Ball detection from broadcast soccer videos using static and dynamic features

In this paper, we propose an approach for detecting ball in broadcast soccer videos. We use hybrid techniques for identifying ball in medium and long shots. Candidate ball positions are first extracted using features based on shape and size. For medium shots, a ball is identified by filtering the candidates with the help of motion information. In long shots, after motion based filtering of the non-ball candidates, a directed weighted graph is constructed for the remaining ball candidates. Each node in the graph represents a candidate and each edge links candidates in a frame with the candidates in next two consecutive frames. Finally, dynamic programming is applied to find the longest path of the graph, which gives the actual ball trajectory. Experiments with several soccer sequences show that the proposed approach is very efficient.     

Robust human detection within a highly dynamic aquatic environment in real time.

This paper presents a real-time foreground detection method for monitoring swimming activities at an outdoor swimming pool. Robust performance and high accuracy of detecting objects-of-interest are two central issues of concern. Therefore, in this paper, a considerable amount of attention has been placed on the following aspects: 1) to establish a better method of modeling aquatic background, which exhibitis dynamic characteristics with random spatial movements, and 2) to establish a method of enhancing the visibility of the foreground by removing specular reflection at nighttime. First, the development of a new background modeling method is reported. In the proposed approach, the background is modeled as a composition of homogeneous blob movements. With an implementation of a spatial searching process, the proposed method shows capability in associating and distinguishing movements caused by the background. Hence, this contributes to better performance in foreground detection. On the issue of enhancing the visibility of the foreground, a decision-based filtering scheme is proposed as a preprocessing step. A defined concept term, fluctuation measure, is defined for classifying each pixel to be one of the predefined types. This has allowed suitable spatial or spatiotemporal filters to be applied accordingly for color the compensation step. All of these developments are evaluated by testing live on a busy Olympic-size outdoor public swimming pool. Both qualitative and quantitative evaluations are reported. This provides a comprehensive study of the system.     

Calibration of tracking systems in a surgical environment

The purpose of this paper was to assess to what extent an optical tracking system (OTS) used for position determination in computer-aided surgery (CAS) can be enhanced by combining it with a direct current (DC) driven electromagnetic tracking system (EMTS). The main advantage of the EMTS is the fact that it is not dependent on a free line-of-sight. Unfortunately, the accuracy of the EMTS is highly affected by nearby ferromagnetic materials. The authors have explored to what extent the influence of the metallic equipment in the operating room (OR) can be compensated by collecting precise information on the nonlinear local error in the EMTS by using the OTS for setting up a calibration look-up table. After calibration of the EMTS and registration of the sensor systems in the OR the authors have found the average euclidean deviation in position readings between the DC tracker and the OTS reduced from 2.9±1.0 mm to 2.1±0.8 mm within a half-sphere of 530-mm radius around the magnetic field emitter. Furthermore the authors have found the calibration to be stable after re-registration of the sensors under varying conditions such as different heights of the OR table and varying positions of the OR equipment over a longer time interval. These results encourage the further development of a hybrid magnetooptical tracker for computer-aided surgery where the electromagnetic tracker acts as an auxiliary source of position information for the optical system. Strategies for enhancing the reliability of the proposed hybrid magnetooptic tracker by detecting artifacts induced by mobile ferromagnetic objects such as surgical tools are discussed     

高动态微弱信标信号载波捕获跟踪的设计与实现

为了研究高动态低信噪比下信标信号的载波捕获跟踪问题,采用两级二阶锁频环(FLL)和一级三阶锁相环(PLL)技术方案。FLL采用基于周期图的鉴频方法,实现极低信噪比下信号载波的捕获。PLL中的三阶锁相环通过对环路压控振荡器(VCO)的输入控制信号进行监测,自适应地调整环路滤波器的带宽,以满足高动态下信号载波频率动态范围大的要求。在基于FPGA构建的信号处理板上验证了上述实现方案,并给出实验结果。     

