Probability-Enhanced Anchor-Free Detector for Remote-Sensing Object Detection

Anchor-free object-detection methods achieve a significant advancement in field of computer vision,particularly in the realm of real-time inferences.However,in remote sensing object detection,anchor-free methods often lack of capability in separating the foreground and background.This paper proposes an anchor-free method named probability-enhanced anchor-free detector(ProEnDet)for remote sensing object detection.First,a weighted bidirectional feature pyramid is used for feature extraction.Second,we introduce probability enhancement to strengthen the classification of the object’s foreground and background.The detector uses the logarithm likelihood as the final score to improve the classification of the foreground and background of the object.ProEnDet is verified using the DIOR and NWPU-VHR-10 datasets.The experiment achieved mean average precisions of 61.4 and 69.0 on the DIOR dataset and NWPU-VHR-10 dataset,respectively.ProEnDet achieves a speed of 32.4 FPS on the DIOR dataset,which satisfies the real-time requirements for remote-sensing object detection.

基于anchor-free的光学遥感舰船关重部位检测算法

针对基于深度学习的遥感舰船检测算法存在精细化程度不足、检测效率低的问题,提出一种基于anchor-free的光学遥感舰船关重部位检测算法。所提算法以全卷积的单阶段目标检测(FCOS)算法为基准,在主干网络中引入全局上下文模块,提高网络的特征表达能力;为更好地描述目标的方向性,在预测阶段构建了具有方向表征能力的回归分支;对中心度函数进行优化,使其具备方向感知和自适应能力。实验结果表明:在自建舰船关重部位数据集和HRSC2016上,所提算法的平均精度(AP)比FCOS算法有显著提升;与其他算法相比,所提算法在检测速度和检测精度上均表现优越,具有较高的检测效率。

Anchor-free目标检测算法综述

目标检测作为计算机视觉领域的基础,其研究价值对于推动人工智能发展具有重要意义。长期以来,许多学者都致力于提升目标检测算法效率及性能的研究,无锚点(anchor-free)的目标检测深度学习算法以尺度灵活、鲁棒性强等优势,开始逐渐广泛应用于目标检测任务。介绍了目标检测领域中卷积神经网络和Transformer两种经典的网络架构;以核心网络架构为分类标准,分别介绍了基于卷积神经网络和基于Transformer的anchor-free目标检测深度学习算法,总结了这些算法的改进点和优缺点,并对该方向的未来发展及应用做出展望。

Insight Into the Separation-of-Variable Methods for the Closed-Form Solutions of Free Vibration of Rectangular Thin Plates

The separation-of-variable(SOV)methods,such as the improved SOV method,the variational SOV method,and the extended SOV method,have been proposed by the present authors and coworkers to obtain the closed-form analytical solutions for free vibration and eigenbuckling of rectangular plates and circular cylindrical shells.By taking the free vibration of rectangular thin plates as an example,this work presents the theoretical framework of the SOV methods in an instructive way,and the bisection–based solution procedures for a group of nonlinear eigenvalue equations.Besides,the explicit equations of nodal lines of the SOV methods are presented,and the relations of nodal line patterns and frequency orders are investigated.It is concluded that the highly accurate SOV methods have the same accuracy for all frequencies,the mode shapes about repeated frequencies can also be precisely captured,and the SOV methods do not have the problem of missing roots as well.

Structural Modal Parameter Recognition and Related Damage Identification Methods under Environmental Excitations: A Review

Modal parameters can accurately characterize the structural dynamic properties and assess the physical state of the structure.Therefore,it is particularly significant to identify the structural modal parameters according to the monitoring data information in the structural health monitoring(SHM)system,so as to provide a scientific basis for structural damage identification and dynamic model modification.In view of this,this paper reviews methods for identifying structural modal parameters under environmental excitation and briefly describes how to identify structural damages based on the derived modal parameters.The paper primarily introduces data-driven modal parameter recognition methods(e.g.,time-domain,frequency-domain,and time-frequency-domain methods,etc.),briefly describes damage identification methods based on the variations of modal parameters(e.g.,natural frequency,modal shapes,and curvature modal shapes,etc.)and modal validation methods(e.g.,Stability Diagram and Modal Assurance Criterion,etc.).The current status of the application of artificial intelligence(AI)methods in the direction of modal parameter recognition and damage identification is further discussed.Based on the pre-vious analysis,the main development trends of structural modal parameter recognition and damage identification methods are given to provide scientific references for the optimized design and functional upgrading of SHM systems.

