孪生网络跟踪算法并行计算结构研究

基于嵌入式平台的复杂背景目标跟踪技术在智能视频监控设备、无人机跟踪等领域有重要作用.卷积神经网络在跟踪问题上有准确率高、鲁棒性强的优点,但基于卷积特征的算法计算复杂度高,受嵌入式平台面积和功耗的限制,实时性难以满足嵌入式平台应用场景的需求.针对基于卷积特征的跟踪算法计算复杂度高、存储参数量大的难题,率先提出一种利用FPGA实现基于卷积神经网络的复杂背景目标跟踪硬件加速架构.该方法通过利用KL相对熵对目标跟踪算法Siamese-FC进行定点量化,设计了基于通道并行的卷积层加速架构.实验结果表明,定点量化后跟踪算法相比于原算法的平均精度损失不超过4.57％,FPGA部署后前向推理耗时仅为CPU的16.15％,功耗仅为CPU的13.7％.     

基于改进PP-YOLO和Deep-SORT的多无人机实时跟踪算法

无人机（UAV）目标尺寸较小,多架无人机之间特征也不明显,且鸟类和飞虫的干扰给无人机目标的准确检测和稳定跟踪带来了巨大挑战。针对传统目标检测算法对小目标无人机检测性能差、跟踪不稳定的问题,提出一种基于改进PP-YOLO和Deep-SORT的多无人机实时跟踪算法。首先,将压缩-激励模块融入PP-YOLO检测算法中,以实现对无人机目标的特征提取和检测;其次,在ResNet50-vd结构中引入Mish激活函数,以解决反向传播过程中的梯度消失问题,并进一步提升检测精度;然后,采用Deep-SORT算法来实时跟踪无人机目标,并将提取外观特征的主干网络更换为ResNet50,从而改善原有网络对微小外观感知能力弱的状况;最后,引入损失函数Margin Loss,既提高了类别可分性,又加强了类内紧度和类间差异。实验结果表明,所提算法的检测平均精度均值（mAP）相比原始PP-YOLO算法提升了2.27个百分点,跟踪准确性相对于原始Deep-SORT算法提升了4.5个百分点。所提算法的跟踪准确性可达91.6%,能够实时跟踪600 m以内多架无人机目标,有效解决了跟踪过程中的“丢帧”问题。     

Algorithms and experiments on routing of unmanned aerial vehicles with mobile recharging stations

We study the problem of planning a tour for an energy‐limited Unmanned Aerial Vehicle (UAV) to visit a set of sites in the least amount of time. We envision scenarios where the UAV can be recharged at a site or along an edge either by landing on stationary recharging stations or on Unmanned Ground Vehicles (UGVs) acting as mobile recharging stations. This leads to a new variant of the Traveling Salesperson Problem (TSP) with mobile recharging stations. We present an algorithm that finds not only the order in which to visit the sites but also when and where to land on the charging stations to recharge. Our algorithm plans tours for the UGVs as well as determines the best locations to place stationary charging stations. We study three variants for charging: Multiple stationary charging stations, single mobile charging station, and multiple mobile charging stations. As the problems we study are nondeterministic polynomial time (NP)‐Hard, we present a practical solution using Generalized TSP that finds the optimal solution that minimizes the total time, subject to the discretization of battery levels. If the UGVs are slower than the UAVs, then the algorithm also finds the minimum number of UGVs required to support the UAV mission such that the UAV is not required to wait for the UGV. Our simulation results show that the running time is acceptable for reasonably sized instances in practice. We evaluate the performance of our algorithm through simulations and proof‐of‐concept field experiments with a fully autonomous system of one UAV and UGV.     

Road Detection and Tracking from Aerial Desert Imagery

We present a fast, robust road detection and tracking algorithm for aerial images taken from an Unmanned Aerial Vehicle. A histogram-based adaptive threshold algorithm is used to detect possible road regions in an image. A probabilistic hough transform based line segment detection combined with a clustering method is implemented to further extract the road. The proposed algorithm has been extensively tested on desert images obtained using an Unmanned Aerial Vehicle. Our results indicate that we are able to successfully and accurately detect roads in 96% of the images. We experimentally validated our algorithm on over a thousand aerial images obtained using our UAV. These images consist of straight and curved roads in various conditions with significant changes in lighting and intensity. We have also developed a road-tracking algorithm that searches a local rectangular area in successive images. Initial results are presented that shows the efficacy and the robustness of this algorithm. Using this road tracking algorithm we are able to further improve the road detection and achieve a 98% accuracy.     

