Oriented Bounding Box Object Detection Model Based on Improved YOLOv8

In the study of oriented bounding boxes(OBB)object detection in high-resolution remote sensing images,the problem of missed and wrong detection of small targets occurs because the targets are too small and have different orientations.Existing OBB object detection for remote sensing images,although making good progress,mainly focuses on directional modeling,while less consideration is given to the size of the object as well as the problem of missed detection.In this study,a method based on improved YOLOv8 was proposed for detecting oriented objects in remote sensing images,which can improve the detection precision of oriented objects in remote sensing images.Firstly,the ResCBAMG module was innovatively designed,which could better extract channel and spatial correlation information.Secondly,the innovative top-down feature fusion layer network structure was proposed in conjunction with the Efficient Channel Attention(ECA)attention module,which helped to capture inter-local cross-channel interaction information appropriately.Finally,we introduced an innovative ResCBAMG module between the different C2f modules and detection heads of the bottom-up feature fusion layer.This innovative structure helped the model to better focus on the target area.The precision and robustness of oriented target detection were also improved.Experimental results on the DOTA-v1.5 dataset showed that the detection Precision,mAP@0.5,and mAP@0.5:0.95 metrics of the improved model are better compared to the original model.This improvement is effective in detecting small targets and complex scenes.

基于Bounding Box的车辆行为标注

针对目前自动驾驶汽车行为预测对目标行为标注准确率低及压线行驶行为无法标注问题,首先通过建立车辆包围盒(Bounding Box)将车辆的形状描述出来,随后通过Bounding Box 4个顶点与车道线的相交关系来判断目标车是否有换道行为。对于无车道线的情况,首先通过自车轨迹左右拓展出虚拟车道线,通过Bounding Box与虚拟车道线的关系判断目标车是否有切入自车道的行为,随后进行标注。通过Bounding Box对目标行为进行标注可以将标注的准确率提高至80%,并且可以将压线行驶行为标注出来,为后续行为预测模型训练打下良好的基础。

圆外切Bounding-box WSN定位方法

在Bounding-box及其改进方法研究中,普遍采用正方形的重叠区域的质心作为定位的结果,然而该正方形与实际无线传感器节点的通信区域模型之间存在较大差异,导致定位误差较大。针对此问题,提出一种改进的Bounding-box定位方法。该方法在定位时,不再采用正方形的通信区域模型,而是采用圆形的通信区域模型进行定位。基于仿真数据以及采用3种典型通信环境下真实的到达信号强度指示(received signal strength indicator,RSSI)数据完成定位实验,实验结果表明,该方法具有较高的定位精度,因此具有一定的实际应用价值。

基于信号飞行时间与误差分析的改进无线传感网络Bounding-box定位算法

为提高无线传感网络定位算法的实效性,针对Bounding-box定位算法定位精度不足的问题,提出了基于信号飞行时间与误差分析的改进Bounding-box定位算法。该算法根据累计距离误差,在正方形重叠区域重新划分离散小方格,然后按照累计距离误差最小化准则,选择对应离散小方格的中心点坐标作为待定位节点的定位位置。通过仿真实验表明,提出的改进Bounding-box定位算法,在距离测量精确和小误差情况下,能够明显提高定位精度。此外,真实环境实验表明,在采用信号飞行时间作为距离测量技术的条件下,提出算法的定位误差最小。

基于无线传感器离散网络模型的Bounding Box定位算法研究

Bounding Box算法是一种典型的基于离散网络模型的无线传感器网络节点定位算法。针对Bounding Box算法定位误差大、覆盖率低的缺点,提出一种采用虚拟锚节点策略的改进定位算法。首先未知节点利用其通信范围内的锚节点进行定位;其次,已定位的节点根据升级策略有选择性的升级为虚拟锚节点;最后,无法定位的节点利用虚拟锚节点实现定位。另外,在离散网络模型的基础上,通过建立双半径网络节点模型从而进一步约束了未知节点的位置。理论分析及仿真结果均表明,该算法在显著提高定位覆盖率的同时,有效地提高了定位精度。

