传感器自适应跟踪算法研究及仿真系统实现

雷达和红外作为目标跟踪常用的两种探测手段,各有其优缺点,利用雷达高精度的距离测量和红外高精度的角度测量,通过信息融合技术充分实现二者的优势互补,并结合交互式多模型(IMM)跟踪思想,给出对目标位置的精确估计;设计基于雷达/红外多传感器跟踪平台的自适应融合跟踪算法,实现根据目标不同运动特性进行跟踪模型灵活、合理切换的自适应目标跟踪,改善对目标的综合识别,达到更好的跟踪效果;选取当前工程实践中广泛应用的目标运动模型,设计基于VC++环境的目标跟踪仿真系统软件,并利用MFC界面制作技术创建可视化目标跟踪仿真软件平台,对跟踪算法性能进行验证。     

Context-based multi-target tracking with occlusion handling

Occlusion has long been a core challenge for multi-target tracking tasks. In this paper we present context-based tracking strategies and demonstrate those for two very different types of targets, namely vehicles and fruit flies, representing examples of different target categories (e.g. individually identifiable with relatively consistent trajectories versus nearly identical targets with highly irregular trajectories). Those two classes of targets are also recorded with either mobile or static camera systems, and they represent either long-term or high-frequency occlusion scenarios, respectively. Occlusions among rigid vehicles have various occlusion patterns because of the mobile recording platform and the dynamic traffic environment. In contrast, a high-density scene of fruit flies contains hundreds of targets where occlusion is relatively short, but the frequency of occlusions is very high. In this paper we propose tracking systems based on context information, and show that those are able to address both application scenarios of target tracking. The proposed strategy outperforms state-of-the-art methods in both cases. Experimental results also demonstrate the efficiency of the proposed systems for occlusion handling.     

Development of a vision-based ground target detection and tracking system for a small unmanned helicopter

It is undoubted that the latest trend in the unmanned aerial vehicles (UAVs) community is towards visionbased unmanned small-scale helicopter, utilizing the maneuvering capabilities of the helicopter and the rich information of visual sensors, in order to arrive at a versatile platform for a variety of applications such as navigation, surveillance, tracking, etc. In this paper, we present the development of a visionbased ground target detection and tracking system for a small UAV helicopter. More specifically, we propose a real-time vision algorithm, based on moment invariants and two-stage pattern recognition, to achieve automatic ground target detection. In the proposed algorithm, the key geometry features of the target are extracted to detect and identify the target. Simultaneously, a Kalman filter is used to estimate and predict the position of the target, referred to as dynamic features, based on its motion model. These dynamic features are then combined with geometry features to identify the target in the second-stage of pattern recognition, when geometry features of the target change significantly due to noise and disturbance in the environment. Once the target is identified, an automatic control scheme is utilized to control the pan/tilt visual mechanism mounted on the helicopter such that the identified target is to be tracked at the center of the captured images. Experimental results based on images captured by the small-scale unmanned helicopter, SheLion, in actual flight tests demonstrate the effectiveness and robustness of the overall system.     

On exploiting ‘negative’ sensor evidence for target tracking and sensor data fusion

In various applications of target tracking and sensor data fusion all available information related to the sensor systems used and the underlying scenario should be exploited for improving the tracking/fusion results. Besides the individual sensor measurements themselves, this in particular includes the use of more refined models for describing the sensor performance. By incorporating this type of background information into the processing chain, it is possible to exploit ‘negative’ sensor evidence. The notion of ‘negative’ sensor evidence covers the conclusions to be drawn from expected but actually missing sensor measurements for improving the position or velocity estimates of targets under track. Even a failed attempt to detect a target is a useful sensor output, which can be exploited by appropriate sensor models providing background information. The basic idea is illustrated by selected examples taken from more advanced tracking and sensor data fusion applications such as group target tracking, tracking with agile beam radar, ground moving target tracking, or tracking under jamming conditions.     

