YOLO-MFD:Remote Sensing Image Object Detection with Multi-Scale Fusion Dynamic Head

Remote sensing imagery,due to its high altitude,presents inherent challenges characterized by multiple scales,limited target areas,and intricate backgrounds.These inherent traits often lead to increased miss and false detection rates when applying object recognition algorithms tailored for remote sensing imagery.Additionally,these complexities contribute to inaccuracies in target localization and hinder precise target categorization.This paper addresses these challenges by proposing a solution:The YOLO-MFD model(YOLO-MFD:Remote Sensing Image Object Detection withMulti-scale Fusion Dynamic Head).Before presenting our method,we delve into the prevalent issues faced in remote sensing imagery analysis.Specifically,we emphasize the struggles of existing object recognition algorithms in comprehensively capturing critical image features amidst varying scales and complex backgrounds.To resolve these issues,we introduce a novel approach.First,we propose the implementation of a lightweight multi-scale module called CEF.This module significantly improves the model’s ability to comprehensively capture important image features by merging multi-scale feature information.It effectively addresses the issues of missed detection and mistaken alarms that are common in remote sensing imagery.Second,an additional layer of small target detection heads is added,and a residual link is established with the higher-level feature extraction module in the backbone section.This allows the model to incorporate shallower information,significantly improving the accuracy of target localization in remotely sensed images.Finally,a dynamic head attentionmechanism is introduced.This allows themodel to exhibit greater flexibility and accuracy in recognizing shapes and targets of different sizes.Consequently,the precision of object detection is significantly improved.The trial results show that the YOLO-MFD model shows improvements of 6.3%,3.5%,and 2.5%over the original YOLOv8 model in Precision,map@0.5 and map@0.5:0.95,separately.These results illustrate the clear advantages of the method.

MSC-YOLO:Improved YOLOv7 Based on Multi-Scale Spatial Context for Small Object Detection in UAV-View

Accurately identifying small objects in high-resolution aerial images presents a complex and crucial task in thefield of small object detection on unmanned aerial vehicles(UAVs).This task is challenging due to variations inUAV flight altitude,differences in object scales,as well as factors like flight speed and motion blur.To enhancethe detection efficacy of small targets in drone aerial imagery,we propose an enhanced You Only Look Onceversion 7(YOLOv7)algorithm based on multi-scale spatial context.We build the MSC-YOLO model,whichincorporates an additional prediction head,denoted as P2,to improve adaptability for small objects.We replaceconventional downsampling with a Spatial-to-Depth Convolutional Combination(CSPDC)module to mitigatethe loss of intricate feature details related to small objects.Furthermore,we propose a Spatial Context Pyramidwith Multi-Scale Attention(SCPMA)module,which captures spatial and channel-dependent features of smalltargets acrossmultiple scales.This module enhances the perception of spatial contextual features and the utilizationof multiscale feature information.On the Visdrone2023 and UAVDT datasets,MSC-YOLO achieves remarkableresults,outperforming the baseline method YOLOv7 by 3.0%in terms ofmean average precision(mAP).The MSCYOLOalgorithm proposed in this paper has demonstrated satisfactory performance in detecting small targets inUAV aerial photography,providing strong support for practical applications.

A New method for selecting multi-scale road network objects

Aimed at solving the problems of road network object selection at any unknown scale, the existing methods on object selection are integrated and extended in this paper, and a new object interpolation method is proposed, which reflects the inheritable and transferable characteristics of related information among multi-scale representation objects, and takes the attribute effects into account. Then the basic idea, the overall framework and the technical flow of the interpolation are put forward, at the samet：me synthetical weight function of the interpolation method is defined and described. The method and technical strategies of object selection are extended, and the key problems are solved, including the dejign of the objective quantitative and structural selections based on the weight values, the interpolation experiment strategies and technical flows, the result of the test shows that the object interpolation method not only inherits the objects at smaller scales, but also takes the attribute effect into account when deriving objects from larger scales according to the road importance, which is a guarantee to objective selection of the road objects at middle scales.

Automatic Matching of Multi-scale Road Networks under the Constraints of Smaller Scale Road Meshes

In this paper,we propose a new method to achieve automatic matching of multi-scale roads under the constraints of smaller scale data.The matching process is:Firstly,meshes are extracted from two different scales road data.Secondly,several basic meshes in the larger scale road network will be merged into a composite one which is matched with one mesh in the smaller scale road network,to complete the N∶1(N>1)and 1∶1 matching.Thirdly,meshes of the two different scale road data with M∶N(M>1,N>1)matching relationships will be matched.Finally,roads will be classified into two categories under the constraints of meshes:mesh boundary roads and mesh internal roads,and then matchings between the two scales meshes will be carried out within their own categories according to the matching relationships.The results show that roads of different scales will be more precisely matched using the proposed method.

