Adaptive pyramid mean shift for global real-time visual tracking

Tracking objects in videos using the mean shift technique has attracted considerable attention. In this work, a novel approach for global target tracking based on mean shift technique is proposed. The proposed method represents the model and the candidate in terms of background weighted histogram and color weighted histogram, respectively, which can obtain precise object size adaptively with low computational complexity. To track targets whose displacements between two successive frames are relatively large, we implement the mean shift procedure via a coarse-to-fine way for global maximum seeking. This procedure is termed as adaptive pyramid mean shift, because it uses the pyramid analysis technique and can determine the pyramid level adaptively to decrease the number of iterations required to achieve convergence. Experimental results on various tracking videos and its application to a tracking and pointing subsystem show that the proposed method can successfully cope with different situations such as camera motion, camera vibration, camera zoom and focus, high-speed moving object tracking, partial occlusions, target scale variations, etc.     

Video stabilization using maximally stable extremal region features

Video stabilization is an important technique in present day digital cameras as most of the cameras are hand-held, mounted on moving platforms or subjected to atmospheric vibrations. In this paper we propose a novel video stabilization scheme based on estimating the camera motion using maximally stable extremal region features. These features traditionally used in wide baseline stereo problems were never explored for video stabilization purposes. Through our extensive experiments show we how some properties of these region features are suitable for the stabilization task. After estimating the global camera motion parameters using these region features, we smooth the motion parameters using a gaussian filter to retain the desired motion. Finally, motion compensation is carried out to obtain a stabilized video sequence. A number of examples on real and synthetic videos demonstrate the effectiveness of our proposed approach. We compare our results to existing techniques and show how our proposed approach compares favorably to them. Interframe Transformation Fidelity is used for objective evaluation of our proposed approach.     

Recognizing 50 human action categories of web videos

Action recognition on large categories of unconstrained videos taken from the web is a very challenging problem compared to datasets like KTH (6 actions), IXMAS (13 actions), and Weizmann (10 actions). Challenges like camera motion, different viewpoints, large interclass variations, cluttered background, occlusions, bad illumination conditions, and poor quality of web videos cause the majority of the state-of-the-art action recognition approaches to fail. Also, an increased number of categories and the inclusion of actions with high confusion add to the challenges. In this paper, we propose using the scene context information obtained from moving and stationary pixels in the key frames, in conjunction with motion features, to solve the action recognition problem on a large (50 actions) dataset with videos from the web. We perform a combination of early and late fusion on multiple features to handle the very large number of categories. We demonstrate that scene context is a very important feature to perform action recognition on very large datasets. The proposed method does not require any kind of video stabilization, person detection, or tracking and pruning of features. Our approach gives good performance on a large number of action categories; it has been tested on the UCF50 dataset with 50 action categories, which is an extension of the UCF YouTube Action (UCF11) dataset containing 11 action categories. We also tested our approach on the KTH and HMDB51 datasets for comparison.     

Traction force between rotating rolls and moving web considering the effect of air-entrainment

High-speed transportation of paper web sometimes leads the web handling system into unstable state because of increase in the air-entrainment into the gap between a rotating roll and moving web or the nip region of winding system. In this paper, the property of the traction change with increase in the air-entrainment into the gap between a paper roll and web or the nip region of winding system was investigated experimentally and theoretically. The critical speed to avoid slippage between a roll and web was found to be estimable by applying and extending the concept of “effective” frictional coefficient with the consideration of air-entrainment, which is proposed by Good et al. (Proceedings of the fourth international conference on web handling, 1997), Hashimoto (Proc JSME 1999(5):183–184, 1999a) and so on, to the estimation of the traction force defined as the frictional force on a paper roll or at the nip region. Consequently, the web handling stability at high-speed was found to be predictable.     

旋转圆环平面外振动的行波法研究

以高速球轴承保持架为应用对象,针对旋转薄壁圆环的平面外振动问题,开展弹性波传播的基本特性研究,分析平面外波动的色散方程、波数、截止频率、相速度以及位移耦合系数.基于行波动力学方法,根据波动正向传递的判据,将正负行波的波数进行分离.结合相位封闭原理和波传递矩阵,建立旋转圆环的频率特征方程.文中算例给出了旋转薄壁圆环平面外振动的固有频率,对其计算结果与文献结果作了比较,验证了计算方法的准确性.     

Web Communities: Models and Algorithms

In the last few years, a lot of research has been devoted to developing new techniques for improving the recall and the precision of current web search engines. Few works deal with the interesting problem of identifying the communities to which pages belong. Most of the previous approaches try to cluster data by means of spectral techniques or by means of traditional hierarchical algorithms. The main problem with these techniques is that they ignore the relevant fact that web communities are social networks with distinctive statistical properties.In this paper we analyze web communities on the basis of the evolution of an initial set of hubs and authoritative pages. The evolution law captures the behaviour of page authors with respect to the popularity of existing pages for the topics of interest. Assuming such a model, we have found interesting properties of web communities. On the basis of these properties we have proposed a technique for computing relevant properties for specific topics. Several experiments confirmed the validity of both the model and identification method.     

