Depth extraction of partially occluded objects using deformable net

Estimating depth using a single camera moving along its optical axis has great benefits to autonomous robot navigation. In Shaaban and Omar (2012) we estimated depth information for non-occluded regions using the change of their seen area. The proposed work extends this technique to handle regions with partial occlusion. As the robot moves, the seen area of a partially occluded region is different from the two points of view. Therefore, at least one of the edges is deceptive and is not a real object boundary. We propose a technique to detect deceptive-edges at the boundary of occlusion then use triangulation to detect the structure of occlusion. With this knowledge, we estimate the percentage change in the actual area seen as the camera moves. This percentage is used to correct the results of the original Area-based method. Experimentally the algorithm provides an average depth with good accuracy for both far and near objects.     

Three-dimensional parameter estimation from stereo image sequences for model-based image coding

It is shown that the analysis of moving image sequences for 3D modelling can be performed in a relatively straightforward manner if the scene is captured in stereo. Output from a stereo disparity estimation process using calibrated cameras gives absolute 3D surface coordinates from a single stereo pair. When combined with monocular motion cues, the true 3D motion parameters of moving objects can be accurately calculated. Further analysis enables segmentation of body elements according to motion while the 3D surface feature structure, although available from the start, can be integrated and checked for anomalies over the sequence. These results are expected to alleviate the known problems of ambiguity suffered by monocular-source model-based coders.     

融合颜色信息与深度信息的运动目标检测方法

基于颜色信息的运动目标检测易受光照、阴影等影响,基于深度信息的运动目标检测存在目标边缘噪声大,无法检测距离背景较近的目标等问题。针对上述问题,该文利用CCD相机获取的颜色信息及TOF相机获取的深度信息分别为每个像素建立颜色与深度信息的分类器,根据像素点的深度特征及前一帧的检测结果,自适应地为每个分类器的输出分配不同的权值,实现运动目标的检测。该文采集多组视频序列进行实验,实验结果表明该方法能有效解决单独利用颜色或深度信息进行运动目标检测时出现的问题。     

针对运动摄像机的快速低存储开销运动目标检测算法

摄像机的运动会导致整幅图像的运动,使得此情形下的目标检测极具挑战性。针对该问题提出一种快速低存储开销检测算法。首先,利用一种快速低存储开销配准方法计算相邻两帧的单应变换矩阵。而后,使用单应变换矩阵进行相邻两帧之间的配准,并由帧间差分获取帧间运动信息。最后,采用积累运动信息的方式构造不断更新的运动图像,通过对此运动图像进行阈值分割分离出最终的运动目标。在多个不同视频序列下的实验表明该算法能够有效地从嘈杂的场景中检测出运动目标。此外,与先前算法相比,该算法检测性能更好,且显著地降低了存储开销与计算时间开销。对于480360的序列而言,该算法需要的存储开销仅为825 kByte,且运算速度达到16帧/m。     

Spatiotemporal motion boundary detection and motion boundary velocity estimation for tracking moving objects with a moving camera: a level sets PDEs approach with concurrent camera motion compensation

The purpose of this study is to investigate a method of tracking moving objects with a moving camera. This method estimates simultaneously the motion induced by camera movement. The problem is formulated as a Bayesian motion-based partitioning problem in the spatiotemporal domain of the image quence. An energy functional is derived from the Bayesian formulation. The Euler-Lagrange descent equations determine imultaneously an estimate of the image motion field induced by camera motion and an estimate of the spatiotemporal motion undary surface. The Euler-Lagrange equation corresponding to the surface is expressed as a level-set partial differential equation for topology independence and numerically stable implementation. The method can be initialized simply and can track multiple objects with nonsimultaneous motions. Velocities on motion boundaries can be estimated from geometrical properties of the motion boundary. Several examples of experimental verification are given using synthetic and real-image sequences.     

