Feature detection and tracking in optical flow on non-flat manifolds

Optical flow is a classical approach to estimating the velocity vector fields associated to illuminated objects traveling onto manifolds. The extraction of rotational (vortices) or curl-free (sources or sinks) features of interest from these vector fields can be obtained from their Helmholtz-Hodge decomposition (HHD). However, the applications of existing HHD techniques are limited to flat, 2D domains. Here we demonstrate the extension of the HHD to vector fields defined over arbitrary surface manifolds. We propose a Riemannian variational formalism, and illustrate the proposed methodology with synthetic and empirical examples of optical-flow vector field decompositions obtained on a variety of surface objects.     

Scalable continuous object detection and tracking in sensor networks

With the advancement of MEMS technologies, sensor networks have opened up broad application prospects. An important issue in wireless sensor networks is object detection and tracking, which typically involves two basic components, collaborative data processing and object location reporting. The former aims to have sensors collaborating in determining a concise digest of object location information, while the latter aims to transport a concise digest to sink in a timely manner. This issue has been intensively studied in individual objects, such as intruders. However, the characteristic of continuous objects has posed new challenges to this issue. Continuous objects can diffuse, increase in size, or split into multiple continuous objects, such as a noxious gas. In this paper, a scalable, topology-control-based approach for continuous object detection and tracking is proposed. Extensive simulations are conducted, which show a significant improvement over existing solutions.     

对数极坐标域梯度光流跟踪研究

针对直角坐标系中光流跟踪算法无法跟踪存在旋转和尺度变化目标图像的问题,在分析Horn-Schunck经典光流计算公式基础上,提出了一种对数极坐标域的梯度跟踪算法。该算法可以对存在旋转和尺度变化的运动目标实施跟踪,通过实验证明了这种方法在处理运动图像变化时是有效的。因而,这种用对数极坐标域的跟踪算法有一定的实用价值。     

Visual object tracking using similarity transformation and adaptive optical flow

Multimedia Tools and Applications - Visual object tracking is among the most attractive topics in various applications of vision system. Target objects’ appearance often drastically changes...     

Unified optical flow field approach to motion analysis from a sequence of stereo images

In this paper a new approach to motion analysis from stereo image sequences using unified temporal and spatial optical flow field (UOFF) is reported. That is, based on a four-frame rectangular model and the associated six UOFF field quantities, a set of equations is derived from which both position and velocity can be determined. It does not require feature extraction and correspondence establishment, which are known to be difficult, and only partial solutions suitable for simplistic situations have been developed. Furthermore, it is capable of detecting multiple moving objects even when partial occlusion occurs, and is potentially suitable for nonrigid motion analysis. Unlike the current existing techniques for motion analysis from stereo imagery, the recovered motion by using this new approach is for a whole continuous field instead of only for some features. It is a purely optical flow approach. Two experiments are presented to demonstrate the feasibility of the approach.     

Video object tracking based on improved gradient vector flow snake and intra-frame centroids tracking method

Accurately tracking the video object in video sequence is a crucial stage for video object processing which has wide applications in different fields. In this paper, a novel video object tracking algorithm based on the improved gradient vector flow (GVF) snake model and intra-frame centroids tracking algorithm is proposed. Unlike traditional gradient vector flow snake, the improved gradient vector flow snake adopts anisotropic diffusion and a four directions edge operator to solve the blurry boundary and edge shifting problem. Then the improved gradient vector flow snake is employed to extract the object contour in each frame of the video sequence. To set the initial contour of the gradient vector flow snake automatically, we design an intra-frame centroids tracking algorithm. Splitting the original video sequence into segments, for each segment, the initial contours of first two frames are set by change detection based on t-distribution significance test. Then, utilizing the redundancy between the consecutive frames, the subsequent frames’ initial contours are obtained by intra-frame motion vectors. Experimental results with several test video sequences indicate the validity and accuracy of the video object tracking.     

Smoothing of optical flow using robustified diffusion kernels

This paper proposes a new optical flow smoothing methodology combining vector diffusion and robust statistics. Vector smoothing using diffusion preserves moving object boundaries and the main motion discontinuities. According to a study provided in the paper, diffusion does not remove the outliers but spreads them out, introducing a bias in the neighbourhood. In this paper robust statistics operators such as the median and alpha-trimmed mean are considered for robustifying the diffusion kernels. The robust diffusion smoothing process is extended to 3-D lattices as well. The proposed algorithms are applied for smoothing artificially generated vector fields as well as the optical flow estimated from image sequences.     