Extracting mobile objects by sequential background detection on a video

This paper describes a technique for extracting moving objects from a video image sequence taken by a slowly moving camera as well as a fixed camera. The background subtraction method is effective for extracting moving objects from a video. But the latest background image should be employed for the subtraction in the mobile camera case and in order not to be influenced by the light intensity change. A temporal median technique is proposed in this paper which detects the background at every moment. The camera motion is estimated using a local correlation map and the temporal median filter is applied to the common image area among a set of successive image frames to extract the background. The technique was applied to the video images obtained at a junction from a hand-held camera and those taken at a pedestrians crossing by a camera fixed in a car and successfully detected pedestrians. This work was presented in part at the 13th International Symposium on Artificial Life and Robotics, Oita, Japan, January 31–February 2, 2008     

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.     

Zero-phase velocity tracking of vibratory systems with actuation constraints

In this paper, a novel filter for precise tracking of constant velocity signals is presented, which allows the reduction of residual vibrations along with the compliance with kinematic constraints that affect the actuation system. A technique achieving both these two objectives at the same time is the main contribution of the work. The filter is based on a cascade of smoothers, i.e. dynamic filters that act on the input signal by increasing its continuity level. Unfortunately, when applied to a generic input composed by ramp (and step) functions, the filter introduces a phase delay not acceptable in many applications where moving parts have to be mated, such as high-speed automatic machines. In order to guarantee a perfect synchronization between the original and the filtered reference signal, once the transient is terminated, a proper compensation scheme has been designed. Moreover, the expressions of the smoothers parameters which assure vibration cancellation at specific frequencies and compliance with given bounds on velocity and acceleration have been analytically deduced. By means of an extensive experimental activity, the effectiveness of the proposed approach has been demonstrated, by comparing its performances with the results of well established approaches for vibrations suppression or signal derivatives limitation.     

Design of a multilink-articulated wheeled pipeline inspection robot using only passive elastic joints

This paper presents a multilink-articulated robot with omni and hemispherical wheels (AIRo-2.1) for inspecting and exploring pipelines. To quickly adapt to winding pipes, holonomic rolling movement without moving forward and backward is useful. However, this requires the rolling actuators to replace the driving actuators at the expense of the driving force. Furthermore, so far the number of driving wheels and torsion springs, magnitude of driving forces, stiffness and natural angle of the spring that are required to adapt to various pipelines have not been clarified. In this paper, we investigate the possibility of high maneuverability of multilink-articulated robots in winding pipes with as few driving actuators as possible and only elastic joints (torsion springs) for body bending. We further validate its effectiveness by experimental verification.     

A hierarchy of cameras for 3D photography

The view-independent visualization of 3D scenes is most often based on rendering accurate 3D models or utilizes image-based rendering techniques. To compute the 3D structure of a scene from a moving vision sensor or to use image-based rendering approaches, we need to be able to estimate the motion of the sensor from the recorded image information with high accuracy, a problem that has been well-studied. In this work, we investigate the relationship between camera design and our ability to perform accurate 3D photography, by examining the influence of camera design on the estimation of the motion and structure of a scene from video data. By relating the differential structure of the time varying plenoptic function to different known and new camera designs, we can establish a hierarchy of cameras based upon the stability and complexity of the computations necessary to estimate structure and motion. At the low end of this hierarchy is the standard planar pinhole camera for which the structure from motion problem is non-linear and ill-posed. At the high end is a camera, which we call the full field of view polydioptric camera, for which the motion estimation problem can be solved independently of the depth of the scene which leads to fast and robust algorithms for 3D Photography. In between are multiple view cameras with a large field of view which we have built, as well as omni-directional sensors.     

Heterogeneous multisensor fusion for mapping dynamic environments

In this paper, we propose a heterogeneous multisensor fusion algorithm for mapping in dynamic environments. The algorithm synergistically integrates the information obtained from an uncalibrated camera and sonar sensors to facilitate mapping and tracking. The sonar data is mainly used to build a weighted line-based map via the fuzzy clustering technique. The line weight, with confidence corresponding to the moving object, is determined by both sonar and vision data. The motion tracking is primarily accomplished by vision data using particle filtering and the sonar vectors originated from moving objects are used to modulate the sample weighting. A fuzzy system is implemented to fuse the two sensor data features. Additionally, in order to build a consistent global map and maintain reliable tracking of moving objects, the well-known extended Kalman filter is applied to estimate the states of robot pose and map features. Thus, more robust performance in mapping as well as tracking are achieved. The empirical results carried out on the Pioneer 2DX mobile robot demonstrate that the proposed algorithm outperforms the methods a using homogeneous sensor, in mapping as well as tracking behaviors.     