Joint audio-video object localization and tracking

There has been a tremendous amount of research on object localization either involving microphone arrays or video cameras. Considerable less attention has been paid, however, to object localization and tracking based on joint audio-video processing thus far. This may be related to the lack of suitable algorithms for object localization simultaneously using multimicrophone outputs and color image sequences. In this article, we propose a solution to this problem. Before elaborating on joint audio-video processing, we review some previous work the areas of audio and video object localization. Then a recursive sensor fusion method based on decentralized Kalman filtering is introduced. Unfortunately, the decentralized Kalman filter cannot be directly used for joint audio-video object localization due to specific properties of the audio sensor. By properly adjusting the local audio position estimator, however, we manage to keep the overall architecture. We stress the general methodology     

Cooperative localization and tracking in wireless sensor networks

Cooperative localization has attracted great attention in recent years. However, in some scenarios, localization precision is challenging and does not meet the application requirements. In this paper, Kalman and Particle filters (KF and PF) are considered for cooperative localization scenarios purpose. We propose to apply these techniques to cooperative localization approaches that we investigated in previous papers: Evolved Variational Message Passing algorithm (E‐VMP) and Cooperative Robust Geometric Positioning Algorithm (C‐RGPA). The main added value of distributed tracking filters is to guarantee dynamic versions of these two algorithms. The proposed techniques are evaluated and compared by means of real heterogeneous measurements carried out using ZigBee and OFDM devices and where location‐dependent parameters such as RSSI and RTD are exploited. Experiments and realistic simulations reveal that the proposed techniques exhibit better localization accuracy for very low complexity and cost. Moreover, the comparative study shows that distributed particle filter (DPF) provides better performance than KF in terms of positioning accuracy and root‐mean square error.     

Robust player detection and tracking in broadcast soccer video based on enhanced particle filter

It is significant to detect and track soccer players in broadcast sports video, which is helpful to analysis player activity and team tactics. However, it is challenging to efficiently detect and track soccer players with shots switched and noise caused by auditorium and billboards. And for multi-player tracking how to treat the increase or decrease of player are also difficult. In this paper, a robust player detection algorithm based on salient region detection and tracking based on enhanced particle filtering are proposed. Salient region detection is used to segment sports fields, and then soccer players are detected by edge detection combined with Otsu algorithm. For soccer players tracking, we use an enhanced particle filter which we improve the algorithm in sample and the likelihood function combing the color feature and edge feature. Experimental results show the proposed algorithm can quickly and accurately detect and track soccer players in broadcast video.     

Source localization using vector sensor array in a multipath environment

Coherent signals from distinct directions is a natural characterization of the multipath propagation effect. This paper addresses the problem of coherent/fully correlated source localization using vector sensor arrays. The maximum likelihood (ML) and minimum-variance distortionless response (MVDR) estimators for source direction-of-arrival (DOA) and signal polarization parameters are derived. These estimators require no search over the polarization parameters. In addition, a novel method for "decorrelating" the incident signals is presented. This method is based on the polarization smoothing algorithm (PSA) and enables the use of eigenstructure-based techniques, which assume uncorrelated or partially correlated signals. The method is implemented as a preprocessing stage before applying eigenstructure-based techniques, such as MUSIC. Unlike other existing preprocessing techniques, such as spatial smoothing and forward-backward (FB) averaging, this method is not limited to any specific array geometry. The performance of the proposed PSA preprocessing combined with MUSIC is evaluated and compared to the Crame/spl acute/r-Rao Bound (CRB) and the ML and MVDR estimators. Simulation results show that the MVDR and PSA-MUSIC asymptotically achieve the CRB for a scenario with two coherent sources with and without an uncorrelated interference source. A sensitivity study of PSA-MUSIC to source polarization was also conducted via simulations.     