一种基于虚拟锚节点策略改进的Bounding Box定位算法

针对Bounding Box算法定位误差大、覆盖率低的缺点,提出了一种采用虚拟锚节点策略的改进定位算法。首先未知节点利用其通信范围内的锚节点进行定位;其次,已定位的节点根据升级策略有选择性的升级为虚拟锚节点;最后,无法定位的节点利用虚拟锚节点实现定位。另外,在离散网络模型的基础上,通过建立双半径网络节点模型从而进一步约束了未知节点的位置。理论分析及仿真结果均表明,该算法在显著提高定位覆盖率的同时,有效地提高了定位精度。

极限分割估计矩形的Bounding-Box定位算法

针对无线传感器网络中Bounding-Box算法定位精度低的问题,在Bounding-Box算法的基础上提出一种极限分割估计矩形的方法来改进定位算法,分割后的估计矩形产生一个待选质心,当满足分割条件时,对估计矩形继续分割,并不断产生待选质心,当满足终止分割条件时,将上一次分割得到的待选质心坐标作为未知节点的最终位置,通过极限分割的方法可以修正未知节点的定位误差。仿真结果表明,在无需增加额外通信开销的情况下,改进的算法在一定程度上降低了算法的平均相对定位误差。

基于自适应RSSI的Bounding-Box轮回选择WSN定位算法

针对无线传感器网络(WSN)定位精度不高和环境自适应性较差问题,提出一种基于自适应RSSI的Bounding-Box轮回选择WSN定位算法。传统的RSSI测距模型中距离参考节点1 m处信号强度值A和路径衰减指数n都为固定值,无法适应不同环境的需要,提出了一种测量A的新方法,并且通过引入一个虚拟锚节点动态实时获取n,然后采用三三交集Bounding-Box定位算法得到许多接近未知节点的估计值,最后对这些估计值利用轮回选择法得到最终定位结果。仿真结果表明,该算法与已有的相关Bounding-Box算法相比,具有较高定位精度和一定的实际应用价值。

基于bounding-box与卡尔曼滤波的优化压缩感知算法的目标定位

针对无线传感器网络目标定位过程中存在的测量矩阵维数高、运算量大以及测量向量不准确的问题,文章提出一种优化压缩感知(compressive sensing,CS)定位算法。首先对传感器采集的接收信号强度值进行卡尔曼滤波保证压缩感知测量向量的准确性;然后引入bounding-box方法估计位置区域,缩小节点定位范围从而降低后一阶段压缩感知测量矩阵的维数;最后在节点估计区域进行压缩感知定位,并提出基于原子相关度阈值的回溯匹配追踪算法,通过原子相关度阈值控制对候选集原子进行二次筛选剔除低相关度原子,在支撑集中保留系数较大的原子,提升重建精度。实验结果表明,在信噪比为5 dB,目标数为8时,相较于传统的OMP算法、GMP算法、CoSaMP算法,所提优化定位算法的定位精度分别提升61.21%、51.53%和45.12%。

煤矿井下Bounding-Box的二次定位算法研究

根据煤矿井下人员精确定位系统对实时性和定位精度的要求,提出了基于TOF(time of flight,飞行时间)的Bounding-Box二次定位算法,该算法综合了TOF测距不易受环境干扰和Bounding-Box计算实时性高的优点。利用待定位节点与参考节点测距获得距离,并利用Bounding-Box得到初始区域位置信息后,再将周围已定位的节点考虑进去,并再次利用Bounding-Box算法进行二次定位,缩小未知节点所在的区域,最终获得位置信息。实验结果表明,该算法实时性高,并且能够提高定位精度。