GPU加速的差分进化粒子滤波算法

为了解决实时系统中粒子滤波的计算复杂性问题,本文提出了一种零bank冲突并行规约的差分进化粒子滤波方法。该方法首先分析了并行差分进化粒子滤波算法在GPU中的内存访问模式,根据粒子滤波器的均方根误差与内存访问bank(存储体)冲突度成正比的关系,提出了一种去除bank冲突的有填充寻址的差分进化粒子滤波算法,降低了计算复杂度。将该算法在NVIDIA GTX960 GPU中实现,与串行差分进化粒子滤波算法进行比较。实验表明,随着粒子数增加,计算量以指数增加,采用GPU加速的跟踪算法的执行时间明显减少,有效提高了跟踪精度、降低了计算时间。     

基于CUDA的塔台模拟机冲突检测算法

塔台模拟机冲突检测算法是一种耗时大的并行算法。针对其导致塔台模拟系统核心服务器CPU负担过重的缺点,在常用冲突检测算法的基础上,提出一种基于统一设备构架（CUDA）的塔台模拟机冲突检测实现方案。首先介绍GPU并行运算的体系结构基础,并将基于卡尔曼滤波的目标物体跟踪技术的分层冲突检测算法移植到GPU。然后利用相同价格的CPU和GPU对比运算效果。实验结果表明：与相同算法的CPU实现方案相比,GPU实现方案将计算效率提高10～50倍。使用此方案,极大地减轻了核心服务器的负担,使塔台模拟机的性能得到质的提高。     

High performance memetic algorithm particle filter for multiple object tracking on modern GPUs

This work presents an effective approach to visual tracking using a graphics processing unit (GPU) for computation purposes. In order to get a performance improvement against other platforms it is convenient to select proper algorithms such as population-based ones. They expose a parallel-friendly nature needing from many independent evaluations that map well to the parallel architecture of the GPU. To this end we propose a particle filter (PF) hybridized with a memetic algorithm (MA) to produce a MAPF tracking algorithm for single and multiple object tracking problems. Previous experimental results demonstrated that the MAPF algorithm showed more accurate tracking results than the standard PF, and now we extend those results with the first complete adaptation of the PF and the MAPF for visual tracking to the NVIDIA CUDA architecture. Results show a GPU speedup between 5×–16× for different configurations.     

基于改进TLD算法的无人机自主精准降落

四旋翼无人机（Unmanned Aerial Vehicle,UAV）在航拍、测绘、环境监测、快递等航空领域的广泛应用,对四旋翼无人机的可用性和可靠性提出了更高的要求,而其实现自主精准降落的功能是必不可少的。对目标进行快速鲁棒性跟踪是实现降落的重要基础,TLD（Tracking Learning Detector）算法为这一问题提供了一种有效的解决办法,虽然许多学者对其进行了研究并对传统的TLD算法进行了改进,但算法的跟踪精度及速度仍然难以满足无人机的降落要求。提出了一种基于TLD框架的目标跟踪算法来实现无人机与特定降落目标之间的相对定位。该算法在TLD框架下,提出一种基于目标形状特征自主确定降落目标的算法,提高了降落流程的自主性;用核相关滤波器（Kernelized Correlation Filter,KCF） 实现了TLD框架中的跟踪器,提高了算法的实时性、精准度及鲁棒性;同时在降落过程中采用一种基于方向梯度直方图特征（Histogram of Gradient,HOG）和支持向量机（Support Vector Machine,SVM） 的目标识别方法,以实现目标检测自矫正,保证长时间准确跟踪目标。在七类模拟无人机进行降落的视频集下验证了该算法,与其他三种跟踪算法进行对比,并进行实际降落测试。测试结果表明,该算法的鲁棒性和精准度均优于其他算法,处理速度可达到31.47?f/s,故而在TLD框架下采用核相关滤波器作为跟踪器,对跟踪及检测结果进行有效融合并提高算法实时性的同时,增加的检测自矫正环节保证了长时间跟踪的准确度,从而有效地实现了无人机全自主精准降落。     

无人机目标实时自适应跟踪系统

随着无人机(unmanned aerial vehicle,UAV)在航拍、空中侦察等相关领域被广泛应用,对于无人机的智能化需求逐渐提高.目标跟踪具有信息量大、实时性高等优点,能够为无人机的智能飞行提供大量且实时的外部信息.进行低开销、低功耗的无人机目标跟踪系统的研究,对无人机智能化进程的加速具有深远意义.为更好解决跟...     