Simulation of an optical sensing system for automatic object tracking

An optical guiding system is modeled and the signal processing and its operation are studied. Our model is based on the principle that two moving objects are considered, in which one is the moving robot, and the other one is the sought object. The reported system is capable of detecting and measuring the relative motion of the target, and, in response generating electrical signal capable of directing and guiding the vehicle on the shop floor. In this way, the respected robot or vehicle using such a device can maintain its aim on the related target scene at all times. The proposed system offers a higher degree of accuracy and reliability since it considers the state-of-art electronic and optical components for signal processing. A software package (ORCAD 9) is used to simulate signal processing of such an optical tracking system and the results are reported.     

Fast optical flow using 3D shortest path techniques

Optical flow or image motion estimation is important in the area of computer vision. This paper presents a fast and reliable optical flow algorithm which produces a dense optical flow map by using fast cross correlation and 3D shortest path techniques. Fast correlation is achieved by using the box-filtering technique which is invariant to the size of the correlation window. The motion for each scanline or each column of the input image is obtained from the correlation coefficient volume by finding the best 3D path using dynamic programming techniques rather than simply choosing the position that gives the maximum cross correlation coefficient. Sub-pixel accuracy is achieved by fitting the local correlation coefficients to a quadratic surface. Typical running time for a 256×256 image is in the order of a few seconds on a 85 MHz computer. A variety of synthetic and real images have been tested, and good results have been obtained.     

空间区域中对象流动模式构建方法研究

随着时空数据获取设备的普及应用,产生了大量反映移动对象活动的位置数据,数据的海量性及分析的复杂性决定了该类数据为典型的大数据。位置数据中的到达和离开可以反映移动对象的流动规律,可以表示为区域的流动模式,本文研究空间区域中移动对象流动模式的构建方法,将区域的流动规律以时间序列进行定量表示,模式可用于指导交通、安全等方面的可预测调度。由于对象流动的随机性,使得构建高预测精度的模式成为一个挑战。提出一种基于层次聚类的流动模式构建模型,模型中通过数据的离散化、序列化、模式训练等步骤实现模式构建;提出偏斜度层次聚类树及异常序列去除方法,可以有效去除局部异常序列及自动聚簇选取,提高了模式的预测精度。利用真实数据集对所提出的模式训练方法进行了充分的实验,验证了所构建的空间区域中的流动模式可以用于表达区域中对象的流动规律,所提出的模式训练方法与现有的训练方法相比具有较高的预测精度。     

Harris角点结合金字塔光流法的目标跟踪算法设计研究

针对现存很多跟踪算法在速度和准确度方面很难满足嵌入式跟踪开发的需要,提出一种基于Harris角点和金字塔光流法的快速跟踪算法,并详细给出了DSP-FPGA的硬件设计。首先,使用Harris角点提取目标角点特征;然后,使用金字塔光流法为后续视频帧匹配角点;最后,基于角点的质心跟踪算法用于匹配目标的重心,确定目标的位置,重心跟踪算法可以较好地抵消由于旋转或扭曲带来的形变问题。在硬件实现过程中,FPGA方便电路设计,使用硬件描述程序语言实现硬件算法、逻辑控制和外部接口,DSP则运行目标跟踪算法。实验结果验证了本文硬件实现算法的有效性,相比于AVT21开发板的质心跟踪算法、相位相关跟踪算法和金字塔相关性跟踪算法相比,本文算法在平均重叠和平均中心误差方面具有一定优势,在720p的视频流上可以满足25fps。     

Real-time parallel computation of disparity and optical flow using phase difference

A phase-difference-based algorithm for disparity and optical flow estimation is implemented on a TI-C40-based parallel DSP system. The module performs real-time computation of disparity maps on images of size 128 × 128 pixels and computation of optical flows on images of size 64 × 64 pixels. This paper describes the algorithm and its parallel implementation. Processing times required for the computation of disparity maps and velocity fields and measures of the algorithm's performance are reported in detail.     

Efficient tracking of moving objects using a relational database

Tracking uncooperative moving objects by means of radar is a complex task due to clutter and association problems in multi-target scenarios. An approach to solve this problem is probabilistic multiple hypothesis tracking (PMHT). This method combines classical track filtering with a likelihood ratio test for the estimation of the plot-to-track association. The basics of PMHT and similar algorithms have gained much attention recently. However, the efficient implementation of real world applications of this technique still represents a challenging task. Since a common requirement in this context is the reliable storage of track data in a database, an implementation of the tracker's calculation inside a database management system (DBMS) using SQL views is desirable. A naive implementation of PMHT using a commercial DBMS, however, usually leads to performance problems because of the high frequency of measurement updates. In this paper, we propose possible optimizations for solving these performance problems. Their usage leads to a dramatic run-time improvement in our sample case and makes the implementation of PMHT in a database context feasible.     