一种Anchor-Free的联合模型车辆多目标跟踪算法

针对现有车辆跟踪算法不能很好地平衡效率与精度,存在较多ID切换、误检的问题,提出一种Anchor-Free的联合模型车辆多目标跟踪算法,通过把Anchor-Free可变卷积深度特征融合网络引入联合模型,在联合学习车辆目标检测和重识别特征嵌入的基础上,以轨迹关联的方式,完成车辆多目标跟踪任务.所提出的算法在UA-DETRAC车辆数据集及KITTI-tracking数据集组合成的联合数据集上进行训练和测试,结果表明,提出的车辆多目标跟踪算法有效减少了ID切换、误检问题的出现,网络结构更简单,算法运行效率更高.

基于anchor-free的交通场景目标检测技术

在智能交通领域使用深度学习的方法进行目标检测已成为研究热点。当下经典的目标检测算法,无论是基于回归的单阶目标检测模型还是基于候选区域的二阶段目标检测模型,大部分是利用大量预定义的先验框anchor枚举可能的位置、尺寸和纵横比的方法来搜索对象,往往会造成正负样本严重不均衡的问题,模型的性能和泛化能力也受到anchor自身设计的限制。针对基于anchor的目标检测算法存在的问题,利用单阶目标检测网络RetinaNet,对交通场景中的车辆、行人和骑行者建立基于anchor-free的目标检测模型,采用逐像素预测的方式处理目标检测问题,并添加中心性预测分支,提升检测性能。实验表明,与基于anchor的原RetinaNet算法相比,改进的基于anchor-free的目标检测模型算法能够对交通场景中的车辆、行人、骑行者实现更好的识别。

一种迭代聚合的高分辨率网络Anchor-free目标检测方法

针对目前Anchor-free目标检测方法CenterNet(Objects as Points)生成热力图不准确、检测精度不足的问题,提出了一种基于特征迭代聚合的高分辨率表征网络CenterNet-DHRNet。首先,引入高分辨率表征骨干网络,并用迭代聚合的方式对不同分辨率的特征图进行融合,提高网络的分辨率,有效减少图像在下采样过程中损失的空间语义信息。其次,使用高效通道注意力机制对高分辨率表征骨干网络的输出进行优化。最后,利用结合空洞卷积的空间金字塔池化操作增强网络对不同尺度物体的感受野。实验在PASCAL VOC数据集和KITTI数据集上进行,结果表明:CenterNet-DHRNet精度更高,满足实时检测的性能要求,具有良好的鲁棒性。

Distributed localization for anchor-free sensor networks

Geographic location of nodes is very useful in a sensor network. Previous localization algorithms assume that there exist some anchor nodes in this kind of network, and then other nodes are estimated to create their coordinates. Once there are not anchors to be deployed, those localization algorithms will be invalidated. Many papers in this field focus on anchor-based solutions. The use of anchors introduces many limitations, since anchors require external equipments such as global position system, cause additional power consumption. A novel positioning algorithm is proposed to use a virtual coordinate system based on a new concept--virtual anchor. It is executed in a distributed fashion according to the connectivity of a node and the measured distances to its neighbors. Both the adjacent member information and the ranging distance result are combined to generate the estimated position of a network, one of which is independently adopted for localization previously. At the position refinement stage the intermediate estimation of a node begins to be evaluated on its reliability for position mutation; thus the positioning optimization process of the whole network is avoided falling into a local optimal solution. Simulation results prove that the algorithm can resolve the distributed localization problem for anchor-free sensor networks, and is superior to previous methods in terms of its positioning capability under a variety of circumstances.

多尺度特征融合的Anchor-Free轻量化舰船要害部位检测算法

反舰导弹对舰船要害部位的精确打击能力是精确制导武器的关键技术之一。针对反舰导弹导引头对舰船要害部位检测精度低、特征提取能力不足,预测框的处理降低检测速度等问题,提出了一种多尺度特征融合的Anchor-Free轻量化舰船要害部位检测算法。由于舰船要害部位检测数据具有多尺度、多角度特性,引入多尺度特征融合模块,综合利用不同感受野的检测信息,优化特征提取;利用高效轻量化注意力机制改进Hourglass结构中的跨层连接,提升检测精度,降低算法总参数量;使用迁移学习有效提升算法收敛效果。在建立的舰船要害部位检测数据集和公开的PASCAL VOC数据集进行实验,检测准确率分别提升了4.41%和5.57%,分析算法参数与运算量,设计了模块消融实验,论证了所提算法的有效性。

采用Anchor-Free网络结构的实时火灾检测算法

为了解决现有的火灾检测算法中模型复杂,实时性差,检测精度较低的问题,提出快速高效的火灾检测算法.该算法采用Anchor-Free网络结构,克服了Anchor方法中超参数过多、网络结构复杂的缺点;选用MobileNetV2作为基础特征提取网络,满足了检测的高实时性需求;针对火焰目标的形状、尺度多变的特点,设计适合于火焰检测的分类与边框预测子网络;引入特征选择模块,在特征金字塔网络中自动选择更合适的金字塔特征层.算法在自建数据集上的检测精度达到90.1%;在公开数据集上取得了较好的检测结果,其检测速度可达24.6帧/s.实验结果表明,算法的网络模型简单,检测精度较高,检测速度较快;综合性能优于现有的其他火灾检测算法.