An on-board vision sensor system for small unmanned vehicle applications

This paper describes an on-board vision sensor system that is developed specifically for small unmanned vehicle applications. For small vehicles, vision sensors have many advantages, including size, weight, and power consumption, over other sensors such as radar, sonar, and laser range finder, etc. A vision sensor is also uniquely suited for tasks such as target tracking and recognition that require visual information processing. However, it is difficult to meet the computing needs of real-time vision processing on a small robot. In this paper, we present the development of a field programmable gate array-based vision sensor and use a small ground vehicle to demonstrate that this vision sensor is able to detect and track features on a user-selected target from frame to frame and steer the small autonomous vehicle towards it. The sensor system utilizes hardware implementations of the rank transform for filtering, a Harris corner detector for feature detection, and a correlation algorithm for feature matching and tracking. With additional capabilities supported in software, the operational system communicates wirelessly with a base station, receiving commands, providing visual feedback to the user and allowing user input such as specifying targets to track. Since this vision sensor system uses reconfigurable hardware, other vision algorithms such as stereo vision and motion analysis can be implemented to reconfigure the system for other real-time vision applications.     

Improved assignment with ant colony optimization for multi-target tracking

Detecting and tracking ground targets is crucial in military intelligence in battlefield surveillance. Once targets have been detected, the system used can proceed to track them where tracking can be done using Ground Moving Target Indicator (GMTI) type indicators that can observe objects moving in the area of interest. However, when targets move close to each other in formation as a convoy, then the problem of assigning measurements to targets has to be addressed first, as it is an important step in target tracking. With the increasing computational power, it became possible to use more complex association logic in tracking algorithms. Although its optimal solution can be proved to be an NP hard problem, the multidimensional assignment enjoyed a renewed interest mostly due to Lagrangian relaxation approaches to its solution. Recently, it has been reported that randomized heuristic approaches surpassed the performance of Lagrangian relaxation algorithm especially in dense problems. In this paper, impelled from the success of randomized heuristic methods, we investigate a different stochastic approach, namely, the biologically inspired ant colony optimization to solve the NP hard multidimensional assignment problem for tracking multiple ground targets.     

Copernicus,a hybrid dataflow and peer-to-peer scientific computing platform for efficient large-scale ensemble sampling

Compute-intensive applications have gradually changed focus from massively parallel supercomputers to capacity as a resource obtained on-demand. This is particularly true for the large-scale adoption of cloud computing and MapReduce in industry, while it has been difficult for traditional high-performance computing (HPC) usage in scientific and engineering computing to exploit this type of resources. However, with the strong trend of increasing parallelism rather than faster processors, a growing number of applications target parallelism already on the algorithm level with loosely coupled approaches based on sampling and ensembles. While these cannot trivially be formulated as MapReduce, they are highly amenable to throughput computing. There are many general and powerful frameworks, but in particular for sampling-based algorithms in scientific computing there are some clear advantages from having a platform and scheduler that are highly aware of the underlying physical problem. Here, we present how these challenges are addressed with combinations of dataflow programming, peer-to-peer techniques and peer-to-peer networks in the Copernicus platform. This allows automation of sampling-focused workflows, task generation, dependency tracking, and not least distributing these to a diverse set of compute resources ranging from supercomputers to clouds and distributed computing (across firewalls and fragile networks). Workflows are defined from modules using existing programs, which makes them reusable without programming requirements. The system achieves resiliency by handling node failures transparently with minimal loss of computing time due to checkpointing, and a single server can manage hundreds of thousands of cores e.g. for computational chemistry applications.     