Text detection,localization, and tracking in compressed video

Video text information plays an important role in semantic-based video analysis, indexing and retrieval. Video texts are closely related to the content of a video. Usually, the fundamental steps of text-based video analysis, browsing and retrieval consist of video text detection, localization, tracking, segmentation and recognition. Video sequences are commonly stored in compressed formats where MPEG coding techniques are often adopted. In this paper, a unified framework for text detection, localization, and tracking in compressed videos using the discrete cosines transform (DCT) coefficients is proposed. A coarse to fine text detection method is used to find text blocks in terms of the block DCT texture intensity information. The DCT texture intensity of an 8×8 block of an intra-frame is approximately represented by seven AC coefficients. The candidate text block regions are further verified and refined. The text block region localization and tracking are carried out by virtue of the horizontal and vertical block texture intensity projection profiles. The appearing and disappearing frames of each text line are determined by the text tracking. The final experimental results show the effectiveness of the proposed methods.     

Improving the security of a dynamic look-up table based chaotic cryptosystem

In this brief, we analyze the cause of vulnerability of the original dynamic look-up table based chaotic encryption scheme in detail, and then propose the corresponding enhancement measures. Theoretical analysis and computer simulation indicate that the modified scheme is more secure than the original one.     

Bearings-only maneuvering target tracking based on fuzzy clustering in a cluttered environment

This paper proposes a novel bearings-only maneuvering target tracking algorithm based on maximum entropy fuzzy clustering in a cluttered environment. In the proposed algorithm, the interacting multiple model (IMM) approach is used to solve the maneuvering problem of target, and the false alarms generated by clutter are accommodated through a probabilistic data association filter (PDAF). To reduce the computational load, the association probability is substituted by fuzzy membership degree provided by a modified version of fuzzy clustering algorithm based on maximum entropy principle, and the “maximum validation distance” is also defined based on the discrimination factor, which enables the algorithm eliminate invalid measurements. Moreover, to avoid the unobservability problem of passive target tracking, a nonlinear measurement model of multiple passive sensors is formulated. Finally, simulation results show that the proposed algorithm has advantages over the conventional IMM-PDAF algorithm in terms of simplicity and efficiency.     

A PREPROCESSING LS-CMA IN HIGHLY CORRUPTIVE ENVIRONMENT

A fast preprocessing Least Square-Constant Modulus Algorithm (LS-CMA) is proposed for blind adaptive beamforming. This new preprocessing method precludes noise capture caused by the original LS-CMA with the preprocessing procedure controlled by the static Constant Modulus Algorithm (CMA). The simulation results have shown that the proposed fast preprocessing LS-CMA can effectively reject the co-channel interference, and quickly lock onto the constant modulus desired signal with only one snapshot in a highly corruptive environment.     

Blind high-resolution localization and tracking of multiplefrequency hopped signals

This paper considers the problem of blind localization and tracking of multiple frequency-hopped spread-spectrum signals using a uniform linear antenna array without knowledge of hopping patterns or directions of arrival. As a preprocessing step, we propose to identify a hop-free subset of data by discarding high-entropy spectral slices from the spectrogram. High-resolution localization is then achieved via either quadrilinear regression of four-way data generated by capitalizing on both spatial and temporal shift invariance or a new maximum likelihood (ML)-based two-dimensional (2-D) harmonic retrieval algorithm. The latter option achieves the best-known model identifiability bound while remaining close to the Cramer-Rao bound even at low signal-to-noise ratios (SNRs). Following beamforming using the recovered directions, a dynamic programming approach is developed for joint ML estimation of signal frequencies and hop instants in single-user tracking. The efficacy of the proposed algorithms is illustrated in pertinent simulations     

非视距环境下基于RSS-TOA的定位算法

在无线传感器网络定位系统中,尤其是在室内定位中,非视距（NLOS）误差的存在使定位性能急剧下降。为克服非视距传播带来的定位误差,提出了一种针对非视距环境下联合接收信号强度（RSS）和到达时间（TOA）的定位算法。该方法首先通过 RSS和 TOA的测量结果建立关于目标位置的非凸优化问题,然后通过二阶锥松弛理论,将原始的非凸优化问题转换为一种凸优化问题,由此能够快速得到原问题的一个次优解。通过计算机模拟仿真验证,新方法的估计精度更高,性能更好。     