Zero-DCE++Inspired Object Detection in Less Illuminated Environment Using Improved YOLOv5

Automated object detection has received the most attention over the years.Use cases ranging from autonomous driving applications to military surveillance systems,require robust detection of objects in different illumination conditions.State-of-the-art object detectors tend to fare well in object detection during daytime conditions.However,their performance is severely hampered in night light conditions due to poor illumination.To address this challenge,the manuscript proposes an improved YOLOv5-based object detection framework for effective detection in unevenly illuminated nighttime conditions.Firstly,the preprocessing strategies involve using the Zero-DCE++approach to enhance lowlight images.It is followed by optimizing the existing YOLOv5 architecture by integrating the Convolutional Block Attention Module(CBAM)in the backbone network to boost model learning capability and Depthwise Convolutional module(DWConv)in the neck network for efficient compression of network parameters.The Night Object Detection(NOD)and Exclusively Dark(ExDARK)dataset has been used for this work.The proposed framework detects classes like humans,bicycles,and cars.Experiments demonstrate that the proposed architecture achieved a higher Mean Average Precision(mAP)along with a reduction in model size and total parameters,respectively.The proposed model is lighter by 11.24%in terms of model size and 12.38%in terms of parameters when compared to baseline YOLOv5.

A Lightweight Road Scene Semantic Segmentation Algorithm

In recent years,with the continuous deepening of smart city construction,there have been significant changes and improvements in the field of intelligent transportation.The semantic segmentation of road scenes has important practical significance in the fields of automatic driving,transportation planning,and intelligent transportation systems.However,the current mainstream lightweight semantic segmentation models in road scene segmentation face problems such as poor segmentation performance of small targets and insufficient refinement of segmentation edges.Therefore,this article proposes a lightweight semantic segmentation model based on the LiteSeg model improvement to address these issues.The model uses the lightweight backbone network MobileNet instead of the LiteSeg backbone network to reduce the network parameters and computation,and combines the Coordinate Attention(CA)mechanism to help the network capture long-distance dependencies.At the same time,by combining the dependencies of spatial information and channel information,the Spatial and Channel Network(SCNet)attention mechanism is proposed to improve the feature extraction ability of the model.Finally,a multiscale transposed attention encoding(MTAE)module was proposed to obtain features of different resolutions and perform feature fusion.In this paper,the proposed model is verified on the Cityscapes dataset.The experimental results show that the addition of SCNet and MTAE modules increases the mean Intersection over Union(mIoU)of the original LiteSeg model by 4.69%.On this basis,the backbone network is replaced with MobileNet,and the CA model is added at the same time.At the cost of increasing the minimum model parameters and computing costs,the mIoU of the original LiteSeg model is increased by 2.46%.This article also compares the proposed model with some current lightweight semantic segmentation models,and experiments show that the comprehensive performance of the proposed model is the best,especially in achieving excellent results in small object segmentation.Finally,this article will conduct generalization testing on the KITTI dataset for the proposed model,and the experimental results show that the proposed algorithm has a certain degree of generalization.

图像引导和点云空间约束的公路洒落物检测定位方法

公路洒落物是影响交通安全的重要因素之一,为了解决中小尺度公路洒落物检测中的漏检、误检以及难以定位等问题,本文提出了一种图像引导和点云空间约束的公路洒落物检测定位方法。该方法使用改进的YOLOv7-OD网络处理图像数据获取二维目标预测框信息,将目标预测框投影到激光雷达坐标系下得到锥形感兴趣区域(region of interest,ROI)。在ROI区域内的点云空间约束下,联合点云聚类和点云生成算法获得不同尺度的洒落物在三维空间中的检测定位结果。实验表明:改进的YOLOv7-OD网络在中尺度目标上的召回率和平均精度分别为85.4%和82.0%,相比YOLOv7网络分别提升6.6和8.0个百分点;在小尺度目标上的召回率和平均精度分别为66.8%和57.3%,均提升5.3个百分点;洒落物定位方面,对于距离检测车辆30~40 m处的目标,深度定位误差为0.19 m,角度定位误差为0.082°,实现了多尺度公路洒落物的检测和定位。