Shortest Alternate Path Discovery through Recursive Bounding Box Pruning

Congestion is a dynamic phenomenon and hence efficiently computing alternate shortest route can only help expedite decongestion. This research is aimed to efficiently compute shortest path for road traffic network so that congestion can be eased resulting in reduced CO2 emission and improved economy. Congestion detection is achieved after evaluating road capacity and road occupancy. Congestion index, a ratio of road occupancy to road capacity is computed, congestion index higher than 0.6 necessitates computation of alternate shortest route. Various algorithms offer shortest alternate route. The paper discusses minimization of graph based by removing redundant nodes which don’t play a role in computation of shortest path. The proposal is based on continuous definition of a bounding box every time a next neighboring node is considered. This reduces maximum number of contentious nodes repeatedly and optimizes the network. The algorithm is deployed from both the ends sequentially to ensure zero error and validate the shortest path discovery. While discovering shortest path, the algorithm also offers an array of shortest path in ascending order of the path length. However, vehicular traffic exhibits network duality viz. static and dynamic network graphs. Shortest route for static distance graph is pre-computed and stored for look-up, alternate shortest path based on assignment of congestion levels to edge weights is triggered by congestion index. The research also supports directed graphs to address traffic rules for lanes having unidirectional and bidirectional traffic.

Bounding box based on probability density for the pedestrian tracking

This paper proposes a pedestrian tracking approach using bounding box based on probability densities.It is generally a difficult task to track features like corner points in outdoor images due to complex environment.To solve this problem,the feature points are projected along X and Y direction separately,and a histogram is constructed for each projection,with horizontal axis as positions and vertical axis as the number of feature points that lie on each position.Finally,the vertical axis is normalized for expression as probability.After histogram is constructed,the probability of each feature point is checked with a threshold.A feature point will be ignored if its probability is lower than a threshold,while the remaining feature points are grouped,based on which a bounding box is made.Kanade-Lucas Tomasi(KLT)algorithm is adopted as the tracking algorithm because it is able to track local features in images robustly.The efficiency of the tracking results using this method is verified in real environment test.

LiDAR-based estimation of bounding box coordinates using Gaussian process regression and particle swarm optimization

Camera-based object tracking systems in a given closed environment lack privacy and confidentiality.In this study,light detection and ranging(LiDAR)was applied to track objects similar to the camera tracking in a closed environment,guaranteeing privacy and confidentiality.The primary objective was to demonstrate the efficacy of the proposed technique through carefully designed experiments conducted using two scenarios.In Scenario I,the study illustrates the capability of the proposed technique to detect the locations of multiple objects positioned on a flat surface,achieved by analyzing LiDAR data collected from several locations within the closed environment.Scenario II demonstrates the effectiveness of the proposed technique in detecting multiple objects using LiDAR data obtained from a single,fixed location.Real-time experiments are conducted with human subjects navigating predefined paths.Three individuals move within an environment,while LiDAR,fixed at the center,dynamically tracks and identifies their locations at multiple instances.Results demonstrate that a single,strategically positioned LiDAR can adeptly detect objects in motion around it.Furthermore,this study provides a comparison of various regression techniques for predicting bounding box coordinates.Gaussian process regression(GPR),combined with particle swarm optimization(PSO)for prediction,achieves the lowest prediction mean square error of all the regression techniques examined at 0.01.Hyperparameter tuning of GPR using PSO significantly minimizes the regression error.Results of the experiment pave the way for its extension to various real-time applications such as crowd management in malls,surveillance systems,and various Internet of Things scenarios.

Best bounds on the distance between 3-direction quartic box spline surface and its control net

We present the best bounds on the distance between 3-direction quartic box spline surface patch and its control net by means of analysis and computing for the basis functions of 3-direction quartic box spline surface.Both the local bounds and the global bounds are given by the maximum norm of the first differences or second differences or mixed differences of the control points of the surface patch.

Box Dimension of Weyl Fractional Integral of Continuous Functions with Bounded Variation

We know that the Box dimension of f（x） ∈ C^1[0,1] is 1. In this paper, we prove that the Box dimension of continuous functions with bounded variation is still 1. Furthermore, Box dimension of Weyl fractional integral of above function is also 1.