结合颜色属性的分层结构直方图

目的 为克服单一颜色特征易受光照变化影响,以及图像的空间结构特征对目标形变较为敏感等问题,提出一种结合颜色属性的分层结构直方图。方法 首先,鉴于使用像素灰度值对图像进行分层易受光照变化影响,本文基于颜色属性对图像进行分层,即将输入的彩色图像从RGB空间映射到颜色属性空间,得到11种概率分层图;之后,将图像中的每一个像素仅投影到其概率值最大的分层中,使得各分层之间像素的交集为空,并集为整幅图像;对处理后的每一个分层,通过定义的结构图元来统计像素分布情况,得到每一分层的空间分布信息;最后,将每一分层的像素空间分布信息串联作为输入图像的分层结构直方图,以此来表征图像。结果 为证明本文特征的有效性,将该特征用于图像匹配和视觉跟踪,与参考特征相比,利用本文特征进行图像匹配时,峰值旁瓣比均值提升1.347 9;将本文特征用于视觉跟踪时,采用粒子滤波作为跟踪框架,成功率相对上升4%,精度相对上升4.6%。结论 该特征将图像的颜色特征与空间结构信息相结合,有效解决了单一特征分辨性较差的问题,与参考特征相比,该特征具有更强的分辨性和鲁棒性,因此本文特征可以更好地应用于图像处理应用中。     

Deep Learning and Preference Learning for Object Tracking: A Combined Approach

Object tracking is one of the most important processes for object recognition in the field of computer vision. The aim is to find accurately a target object in every frame of a video sequence. In this paper we propose a combination technique of two algorithms well-known among machine learning practitioners. Firstly, we propose a deep learning approach to automatically extract the features that will be used to represent the original images. Deep learning has been successfully applied in different computer vision applications. Secondly, object tracking can be seen as a ranking problem, since the regions of an image can be ranked according to their level of overlapping with the target object (ground truth in each video frame). During object tracking, the target position and size can change, so the algorithms have to propose several candidate regions in which the target can be found. We propose to use a preference learning approach to build a ranking function which will be used to select the bounding box that ranks higher, i.e., that will likely enclose the target object. The experimental results obtained by our method, called \( DPL ^{2}\) (Deep and Preference Learning), are competitive with respect to other algorithms.     

利用Jetson TK1平台的行人运动目标跟踪系统

针对图像检测识别和目标跟踪技术中存在的抗遮挡性弱、无法应对目标丢失、对目标多尺度变化适应不了等问题,设计开发了基于Jetson TK1平台及计算机视觉OpenCV(Open Source Computer Vision Library)的行人运动目标跟踪系统,利用GPU高效图像处理能力,结合改进的KCF(Kerneli...     

Visual tracking based on online sparse feature learning

Various visual tracking approaches have been proposed for robust target tracking, among which using sparse representation of the tracking target yields promising performance. Some earlier works in this line used a fixed subset of features to compress the target's appearance, which has limited modeling capacity between the target and the background, and could not accommodate their appearance change over long period of time. In this paper, we propose a visual tracking method by modeling targets with online-learned sparse features. We first extract high dimensional Haar-like features as an over-completed basis set, and then solve the feature selection problem in an efficient L₁-regularized sparse-coding process. The selected low-dimensional representation best discriminates the target from its neighboring background. Next we use a naive Bayesian classifier to select the most-likely target candidate by a binary classification process. The online feature selection process happens when there are significant appearance changes identified by a thresholding strategy. In this way, our proposed method could work for long tracking tasks. At the same time, our comprehensive experimental evaluation has shown that the proposed methods achieve excellent running speed and higher accuracy over many state-of-the-art approaches.     