基于改进Kalman滤波的可见光极小目标TBD跟踪方法

针对无人机可见光图像极小目标跟踪问题,本文提出一种基于改进卡尔曼滤波的 (Tracking before detection,TBD)跟踪方法。首先利用检测算法定位目标位置作为卡尔曼滤波的测量值,检测过程中的匹配相似度参数作为卡尔曼滤波测量噪声协方差矩阵的参照依据,其次利用卡尔曼滤波建立跟踪框架预测下一帧的目标位置,最后检测模块以预测位置为 参考位置进行局部搜索,完成整个检测跟踪过程。为了提高跟踪效率,本文根据检测和预测位置积累误差判决检测模式,误差超过门限值则采取全局检测模式消除积累误差,否 则使用局部检测模式,降低TBD跟踪算法的运算复杂度。仿真实验证明,本文方法可以有效检测跟踪极小目标,提高跟踪的实时处理能力。     

应用机器人轨迹跟踪技术的电力线路无人机智能化巡检系统设计

野外电力线路易发生损坏,且时变特性干扰较大,检测准确度较低,因此,设计应用机器人轨迹跟踪技术的电力线路无人机智能化巡检系统。该系统通过数据采集模块和飞行状态检测模块,分别进行电力线路图像数据获取与飞行状态监测,飞行控制模块接收图像与状态数据,并在轨迹跟踪控制子模块中使用自适应鲁棒滑模控制算法,实现无人机的轨迹跟踪,同时,该模块经无线数据传输模块将数据传输至地面站,在巡检数据智能分析管理模块中,地面站根据数据信息,完成电力线路故障识别,进而实现电力线路无人机智能化巡检。实验结果表明,该系统具有良好的轨迹跟踪效果,且巡检准确率较高,满足多种天气作业需求。     

An efficient parallel-network packet pattern-matching approach using GPUs

In the past few years, the increase in interest usage has been substantial. The high network bandwidth speed and the large amount of threats pose challenges to current network intrusion detection systems, which manage high amounts of network traffic and perform complicated packet processing. Pattern matching is a computationally intensive process included in network intrusion detection systems. In this paper, we present an efficient graphics processing unit (GPU)-based network packet pattern-matching algorithm by leveraging the computational power of GPUs to accelerate pattern-matching operations and subsequently increase the overall processing throughput. According to the experimental results, the proposed algorithm achieved a maximal traffic processing throughput of over 2 Gbit/s. The results demonstrate that the proposed GPU-based algorithm can effectively enhance the performance of network intrusion detection systems.     

Algorithmic performance studies on graphics processing units

We report on our experience with integrating and using graphics processing units (GPUs) as fast parallel floating-point co-processors to accelerate two fundamental computational scientific kernels on the GPU: sparse direct factorization and nonlinear interior-point optimization. Since a full re-implementation of these complex kernels is typically not feasible, we identify the matrix–matrix multiplication as a first natural entry-point for a minimally invasive integration of GPUs. We investigate the performance on the NVIDIA GeForce 8800 multicore chip initially architectured for intensive gaming applications. We exploit the architectural features of the GeForce 8800 GPU to design an efficient GPU-parallel sparse matrix solver. A prototype approach to leverage the bandwidth and computing power of GPUs for these matrix kernel operation is demonstrated resulting in an overall performance of over 110 GFlops/s on the desktop for large matrices and over 38 GFlops/s for sparse matrices arising in real applications. We use our GPU algorithm for PDE-constrained optimization problems and demonstrate that the commodity GPU is a useful co-processor for scientific applications.     

HPCCD: Hybrid Parallel Continuous Collision Detection using CPUs and GPUs

We present a novel, hybrid parallel continuous collision detection (HPCCD) method that exploits the availability of multi‐core CPU and GPU architectures. HPCCD is based on a bounding volume hierarchy (BVH) and selectively performs lazy reconstructions. Our method works with a wide variety of deforming models and supports self‐collision detection. HPCCD takes advantage of hybrid multi‐core architectures – using the general‐purpose CPUs to perform the BVH traversal and culling while GPUs are used to perform elementary tests that reduce to solving cubic equations. We propose a novel task decomposition method that leads to a lock‐free parallel algorithm in the main loop of our BVH‐based collision detection to create a highly scalable algorithm. By exploiting the availability of hybrid, multi‐core CPU and GPU architectures, our proposed method achieves more than an order of magnitude improvement in performance using four CPU‐cores and two GPUs, compared to using a single CPU‐core. This improvement results in an interactive performance, up to 148 fps, for various deforming benchmarks consisting of tens or hundreds of thousand triangles.     