挖掘文本框位置特性的anchor-free自然场景文本检测

针对现有优秀的anchor-free文本检测方法只挖掘了文本框几何特性而没有考虑文本框位置特性且缺乏有效的过滤机制,提出了挖掘文本框位置特性的anchor-free自然场景文本检测方法。该方法以ResNet50作为卷积神经网络的主干网络,将多个不同尺寸的特征层融合后预测文本框的几何特性和位置特性,最后辅之以二层过滤机制得到最终的检测文本框。在公开的数据集ICDAR2013和ICDAR2011上F值分别达到了0.870和0.861,证明了该方法的有效性。

Current-Aided Multiple-AUV Cooperative Localization and Target Tracking in Anchor-Free Environments

In anchor-free environments,where no devices with known positions are available,the error growth of autonomous underwater vehicle(AUV)localization and target tracking is unbounded due to the lack of references and the accumulated errors in inertial measurements.This paper aims to improve the localization and tracking accuracy by involving current information as extra references.We first integrate current measurements and maps with belief propagation and design a distributed current-aided message-passing scheme that theoretically solves the localization and tracking problems.Based on this scheme,we propose particle-based cooperative localization and target tracking algorithms,named CaCL and CaTT,respectively.In AUV localization,CaCL uses the current measurements to correct the predicted and transmitted position information and alleviates the impact of the accumulated errors in inertial measurements.With target tracking,the current maps are applied in CaTT to modify the position prediction of the target which is calculated through historical estimates.The effectiveness and robustness of the proposed methods are validated through various simulations by comparisons with alternative methods under different trajectories and current conditions.

基于Anchor-free的孪生网络目标跟踪算法

基于anchor-free的目标预测方法相较于anchor-based方法速度更快,故设计一种基于anchor-free的孪生网络目标跟踪算法(AFSN)。通过对特征图、预测结果进行双重融合来提升跟踪效果,由深至浅对特征图进行堆叠融合,利用多层特征图进行目标预测,融合多个预测结果来稳定跟踪效果。采用anchor-free的目标预测方法,直接在像素点上进行目标类别的预测和边界框回归,避免了需设计大量锚点包围盒的问题。在GOT-10K数据集上,该算法的平均重叠率(AO)和成功率(SR_(0.75))相较于SiamRPN++算法提高了4.9和9.9百分点,算法处理速度可达每秒37帧。

可重叠抑制的Anchor-free目标检测算法

针对Anchor-base目标检测算法的预定义边界框尺度、长宽比固定和需要预先设计的缺陷,提出了一种新的重叠抑制Anchor-free目标检测算法。该算法舍弃了预定义边界框生成,选择直接回归预测特征层上像素点到对象边界框四边的距离,摆脱了预定义边界框的尺度和长宽比限制,可以实现对任意形状的目标对象的识别和边界框回归。在边界框回归时,将周围重叠遮挡对象的影响考虑在内,在边界框回归损失函数中增加与重叠对象边界框之间距离成反比的辅助损失函数,使对象的预测边界框尽可能远离周围重叠遮挡对象的预测边界框和边界框真实值。实验结果表明,提出的Anchor-free目标检测算法能够显著提升极端形状对象和重叠遮挡对象的检测鲁棒性。

Anchor-free Siamese Network Based on Visual Tracking

The Visual tracking problem can usually be solved in two parts.The first part is to extract the feature of the target and get the candidate region.The second part is to realize the classification of the target and the regression of the bounding box.In recent years,Siameses network in visual tracking problem has always been a frontier research hotspot.In this work,it applies two branches namely search area and tracking template area for similar learning to track.Some related researches prove the feasibility of this network structure.According to the characteristics of two branch shared networks in Siamese network,we also propos a new fully convolutional Siamese network to solve the visual tracking problem.Based on the Siamese network structure,the network we designed adopt a new fusion module,which realizes the fusion of multiple feature layers at different depths.We also devise a better target state estimation criterion.The overall structure is simple,efficient and has wide applicability.We extensive experiments on challenging benchmarks including generic object tracking-10k(GOT-10K),online object tracking benckmark2015(OTB2015)and unmanned air vehicle123(UAV123),and comparisons with state-of-the-art trackers and the fusion module commonly used in the past,Finally,our network performed better under the same backbone,and achieved good tracking effect,which proved the effectiveness and universality of our designed network and feature fusion method.