Particle filter-based aerial tracking for moving targets

This paper considers the problem of tracking a moving target with a radio transmitter using an aerial robot in an online manner. The aerial robot is equipped with a low-cost directional antenna and Software Defined Radio receiver to obtain the signal emitted by the target. The aerial robot rotates around itself and collects a predefined number of signal recordings from each direction to determine the bearing angle to the target in which the received signal strength is maximized. The measurement uncertainty is assumed to be bounded and represented by two triangular areas divided by a bisector. To localize and track the target, a particle filter-based approach is proposed. In this approach, we integrate the discrete and bounded measurement model with the particle filter in such a way that the particles' weights are updated based on a novel method which considers the measurement wedge and the particle locations with respect to this wedge along with a logistic function. We also incorporate the doubling strategy into the particle filter to determine the next measurement locations and avoid arbitrarily large number of measurements. We choose wildlife monitoring as a use case scenario in which a radio transmitter is put on the animal under consideration to allow wildlife researchers to track it. Since each animal has its own motion behavior, we consider different motion models for the target, which are used in modeling animal movements in wildlife studies. Therefore, the proposed approach is validated using a target moving with varying velocity and acceleration. We verified the tracking performance of the approach through a series of extensive simulations. We compared the proposed approach with the optimal offline strategy in terms of the empirical competitive ratio of the total distance traveled and the tracking distance. We also developed a low-cost hardware platform and software infrastructure for the proposed tracking system. Using this platform, we conducted field experiments for the stationary and moving targets.     

天波超视距雷达的坐标变换

传统超视距跟踪算法多在雷达坐标系下实现。为了避免加入独立的坐标配准算法,严格推导了天波超视距雷达坐标系与地理坐标系之间复杂的非线性坐标变换关系,得出了相应的变换公式,以直接得到目标在地理坐标系下的状态估计。比较发现,目前公开的雅可比矩阵存在两处错误,最后给出了计算机仿真证明,仿真结果表明我们推导的公式是正确的。对于发现的错误给出更正说明。给出的坐标变换法可与相应的跟踪算法结合,得到独立的地理坐标系下的天波超视距雷达跟踪算法。     

无人机多机动目标自主探测与跟踪

无人机机载相机图像中机动目标尺寸较小而且会发生显著变化,加上大量的背景噪声干扰,给目标探测和跟踪带来很大困难.针对这些问题,本文提出了一种在无人机机载相机图像序列中自主探测与跟踪多个机动目标的方法.首先,提取目标的图像数字特征并采用级联分类算法进行特征分类,得到目标的强分类器,对目标进行自主探测搜索.然后,基于全局最优关联算法对探测回波进行关联滤波,实现对多个机动目标的跟踪与识别,其中最优关联代价矩阵融合了距离和方向信息,提高了关联和跟踪的鲁棒性.将无人机航拍图像序列中的地面坦克作为目标进行实验,结果表明本文算法可以实现对多个机动目标的自主探测和跟踪,并具有较好的跟踪鲁棒性.     

Adaptive compressive sensing for target tracking within wireless visual sensor networks-based surveillance applications

Wireless Visual Sensor Networks (WVSNs) have gained significant importance in the last few years and have emerged in several distinctive applications. The main aim is to design low power WVSN surveillance application using adaptive Compressive Sensing (CS) which is expected to overcome the WVSN resource constraints such as memory limitation, communication bandwidth and battery constraints. In this paper, an adaptive block CS technique is proposed and implemented to represent the high volume of captured images in a way for energy efficient wireless transmission and minimum storage. Furthermore, to achieve energy-efficient target detection and tracking with high detection reliability and robust tracking, to maximize the lifetime of sensor nodes as they can be left for months without any human interactions. Adaptive CS is expected to dynamically achieve higher compression rates depending on the sparsity nature of different datasets, while only compressing relative blocks in the image that contain the target to be tracked instead of compressing the whole image. Hence, saving power and increasing compression rates. Least mean square adaptive filter is used to predicts target’s next location to investigate the effect of CS on the tracking performance. The tracking is achieved in both indoor and outdoor environments for single/multi targets. Results have shown that with adaptive block CS up to 20 % measurements of data are required to be transmitted while preserving the required performance for target detection and tracking.     

REACTIVE TUNING OF TARGET ESTIMATE ACCURACY IN MULTISENSOR DATA FUSION

Dealing with conflicting and target-specific requirements is an important issue in multisensor and multitarget tracking. This paper aims to allocate sensing resources among various targets in reaction to individual information requests. The proposed approach is to introduce agents for every relevant target responsible for its tracking. Such agents are expected to bargain with each other for a division of resources. A bilateral negotiation model is established for resource allocation in two-target tracking. The applications of agent negotiation to target covariance tuning are illustrated together with simulation results presented. Moreover, we suggest a way of organizing simultaneous one-to-one negotiations, making our negotiation model still applicable in scenarios of tracking more than two targets.     

