量场插值作为时间域的特征,将重构的直流图像转换到LUV颜色空间作为空间域的特征,采用快速平均移聚类找到时间和空间特征具有相似性的区域,得到细化的区域边界;最后结合运动块分布和聚类分析的结果,通过基于马尔可夫随机场的统计标号方法进行背景分离,得到运动目标的掩模。实验结果表明该算法可以有效地消除运动向量噪声的影响,并有很高的处理速度,对于CIF格式的视频码流,每秒可以处理约50帧。     

视频序列的全景图拼接技术

提出了一种对视频序列进行全景图拼接的方法。主要讨论了有大面积的非刚性运动物体出现的序列，不过此方法也同样适用于无运动物体的纯背景序列。为计算各帧间的投影关系，用仿射模型来描述摄像机运动，并用特征点匹配的方法计算出模型中各参数的值。由于用相关法计算的匹配结果准确率比较低，所以用RANSAC（Random Sampling Consensus）对匹配结果进行了筛选，可以准确求出摄像机运动参数。利用运动参数进行投影，然后用多帧相减并求交集，估计出每帧图像中运动物体存在的区域，最后计算得到了全景图。该方法的结果与前人得到的结果进行了比较，证明用此方法能获得质量较高的全景图。