基于改进YOLOv8的嵌入式道路裂缝检测算法

在边缘端设备部署YOLOv8L模型进行道路裂缝检测可以实现较高的精度,但难以保证实时检测。针对此问题,提出一种可部署到边缘计算设备Jetson AGX Xavier上的基于改进YOLOv8模型的目标检测算法。首先,利用部分卷积设计Faster Block结构以替换YOLOv8 C2f模块中的Bottleneck结构,并将改进后的C2f模块记为C2f-Faster;其次,在YOLOv8主干网络中的每个C2f-Faster模块之后接一个SE(Squeeze-and-Excitation)通道注意力层,进一步提高检测的精度。在开源道路损害数据集RDD20(Road Damage Detection 20)上的实验结果表明:所提方法的平均F1得分为0.573,每秒检测帧数(FPS)为47,模型大小为55.5MB,相较于GRDDC2020(GlobalRoadDamageDetection Challenge 2020)的SOTA(State-Of-The-Art)模型,F1得分提高了0.8个百分点,FPS提高了291.7%,模型大小减小了41.8%,实现了在边缘设备上对道路裂缝实时且准确的检测。

基于三级养护标准的沥青路面预养护方案多目标加权灰靶决策

针对沥青路面最佳预防性养护策略选择问题,结合关于沥青路面预防性养护指标及规范标准,建立了基于判断性指标、综合性指标和控制性指标的三级预防性养护判断标准。在此标准下,以多年度项目级养护规划为研究对象,结合GM(1,1)预测模型确定预防性养护时段,并引入多目标智能加权灰靶决策模型对适用性预防性养护方案进行优化决策。在此过程中,确定了养护费用、耐久性等8个养护目标并利用博弈论组合赋权法确定权重,选取G30连霍高速甘肃省境内某路段进行决策分析。结果表明:该路段最早需要开展预防性养护的时间为第3年,在第6年底之后不宜再实施预防性养护,在该预防性养护时段内,方案4的综合效益值最大,其值为0.735 8,即应在第4年采取超薄层罩面预养护措施。该方法简单实用,可成为沥青路面预防性养护策略选择的一种新方法。

基于多目标优化的变电站消防资源配置算法

针对变电站消防资源分配与分布不均匀的问题,提出了一种基于多目标优化的变电站消防资源配置算法。该算法采用电力生产场所的道路网作为变电站消防责任区划分的依据,并结合各划分区域的消防需求构建消防资源配置模型。根据该模型的特点,在帕累托最优解的约束下提出了一种基于模拟退火的多目标优化算法,来求解该消防资源配置模型。仿真与实验结果表明,所提出的消防资源配置模型更符合实际变电站各场所分布的特点,且所提出的多目标优化算法得到的消防资源分配结果能在消防资源有限的条件下,实现最大的配置效益和快速的消防响应。

考虑偏好的空间文本对象多目标最短路径查询

为了解决路网中考虑偏好的空间文本对象多目标最短路径查询问题,设计了包含属性的IR树索引结构;然后利用类别约束,排序约束构建限定的有向无环图.提出了支持属性的局部贪婪算法SALG_SPG,以对最短路径查询进行处理;为进一步提高查询处理效率,提出了支持属性的全局优化算法SAGO_SPG,该算法利用阈值和缓存机制减少了大量无效、重复的计算;最后,通过与现有的FEBF算法的对比实验,分析并验证了所提算法的高效性.

寒区再生砖骨料混凝土路用性能多目标优化

以5~10 mm、10~20 mm再生砖骨料和水灰比为自变量因子,将抗压强度、耐磨性能和抗冻性能等路用性能作为目标,采用中心复合试验设计,确定混凝土中不同因素的影响程度。对试验结果进行回归拟合,提出因子与混凝土路用性能之间的拟合模型,并利用方差分析验证模型的可靠性和稳定性。利用响应面3D图对模型深入分析,确定因子对再生砖骨料混凝土三项寒区路用性能影响程度,从高到低依次是:水灰比、10~20 mm砖骨料和5~10 mm砖骨料。结合渴求函数优化寒区再生砖骨料混凝土的路用性能,以满足3种寒区路况的要求:最大限度强化抗压强度和抗冻性;最大限度提高耐磨性,同时保持优异的抗压强度和抗冻性;根据权重强化抗冻性。研究结果表明:提出的拟合模型可根据工程目标反向求出最佳配比,优化再生砖骨料混凝土的制备工艺,为实际工程应用提供参考。