无人机平台下的行人与车辆目标实时检测

在无人机图像中快速准确地检测行人和车辆是一项有意义但又极具挑战的任务,其广泛应用于军事侦察、交通管制以及偏远地区救援等任务中。然而,由于无人机属于小型移动设备,其内存和计算能力非常有限,使得如何保证其检测实时性一直是难题。针对SSD算法模型过大、运行内存占用量过高、很难在无人机设备上运行的问题,精心设计了轻量级的基准网络,通过削减原始网络的通道数目以及卷积数目来降低网络的参数量;针对无人机场景下目标小、场景复杂等问题,提出轻量级感受野模块来增强网络特征表示能力,并结合上下文信息来进一步提高小型目标的检测精度。实验结果表明,提出的方法在基于无人机的行人与车辆目标检测任务上有较高的准确性和实时性。     

基于光照自适应动态一致性的无人机目标跟踪

无人机跟踪任务经常面临各种光线变化场景,然而无人机跟踪方法主要在光线充足下实现鲁棒跟踪。提出一种具有光照自适应性和跨帧语义感知动态一致性评估的无人机跟踪方法,实现光线不足下的无人机目标跟踪。首先构建光照自适应模块对昏暗场景进行识别,对视频图像的光照强度进行补偿;其次构建目标模板训练具有目标感知能力的滤波器进行相关运算,并利用跨帧之间的响应信息进行一致性评估;最后构建动态约束策略并对响应差异进行约束,使跟踪器保持时间平滑。在UAVDark135和UAV123数据集上,与9种先进算法进行对比实验,结果表明该算法具有较好的跟踪性能。     

Performance evaluation of a 3D multi-view-based particle filter for visual object tracking using GPUs and multicore CPUs

This paper presents a deep and extensive performance analysis of the particle filter (PF) algorithm for a very compute intensive 3D multi-view visual tracking problem. We compare different implementations and parameter settings of the PF algorithm in a CPU platform taking advantage of the multithreading capabilities of the modern processors and a graphics processing unit (GPU) platform using NVIDIA CUDA computing environment as developing framework. We extend our experimental study to each individual stage of the PF algorithm, and evaluate the quality versus performance trade-off among different ways to design these stages. We have observed that the GPU platform performs better than the multithreaded CPU platform when handling a large number of particles, but we also demonstrate that hybrid CPU/GPU implementations can run almost as fast as only GPU solutions.     

A new parallel particle filter face tracking method based on heterogeneous system

This paper proposed a multi-cue-based face-tracking algorithm with the supporting framework using parallel multi-core and one Graphic Processing Unit (GPU). Due to illumination and partial-occlusion problems, face tracking usually cannot stably work based on a single cue. Focusing on the above-mentioned problems, we first combined three different visual cues??color histogram, edge orientation histogram, and wavelet feature??under the framework of particle filters to considerably improve tracking performance. Furthermore, an online updating strategy made the algorithm adaptive to illumination changes and slight face rotations. Subsequently, attempting two parallel approaches resulted in real-time responses. However, the computational efficiency decreased considerably with the increase of particles and visual cues. In order to handle the large amount of computation costs resulting from the introduced multi-cue strategy, we explored two parallel computing techniques to speed up the tracking process, especially the most computation-intensive observational steps. One is a multi-core-based parallel algorithm with a MapReduce thread model, and the other is a GPU-based speedup approach. The GPU-based technique uses features-matching and particle weight computations, which have been put into the GPU kernel. The results demonstrate that the proposed face-tracking algorithm can work robustly with cluttered backgrounds and differing illuminations; the multi-core parallel scheme can increase the speed by 2?C6 times compared with that of the corresponding sequential algorithms. Furthermore, a GPU parallel scheme and co-processing scheme can achieve a greater increase in speed (8×?C12×) compared with the corresponding sequential algorithms.     

复杂环境下多无人机协作式地面移动目标跟踪

针对多无人机(UAV)协同地面移动目标跟踪问题展开研究.提出一种基于主动感知的问题求解框架,建立多UAV协同目标跟踪问题模型;在此基础上,采用分布式无色信息滤波实现目标状态融合估计与预测;然后,基于预测目标状态,结合滚动时域控制与遗传算法设计一种多UAV在线协同航迹规划算法.仿真结果表明:结合预测目标状态在线优化UAV...     

移动智能终端的SIFT特征检测并行算法

特征的检测和匹配在计算机视觉应用中是一个重要的组成部分,如图像匹配、物体识别和视频跟踪等。SIFT算法以其尺度不变性和旋转不变性在图像配准领域得到了广泛应用。传统的SIFT算法效率低,因此提出一种在移动智能终端上实现的高效方法。在Android平台利用OpenCL框架实现了移动智能终端的SIFT算法,通过计算任务的重新分配,优化SIFT算法在移动GPU上的并行实现。实验结果表明,移动平台的SIFT算法充分利用了GPU并行计算能力,大大提高了SIFT算法的执行效率,实现了高效的特征检测。