鱼眼相机导引下的双目跟踪系统

在智能监控领域,鱼眼相机比传统摄像机拥有更大视野,然而由于其分辨率的限制及鱼眼图像畸变的影响,使得目标物的细节信息难以观察,为克服这个难题,搭建了鱼眼相机导引下的双目跟踪系统。该系统利用鱼眼相机进行全景观察,检测出目标物,采用角度拟合法求出目标物的方位角,通过云台控制双目相机精确定位到目标物,然后对目标物进行距离测量,并使目标在不同的位置进行实验。实验结果表明,系统能准确检测出鱼眼图像中的运动目标,角度标定精度达到系统要求,双目相机能准确测出目标物距离。该智能监控系统能够减小鱼眼相机畸变对检测结果的影响,具有检测视场广和检测精度高的特点,为智能监控技术提供了检测方法。     

手持式线激光源3D扫描系统

以手持式线激光源为工具,采用摄像方式,实现一种简便、易行的3D表面快速反求建模方法;避免了复杂的光学系统、机电控制系统设计,只需在线激光源扫掠物体表面的同时,连续摄像,通过对光条图象序列进行处理,得到物体的3D模型.文中给出了复杂形体的建模实例,效果基本满意.     

基于机器视觉的三维重建技术研究

研究了基于机器视觉的三维重建技术。利用普通的数码摄像机拍摄图片,通过摄像机定标、特征点检测和匹配、基础矩阵和本质矩阵计算来实现图像的三维重建。采用张正友标定方法的相机标定工具箱实现了相机的标定,利用尺度不变特征变换(SIFT)特征点的检测和匹配方法进行了图像特征点的检测和匹配,采用RANSAC算法计算基础矩阵,最后利用相机内参数和由基础矩阵获得的本质矩阵重建物体的特征点,并进行纹理贴图。实验结果表明利用这些图像可以进行物体重建,并且能够很好地反映出物体的三维特征。     

Image segmentation through graph-based clustering from surface normals estimated by photometric stereo

A method for segmenting 2D images based on 3D shape information is proposed. First, a robust photometric stereo technique estimates the 3D normals of the objects present in the scene for every image pixel. Then, the image is segmented by grouping its pixels according to their estimated normals through graph-based clustering. Differently from other image segmentation algorithms based on intensity, colour or texture, the regions of which are determined by the visual appearance of the depicted objects, the regions obtained with the proposed technique only depend on the 3D shapes of those objects. This can be advantageous for higher level scene understanding algorithms. This technique is especially suited to poorly illuminated scenarios and utilises a conventional camera and six inexpensive strobe lights.     

3D-objecttracking with a mixed omnidirectional stereo camera system

This paper presents a novel technique of stereo vision based on the combination of an omnidirectional camera and a perspective camera. The technique combines the 360° field of view of the omnidirectional camera with the long field of view of a perspective camera. We describe the setup of such a camera system and how it can be used to achieve 3D-position estimates. Furthermore, we develop a maximum likelihood approach and a Bayesian approach that are able to fuse monocular and binocular observations of the same object to estimate its position and movement and show how this technique can be applied successfully in the RoboCup MiddleSizeLeague.     

Motion compensating interpolation considering covered and uncovered background

An improved algorithm for motion compensating interpolation of images in digital television sequences is presented. The algorithm is applicable to the interpolation of skipped images in the environment of a low bit rate codec. It is based on the assumption of pure translatorily moving objects. A low complex hierarchical blockmatching algorithm is used to estimate displacement vector fields, which are a close approximation of the true motion. The estimated displacement vector fields are evaluated in combination with the information of a change detector, in order to derive a segmentation of the images into moving objects, static background, covered, and uncovered background. Especially in the case of interpolating more than one image between every two transmitted images, it has to be taken into account that for each of these images an individual displacement vector field and an individual segmentation is required. This is achieved through a transformation of motion information based on the estimation of one displacement vector field for each pair of transmitted images, only. A spatio-temporal filter, controlled by the displacement and segmentation information, is used to interpolate the desired number of images. Computer simulations confirm, that the presented algorithm provides a remarkably improved rendition of motion, even if video sequences are strongly distorted with coding noise caused by a low bit rate coding process.     

基于双目机器人的实时测距与追踪系统

传统的双目立体视觉系统很难同时实现对运动目标的实时测距和追踪.本文设计了一种仿人脖项的双目立体视觉平台:左右摄像机相对位置固定,并安装在一个可做水平转动和垂直俯仰运动的机架上.该系统可以灵活而准确的追踪运动目标,并实时地确定运动目标到立体视觉平台的距离.通过对多种运动的追踪,验证了该系统的准确与稳定性.     