窗口锚定的偏移受限动态蛇形卷积网络航拍小目标检测

为了从小目标有限特征中获取关键的有效信息,提升小目标的定位能力和检测精度,文中提出窗口锚定的偏移受限动态蛇形卷积网络航拍小目标检测方法.首先,构造偏移受限动态蛇形卷积,在不同方位动态偏移,受限蛇形卷积核自适应地关注不同大小和形状的特征区域,使特征提取聚焦于微小局部结构,促进小目标特征的捕获.然后,采用双阶段多尺度特征融合方法,对不同层阶特征图进行特征对齐、融合和注入,增强底层细节信息与高层语义信息的融合,并强化不同尺寸目标信息传输,提高小目标的检测能力.与此同时,设计窗口锚定的边界框回归损失函数,基于辅助边界框和最小点距离进行边界回归,获得准确的回归结果,提高小目标的定位能力.最后,在3个航拍数据集上的实验表明,文中方法对小目标的检测性能有不同程度的改善和提高.

决策树算法在机械臂碰撞规避方法中的应用

针对机械臂在复杂环境作业时,由于碰撞规避方法的碰撞检测效果差、障碍物规避效果不佳,导致机械臂频繁发生碰撞的问题,提出一种应用决策树算法的机械臂碰撞规避方法。通过分析机械臂运动学结构,获取机械臂运动学方程,结合二次投影法将机械臂碰撞过程,简化为三维视角下包围盒相交情况的判断过程,检测机械臂碰撞情况,通过浓度函数采集三维空间中包围盒预计位移信息,建立基于预计位移信息的决策树模型,获取机械臂碰撞规避行为最优决策信息,实现机械臂规避碰撞。实验结果表明,应用决策树算法的机械臂碰撞规避方法仅需0.29s有效检测出碰撞,在复杂环境下,规划的碰撞规避路线中机械臂与障碍物未发生碰撞,因此,该方法有效提高了机械臂碰撞规避的效果。

基于深度学习的实例分割边界框回归方法研究

针对实例分割任务中图像中可能出现相互遮挡或边缘模糊导致边界框定位不准确的问题,本文提出了一种新的边界框回归损失函数。将边界框位置预测转化为估计定位置信度随位置变化的概率分布;考虑坐标点间存在联系,提出一种面积差计算方法;为了证明此方法可以很好地应用于先检测后分割的实例分割模型,本文使用Mask R-CNN作为基线。实验结果表明:在边界框检测及实例分割任务中,本文方法的精度优于其他方法,对于小物体的检测与分割效果更显著,训练和评估速度也更快。

基于MFDC-SSD网络的接触网定位线夹缺陷识别

针对接触网应用环境复杂,定位线夹体积小、安装方向特殊、不易识别,传统的目标检测算法效果较差等问题,基于多尺度特征融合密集连接网络模型,提出了一种接触网定位线夹缺陷检测新方法。首先结合DenseNet与Inception模块对SSD模型的特征提取网络进行改进,在特定的特征层间共享上下文信息,提升特征提取能力。然后从网络深层到浅层,逐级采用FPN融合SSD检测的多尺度特征图,设计多特征融合的密集连接网络模型,最后将f GIoU作为边框损失函数,在训练中优化真实框和预测框的重合度。对采集的某段接触网定位线夹图像数据集进行检测识别。结果表明:该定位线夹缺陷检测方法可在复杂接触网背景下,对定位线夹脱落和松动进行检测,且在不同角度、亮度的图像中均具有较强的鲁棒性。

基于UG二次开发的多材料零件3D打印建模方法研究

随着制造业的不断创新与改进,多材料三维(Three-Dimensions,3D)打印工艺的重要性日益显现,多材料建模技术是3D打印工艺的核心模块。本研究提出一种基于UG二次开发的多材料3D打印建模方法。首先利用现有3D建模软件UG(Unigraphics NX)创建待打印零件的3D模型,通过包围盒原理及交集算法,对3D模型所处的材料空间微分化;其次通过UG对其单个或局部小立方体添加颜色,将颜色信息通过材料颜色映射表映射为材料信息,输出多材料模型文件;最后将3D模型导入材料空间,打印出满足功能要求与外观要求的多材料零件。该建模方法可为多材料3D打印建模技术研究提供参考。