A novel all-neighbor fuzzy association approach for multitarget tracking in a cluttered environment

This paper proposes a novel all-neighbor fuzzy association approach for multitarget tracking in a cluttered environment. It performs data association with a little prior knowledge and updates the predicted target state estimate using a fuzzy weighted sum of innovations. Unlike the joint probabilistic data association filter, in which the similarity measures are determined in terms of the conditional probability for all feasible data association hypothesis, the proposed fuzzy association approach determines the similarity measures between measurements and tracks in terms of possibility weights based on a partition matrix. The possibility weights are determined according to the fuzzy clustering algorithm. The proposed approach is able to perform all-neighbor association with a lower computational complexity in the expense of a little lower performance compared to the standard joint probabilistic data association filter. Computer simulation shows the feasibility and the efficiency of the proposed all-neighbor fuzzy association approach.     

Objects tracking in a dense reader environment utilising grids of RFID antenna positioning

One of the fundamental constraints in radio frequency identification (RFID) large scale deployment, such as in warehouse RFID deployment, is the positioning of RFID reader antennas to efficiently locate all the tagged objects distributed in a dense RFID reader environment. For tracking the tagged objects in a dense RFID deployment, the required number of reader antennas must be optimised in order to reduce the overall cost. This study proposes highly accurate square and hexagonal grid-based positioning and tracking techniques mainly for use indoors and includes performance comparison of both of these grids. The study involves the design of the square and hexagonal grid reader antenna networks and position calculation using a diffusion algorithm. Both of these grids of RFID antenna positioning present a solution for the problem of the placement pattern of RFID reader antennas in a dense reader environment, hence an optimal number of required reader antennas and guaranteed coverage can be achieved. This study also presents a path loss model that can be applied to predict the radio signal strength information at a certain distance. The proposed diffusion algorithm estimates RFID tag position by using distance information between the reader and the tag. The obtained results show that a square grid can yield higher positioning accuracy compared to the hexagonal grid. The obtained results further show that the proposed tracking techniques can achieve an average positioning error below 1 m, which is 85% better in some cases than the results obtained by other known methods.     

An adaptive tracking algorithm for direction finding and array shape estimation in a nonstationary environment

This paper presents an adaptive tracking algorithm for the subspace-based direction of arrival estimation of multiple sources in a nonstationary, environment. The nonstationarities are due to moving sources or to timevarying distortions of the sensor array shape. The proposed algorithm relies on the properties of a linear operator, referred to as the Propagator, which only exploits the linear independency of the source steering vectors. The Propagator allows not only the calibration of the array shape, but also the determination of the source and the noise subspaces without any eigendecomposition of the cross-spectral matrix of the received signals. A gradientbased adaptive algorithm is here proposed for the on-line estimation of the Propagator. A theoretical analysis of the behaviour of this algorithm in a nonstationary environment is given. Simulations are carried out in the case of moving sources and in the case of a time-varying array shape. They exhibit the good performances of the proposed algorithm.     

脉冲噪声环境中自适应阵列对信号的跟踪

以alpha稳定分布作为无线信道的噪声模型,基于分数低阶统计量理论采用子空间和近似最大似然的方法,利用整个时隙内的接收信号恢复出期望用户的发射字符。相对于二阶统计量的方法,该方法有更好的韧性和经济的计算量。     

嘈杂环境中利用CSI信息的室内轨迹跟踪技术

基于信道状态信息的室内轨迹跟踪技术近几年来备受关注。为了利用现有的商用WiFi设备实现实时的轨迹跟踪，本文采用了一发一收的室内轨迹跟踪系统，主要利用通过信道状态信息计算得到的多维参数包括飞行时间、到达角度、多普勒频移和信道衰减来计算得到相应的位置信息，并且提出了利用环境动态参数来修正定位参数的方法，以达到更为精准的轨迹跟踪效果。实验表明，采用这种方法，定位精度可以达到0.65m，证明了该方法能精确有效地实现室内轨迹的跟踪定位。