A Review on Sources,Extractions and Analysis Methods of a Sustainable Biomaterial:Tannins

Condensed and hydrolysable tannins are non-toxic natural polyphenols that are a commercial commodity industrialized for tanning hides to obtain leather and for a growing number of other industrial applications mainly to substitute petroleum-based products.They are a definite class of sustainable materials of the forestry industry.They have been in operation for hundreds of years to manufacture leather and now for a growing number of applications in a variety of other industries,such as wood adhesives,metal coating,pharmaceutical/medical applications and several others.This review presents the main sources,either already or potentially commercial of this forestry by-materials,their industrial and laboratory extraction systems,their systems of analysis with their advantages and drawbacks,be these methods so simple to even appear primitive but nonetheless of proven effectiveness,or very modern and instrumental.It constitutes a basic but essential summary of what is necessary to know of these sustainable materials.In doing so,the review highlights some of the main challenges that remain to be addressed to deliver the quality and economics of tannin supply necessary to fulfill the industrial production requirements for some materials-based uses.

DAAPS: A Deformable-Attention-Based Anchor-Free Person Search Model

Person Search is a task involving pedestrian detection and person re-identification,aiming to retrieve person images matching a given objective attribute from a large-scale image library.The Person Search models need to understand and capture the detailed features and context information of smaller objects in the image more accurately and comprehensively.The current popular Person Search models,whether end-to-end or two-step,are based on anchor boxes.However,due to the limitations of the anchor itself,the model inevitably has some disadvantages,such as unbalance of positive and negative samples and redundant calculation,which will affect the performance of models.To address the problem of fine-grained understanding of target pedestrians in complex scenes and small sizes,this paper proposes a Deformable-Attention-based Anchor-free Person Search model(DAAPS).Fully Convolutional One-Stage(FCOS),as a classic Anchor-free detector,is chosen as the model’s infrastructure.The DAAPS model is the first to combine the Anchor-free Person Search model with Deformable Attention Mechanism,applied to guide the model adaptively adjust the perceptual.The Deformable Attention Mechanism is used to help the model focus on the critical information and effectively improve the poor accuracy caused by the absence of anchor boxes.The experiment proves the adaptability of the Attention mechanism to the Anchor-free model.Besides,with an improved ResNeXt+network frame,the DAAPS model selects the Triplet-based Online Instance Matching(TOIM)Loss function to achieve a more precise end-to-end Person Search task.Simulation experiments demonstrate that the proposed model has higher accuracy and better robustness than most Person Search models,reaching 95.0%of mean Average Precision(mAP)and 95.6%of Top-1 on the CUHK-SYSU dataset,48.6%of mAP and 84.7%of Top-1 on the Person Re-identification in the Wild(PRW)dataset,respectively.

A comparison study on structure-function relationship of polysaccharides obtained from sea buckthorn berries using different methods:antioxidant and bile acid-binding capacity

In this study,the structural characters,antioxidant activities and bile acid-binding ability of sea buckthorn polysaccharides(HRPs)obtained by the commonly used hot water(HRP-W),pressurized hot water(HRP-H),ultrasonic(HRP-U),acid(HRP-C)and alkali(HRP-A)assisted extraction methods were investigated.The results demonstrated that extraction methods had significant effects on extraction yield,monosaccharide composition,molecular weight,particle size,triple-helical structure,and surface morphology of HRPs except for the major linkage bands.Thermogravimetric analysis showed that HRP-U with filamentous reticular microstructure exhibited better thermal stability.The HRP-A with the lowest molecular weight and highest arabinose content possessed the best antioxidant activities.Moreover,the rheological analysis indicated that HRPs with higher galacturonic acid content and molecular weight showed higher viscosity and stronger crosslinking network(HRP-C,HRP-W and HRP-U),which exhibited stronger bile acid binding capacity.The present findings provide scientific evidence in the preparation technology of sea buckthorn polysaccharides with good antioxidant and bile acid binding capacity which are related to the structure affected by the extraction methods.

Drilling-based measuring method for the c-φ parameter of rock and its field application

The technology of drilling tests makes it possible to obtain the strength parameter of rock accurately in situ. In this paper, a new rock cutting analysis model that considers the influence of the rock crushing zone(RCZ) is built. The formula for an ultimate cutting force is established based on the limit equilibrium principle. The relationship between digital drilling parameters(DDP) and the c-φ parameter(DDP-cφ formula, where c refers to the cohesion and φ refers to the internal friction angle) is derived, and the response of drilling parameters and cutting ratio to the strength parameters is analyzed. The drillingbased measuring method for the c-φ parameter of rock is constructed. The laboratory verification test is then completed, and the difference in results between the drilling test and the compression test is less than 6%. On this basis, in-situ rock drilling tests in a traffic tunnel and a coal mine roadway are carried out, and the strength parameters of the surrounding rock are effectively tested. The average difference ratio of the results is less than 11%, which verifies the effectiveness of the proposed method for obtaining the strength parameters based on digital drilling. This study provides methodological support for field testing of rock strength parameters.