机器人卫星地面实验平台全局视觉系统

机器人卫星地面实验平台是研制机器人卫星的重要手段。本文针对所开发的机器人卫星地面实验平台，设计了全局视觉，完成机器人卫星姿态分析、目标和障碍物的识别与定位。     

一种飞机目标及典型地物红外辐射仿真方法

机场场景内的飞机目标及其所处的地物背景具有重要军事应用价值,为了实现对这类目标的检测、识别以及动态监测,需要一套能够在不同季节、不同气象条件、不同时段、不同探测波段等条件下机场场景内飞机/地物红外辐射仿真的软件来提供训练样本。在Visual Studio 2010环境下,利用OpenGL构建了典型机场场景下飞机及地物背景模型,结合传热学和红外辐射理论的分析,将一款用于热红外分析的RadThermIR软件内核嵌入算法中,提出一种计算飞机及其地物背景的红外辐射场模型和构建其红外图像仿真方法。以图像灰度相似度作为评价指标,该方法和真实红外图像相比,仿真精度高于80%,实验结果表明,该方法可为实现全天候机场场景下飞机目标自动检测识别提供丰富的红外特性分析数据和特性知识训练样本。     

An Optimal Approach to Collaborative Target Tracking with Performance Guarantees

In this paper, we present a discrete-time optimization framework for target tracking with multi-agent systems. The “target tracking” problem is formulated as a generic semidefinite program (SDP) that when paired with an appropriate objective yields an optimal robot configuration over a given time step. The framework affords impressive performance guarantees to include full target coverage (i.e. each target is tracked by at least a single team member) as well as maintenance of network connectivity across the formation. Key to this work is the result from spectral graph theory that states the second-smallest eigenvalue—λ ₂—of a weighted graph’s Laplacian (i.e. its inter-connectivity matrix) is a measure of connectivity for the associated graph. Our approach allows us to articulate agent-target coverage and inter-agent communication constraints as linear-matrix inequalities (LMIs). Additionally, we present two key extensions to the framework by considering alternate tracking problem formulations. The first allows us to guarantee k-coverage of targets, where each target is tracked by k or more agents. In the second, we consider a relaxed formulation for the case when network connectivity constraints are superfluous. The problem is modeled as a second-order cone program (SOCP) that can be solved significantly more efficiently than its SDP counterpart—making it suitable for large-scale teams (e.g. 100’s of nodes in real-time). Methods for enforcing inter-agent proximity constraints for collision avoidance are also presented as well as simulation results for multi-agent systems tracking mobile targets in both ?² and ?³.     

低视点下遮挡自适应感知的多目标跟踪算法

目的 针对低视点多目标跟踪场景的遮挡问题,提出一种能够遮挡自适应感知的多目标跟踪算法。方法 首先根据每帧图像的全局遮挡状态,提出了“自适应抗遮挡特征”,增强目标特征对遮挡的感知和调整能力。同时,采用“级联筛查机制”,减少由遮挡带来的目标特征剧烈变化而认定为“虚新入目标”的错误跟踪现象。最后,考虑到历史模板库中存在遮挡的模板对跟踪性能的影响,根据每一帧中目标的局部遮挡状态,提出自适应干扰模板更新机制,进一步提高对遮挡的应变和适应能力。结果 实验结果表明,本文算法在MOTA(multiple object tracking accuracy)、M OTP (multiple object tracking precision)、FN(false negatives)、Rcll (recall)、ML (mostly lost tracklets)等指标上明显优于STAM(spatial-temporal attention mechanism)、ATAF(aggregate tracklet appearance features)、STRN (spatial-temporal relat...