一种脉冲激光雷达与摄像机标定方法的研究

激光雷达和CCD摄像机各自都具有快速获取物体空间信息的能力,广泛应用在真实场景的三维建模中。激光雷达与CCD摄像机数据融合面临的首要问题是二者之间坐标系的标定,针对脉冲激光雷达和CCD的特点设计了一种三维标定靶,提出了一种改进的外部标定算法,利用主成分分析法拟合平面,提高了标定精度。将激光雷达和CCD标定算法运用在物体三维建模中,研究了基于外部标定算法的三维重建和纹理映射,取得了较好效果。     

基于相机标定的非对称裁剪检测算法

该文提出一种针对图像非对称裁剪的取证方法,算法通过相机标定的方法来估计主点位置,并根据主点的位置对图像中存在的非对称裁剪进行指证。该文根据图像取证需求改进了相机标定模型,通过选取不共面的规则图形作为标定物,实现了在不用对标定物进行测量和建模的前提下通过单幅图像对主点坐标进行估计。实验表明,该文提出的算法对非对称裁剪篡改具有较好的检测效果。     

Motion and structure from feature correspondences: a review

We present a review of algorithms and their performance for determining three-dimensional (3D) motion and structure of rigid objects when their corresponding features are known at different times or are viewed by different cameras. Three categories of problems are considered, depending upon whether the features are two (2D) or three-dimensional (3D) and the type of correspondence: a) 3D to 3D (i.e., locations of corresponding features in 3D space are known at two different times), b) 2D to 3D (i.e., locations of features in 3D space and their projection on the camera plane are known, and c) 2D to 2D (i.e., projections of features on the camera plane are known at two different times). Features considered include points, straight lines, curved lines, and corners. Emphasis is on problem formulation, efficient algorithms for solution, existence and uniqueness of solutions, and sensitivity of solutions to noise in the observed data. Algorithms described have been used in a variety of applications. Some of these are: a) positioning and navigating 3D objects in a 3D world, b) camera calibration, i.e., determining location and orientation of a camera by observing 3D features whose location is known, c) estimating motion and structure of moving objects relative to a camera. We mention some of the mathematical techniques borrowed from algebraic geometry, projective geometry, and homotopy theory that are required to solve these problems, list unsolved problems, and give some directions for future research     

远距离监视激光雷达动目标快速检测

激光雷达具有全天候工作、探测精度高、有效探测距离远、易获得三维信息等特点,但工作在远距离模式时,目标点云比较稀疏。当前便携条件下,基于深度学习的算法在激光雷达点云数据直接目标识别时,实时性和成功率尚不能达到远程监视实际工程的要求。针对实际工程中利用激光雷达检测运动目标进而实时引导高分辨率相机的需求,采用基于变化的检测方法,对远距离条件下激光雷达的运动目标检测方法进行了研究,利用点云数据的距离信息,给出三维单高斯模型和三维高斯混合模型检测动目标的过程和方法,提出了利用杂波图恒虚警率检测法处理点云数据的方法。实验表明,与二维图像动目标检测方法相比,三维单高斯模型法会很大程度提高检测准确性,降低虚警率,但仍然存在较高虚警率。为适应复杂三维场景,采用基于三维高斯混合模型的方法进一步降低了虚警率,但也降低了检测速度;而杂波图CFAR的方法具有很高的实时性,同时也具有较好的检测性能。     

视频中运动目标结构特征提取的子区域分割方法

视频中为了研究运动目标的结构特征,利用最远点、信息瓶颈、均值漂移等方法对运动目标进行图像分割实验,获得运动目标的结构子区域。通过对比实验数据,用均值漂移分割方法获得的运动目标子区域较合理,为下一步研究视频中运动目标结构特征提供了合适的运动目标结构子区域,对深入研究运动目标结构特征,利用结构特征进行目标跟踪与识别具有重要意义。     

基于摄像机运动控制的实时对象检测与跟踪算法

提出了一种基于摄像机运动控制的实时运动对象检测与跟踪算法.该算法首先采用非参数核密度估计方法在复杂的动态背景条件下检测运动对象区域;然后由CamShift算法计算跟踪目标的位置,并采用Kalman滤波预测对象的运动信息来控制摄像机的运动,能够准确地跟踪对象并有效解决了背景中的部分遮挡问题.在SonyRZ25网络摄像机上完成了对象的实时检测与跟踪,对多个室内和室外场景的实验验证了所提出方法的实用性和有效性.     

Calculation of 3D trajectories of moving objects fromunsynchronised stereo video signals

A method for the 3D reconstruction of moving objects from unsynchronised stereo video signals is presented. Using a video mosaicing technique for each video signal, all frames are registered in a reference frame and the trajectories of moving objects obtained as a static structure in a scene, so that correspondence can be determined from an epipolar geometry