Finding the focus of expansion and estimating range using optical flow images and a matched filter

The focus of expansion plays an important role in many vision applications such as three-dimensional reconstruction, range estimation, time-to-impact computation, and obstacle avoidance. Most current techniques are based on correspondence or on accurate flow estimation and are therefore considered computationally heavy. This paper presents an efficient technique to find the focus of expansion from optical flow. The technique utilizes a specially designed matched filter that does not require an exact estimation of the optical flow but rather can use a low-quality estimation of it. In addition, based on the location of the focus of expansion and its immediate neighborhood, the paper suggests a way to estimate the range to the focus of expansion. Based on the experimental results, the technique has proved to be both accurate and efficient.Received: 26 January 2003, Accepted: 18 March 2004, Published online: 14 September 2004 Correspondence to: Didi Sazbon     

点线光流预测机制的图像序列运动直线跟踪

目的 针对复杂场景图像序列中运动直线特征的提取、跟踪问题,提出一种基于点、线光流预测机制的图像序列运动直线跟踪方法。方法 首先根据图像直线的表达式定义点、线光流基本约束方程,由基本约束方程推导出关于点光流与直线光流对应关系的3个重要推论。然后依据点、线光流对应关系,利用图像序列中直线特征上的像素点光流计算直线光流的估计值并根据直线光流阈值筛选图像序列运动直线。最后由筛选出的运动直线及直线光流估计值计算直线的预测坐标并在Hough域内进行跟踪匹配,得到图像序列运动直线跟踪结果。结果 通过合成及真实图像序列实验验证,本文方法能够准确地筛选出图像序列中感兴趣的运动直线,并对运动直线进行稳定地跟踪、匹配,直线跟踪结果未产生干扰直线的误匹配,直线跟踪时间消耗不超过12 s。结论 相对于传统的直线跟踪、匹配方法,本文方法具有较高地直线跟踪精度和较好的鲁棒性,更适用于复杂场景下的运动直线跟踪、匹配问题。     

Detecting dings and dents on specular car body surfaces based on optical flow

This paper introduces a new approach to detect defects cataloged as dings and dents on car body surfaces, which is currently one of the most important issues facing quality control in the automotive industry. Using well-known optical flow algorithms and the deflectometry principle, the method proposed in this work is able to detect all kind of anomalies on specular surfaces. Hence, our method consists of two main steps: first, in the pre-processing step, light patterns projected on the body surface sweep uniformly the area of inspection, whilst a new image fusion law, based on optical flow, is used to obtain a resulting fused image holding the information of all variations suffered by the projected patterns during the sweeping process, indicating the presence of anomalies; second, a new post-processing step is proposed that avoids the need of using pre-computed reference backgrounds in order to differentiate defects from other body features such as style-lines. To that end, the image background of the resulting fused image is estimated in the first place through a method based on blurring the image according to the direction of each pixel. Afterwards, the estimated image background is used in a new subtraction law through which defects are well differentiated from other surface deformations, allowing the detection of defects in the entire illuminated area. In addition, since our approach, together with the system used, computes defects in less than 15 s, it satisfies the assembly plants time requirements. Experimental results presented in this paper are obtained from the industrial automatic quality control system QEyeTunnel employed in the production line at the Mercedes-Benz factory in Vitoria, Spain. A complete analysis of the algorithm performance will be shown here, together with several tests proving the robustness and reliability of our proposal.     

稀疏光流快速计算的动态目标检测与跟踪

动态目标的检测与跟踪作为图像处理和计算机视觉学科的重要分支,广泛应用于军事和民用等各个领域。文中提出一种基于稀疏光流快速计算的目标检测和跟踪新方法,该方法通过计算能反映图像特征的特定像素点光流矢量来实现目标检测和跟踪,同时结合图像金字塔技术,可以检测和跟踪运动速度更快、运动尺度更大的目标。文中将该方法分别与稠密光流方法和基于颜色特征方法作对比,结果表明该方法有计算量小、能很好应对目标遮挡情况和能检测和跟踪运动速度较快的目标等诸多优点。实验在多种条件下对该方法进行了验证,跟踪准确率都能达到80%以上,且基本能符合实时性的要求,说明该方法具有可行性和实用价值。     

The flow resistance of single DNA-grafted colloids as measured by optical tweezers

In rheological experiments, the flow resistance of single blank or DNA-grafted colloids is determined and compared. The length of the double-stranded-DNA varies amongst 1,000, 4,000 and 6,000 base pairs (bp) corresponding to contour lengths varying between 340 and 2,040 nm at a grafting density of 0.03±0.01 μm²/chain. The degree of swelling of the grafted DNA is adjusted by exchanging the ion concentration of the surrounding medium. For all examined flow velocities ranging between 100 and 1,200 μm/s, one observes an interesting deviation from Stokes law which can be traced back to a shear-dependent conformational change of the brush layer. The ratio of the effective hydrodynamic radii of DNA-grafted and blank colloids shows a pronounced dependence on the flow velocity, but as well on the length of the grafted DNA and the ionic strength of the solvent. The experimental findings are in qualitative agreement with hydrodynamic simulations based on an elastically jointed chain model.