A mathematical model to predict surface roughness and pattern thickness in roll-to-roll gravure printed electronics

The roll-to-roll printing processes have recently been applied for the manufacturing of printed electronics due to their advantages, such as their high-throughput capabilities and low associated costs. In a roll-to-roll printing machine, a web or substrate is moved from an unwinding roll to a winding roll. During printing, the operating tension is important for correct substrate handling to prevent substrate defects, such as wrinkles, scratches and breaks. Accordingly, the operating conditions of the moving web can affect the quality of the printed pattern. In this study, a mathematical model has been developed to predict the thickness and surface roughness of printed patterns. Because the dynamics of roll-to-roll printing systems are complicated and non-linear, a statistical model is preferred. A full factorial method has been used with four independent variables: operating tension, print speed, ink viscosity and theoretical transfer volume. This model accurately predicted the surface roughness and thickness of the printed pattern.     

Free frequencies and modal shapes of cylindrical vibrating composite structures

The aim of this research is to determine the free frequencies and vibration eigenmodes of cylindrical structures clamped at the ends, manufactured with composite materials by the filament winding technique, typical of vessels of aerospace vehicles. A simplified numerical model for the analysis of the flexural-torsional and in-plane dynamic behaviour has been set up. Two different procedures have been utilized and developed and a comparison of the convergence rate of both methods has been performed. Numerical values of relevant frequencies have been pointed out, which can influence the stability conditions of the aerospace vehicle containing cylindrical vessels. Also the dependence of the numerical results on the winding angle has been considered, which can be important for the design of the cylindrical composite structure.     

Visually guided ranging from observations of points, lines and curves via an identifier based nonlinear observer

In this paper we consider the problem of estimating the range information of features on an affine plane in by observing its image with the aid of a CCD camera, wherein we assume that the camera is undergoing a known motion. The features considered are points, lines and planar curves located on planar surfaces of static objects. The dynamics of the moving projections of the features on the image plane have been described as a suitable differential equation on an appropriate feature space. This dynamics is used to estimate feature parameters from which the range information is readily available. In this paper the proposed identification has been carried out via a newly introduced identifier based observer. Performance of the observer has been studied via simulation.     

Active Tuning of Intrinsic Camera Parameters

In the last years, the research effort of the scientific community to study systems for ambient intelligence has been really strong. Usually, the systems developed so far base their analysis on images acquired by automatic cameras. In this paper, we propose a way to develop new smart systems that are able to actively decide both what to see and how to see it. In particular, the main idea is to tune the acquisition parameters on the basis of what the system desires to acquire. The regulation strategy is based on two camera parameters, focus and iris. It aims to identify an optimal sequence of steps to enhance the acquisition quality of an object of interest. To this end, a hierarchy of neural networks has been employed first to select which parameter must be regulated then to adjust it. The proposed solution can be applied to both static and moving cameras. The results show how the proposed technique can be applied to images acquired by a moving camera with zoom capabilities for surveillance purposes.     

Adaptive Indexing of Moving Objects with Highly Variable Update Frequencies

In recent years, management of moving objects has emerged as an active topic of spatial access methods. Various data structures （indexes） have been proposed to handle queries of moving points, for example, the well-known B^x-tree uses a novel mapping mechanism to reduce the index update costs. However, almost all the existing indexes for predictive queries are not applicable in certain circumstances when the update frequencies of moving objects become highly variable and when the system needs to balance the performance of updates and queries. In this paper, we introduce two kinds of novel indexes, named B^y-tree and αB^y-tree. By associating a prediction life period with every moving object, the proposed indexes are applicable in the environments with highly variable update frequencies. In addition, the αB^y-tree can balance the performance of updates and queries depending on a balance parameter. Experimental results show that the B^y-tree and αB^y-tree outperform the B^x-tree in various conditions.     

PCA-based web page watermarking

The tamper-proof of web pages is of great importance. Some watermarking schemes have been reported to solve this problem. However, both these watermarking schemes and the traditional hash methods have a problem of increasing file size. In this paper, we propose a novel watermarking scheme for the tamper-proof of web pages, which is free of this embarrassment. For a web page, the proposed scheme generates watermarks based on the principal component analysis (PCA) technique. The watermarks are then embedded into the web page through the upper and lower cases of letters in HTML tags. When a watermarked web page is tampered, the extracted watermarks can detect the modifications to the web page, thus we can keep the tampered one from being published. Extensive experiments are performed on the proposed scheme and the results show that the proposed scheme can be a feasible and efficient tool for the tamper-proof of web pages.     

Robust Image Mosaicing of Soccer Videos using Self-Calibration and Line Tracking

In this paper we propose an accurate and robust image mosaicing method of soccer video taken from a rotating and zooming camera using line tracking and self-calibration. The mosaicing of soccer videos is not easy, because their playing fields are low textured and moving players are included in the fields. Our approach is to track line features on the playing fields. The line features are detected and tracked using a self-calibration technique for a rotating and zooming camera. To track line features efficiently, we propose a new line tracking algorithm, called camera parameter guided line tracking, which works even when the camera motion undergoes sudden changes. Since we do not need to know any model for scenes beforehand, the proposed algorithm can be easily extended to other video sources, as well as other sports videos. Experimental results show the accuracy and robustness of the algorithm. An application of mosaicing is also presented.