基于注意力机制CNN-LSTM的毫米波雷达点云特征数据预测生成

在智能驾驶的环境感知领域,毫米波雷达是一种关键的传感器技术。然而,因数据量有限,其特征数据的采集具有一定的挑战性,这限制了环境感知分类模型的训练效果。针对这一难题,提出了一种融合自注意力机制的卷积长短期记忆网络模型,旨在预测并生成毫米波雷达点云的特征数据,以此来扩展雷达特征数据集。首先采集道路目标的运动状态数据,对数据进行二维快速傅里叶变换、恒虚警率检测,并利用多输入多输出(Multiple-Input Multiple-Output,MIMO)技术提升方位分辨率;接着执行点云聚类及特征提取;最后采用含注意力机制的卷积长短期记忆网络对特征数据进行进一步处理与预测。在真实采集的3类道路目标数据集上,与其他模型相比,该方法在不同道路目标运动特征的预测R^(2)上提高了1%~7%。

基于改进YOLOv8的道路缺陷检测

针对道路缺陷小目标在复杂背景下检测精度低、漏检误检率高、泛化能力欠佳的问题,提出了一种改进YOLOv8的道路缺陷检测算法SGBNet。首先,Neck部分用加权双向特征金字塔网络(Bi-directional Feature Pyramid Network, BiFPN)替换PANet,提升模型的特征融合能力;其次,Neck引入全局注意力机制(Global Attention Machanism, GAM),在特征融合阶段进行注意力调整,提高检测精度;最后,添加小目标检测层,进一步增强深层语义信息与浅层语义信息的结合,提高对道路缺陷小目标的检测能力。与原始YOLOv8n算法相比,算法SGBNet的精确率、召回率和平均精度分别提升了3.3%, 2.5%和2.5%,实现了对道路缺陷更精准的检测。

基于改进YOLOv8的道路表面缺陷检测

道路损伤检测是道路安全及道路损伤及时修复的重要前提。针对现有的道路损伤检测算法存在的精度较低,计算量大等问题,提出了一种基于YOLOv8改进的轻量型道路损伤检测算法。首先,将骨干网络中的C2f模块替换为C2f_FasterNext模块,增强有效特征复用的同时降低计算复杂度;其次,然后在骨干网络末端和颈部网络中引入坐标注意力机制(Coordinate Attention,CA),将位置信息嵌入到通道注意力中,强化特征提取能力,并抑制无关特征的干扰。在开源道路损害数据集RDD20(Road Damage Detection20)上的实验结果表明:所提方法的平均F1得分为0.61,每秒检测帧数(FPS)为88,模型大小为45.5MB,改进算法与原算法相比m AP50分别提高了2%和3.7%,算法检测速度达到88FPS,能够实时准确检测道路损伤目标。通过与其他主流目标检测算法比较,验证了该方法的有效性和优越性。

基于改进YOLOv5的路面裂缝检测方法

针对现有裂缝检测模型体积较大且检测精度不高的问题,提出一种基于轻量化网络的无人机航拍图像裂缝检测方法。首先,使用MobileNetv3网络替代YOLOv5的主干网络,降低模型大小;其次,引入C3TR和CBAM模块提高网络表征能力,将损失函数替换为EIOU以提高模型的鲁棒性。实验结果表明,该方法在自制数据集上获得98.9%的精度,相较于原始YOLOv5提高1.2%,模型大小减小51.5%,检测速度提高37%。改进后的模型在精度、大小和速度上均优于Faster-RCNN等4种常见裂缝检测模型,满足了裂缝检测的实时性、轻量化和精度需求。

基于加强特征提取的道路病害检测算法

针对道路病害区域小、类别数量不均衡导致检测困难的问题,提出基于YOLOv7-tiny的道路病害检测算法RDD-YOLO。首先,采用K-means++算法得到拟合目标尺寸更好的锚框。其次,在小目标检测支路上使用量化感知重参数化模块(QARepVGG),增强浅层特征提取,同时构建加强注意力模块(AM-CBAM)嵌入颈部的3个输入,抑制复杂背景干扰。然后,设计特征融合模块(Res-RFB),模拟人眼扩大感受野融合多尺度信息,提高表征能力;另外,构造轻量级解耦头(S-DeHead)提高小目标检测精确率。最后,采用归一化Wasserstein距离度量(NWD)优化小目标定位过程,并缓解样本不均衡问题。实验结果表明,与YOLOv7-tiny相比,RDD-YOLO算法在仅增加0.71×10^(6)参数量和1.7 GFLOPs计算量的成本下,mAP50提高6.19个百分点,F1-Score提高5.31个百分点,并且检测速度达到135.26 frame/s,满足道路养护工作中对检测精度和速度的需求。

复杂道路监控场景下的车辆检测与跟踪数据集

针对现有大部分车辆检测与跟踪数据集通常存在的采集场景单一、数据集长尾分布以及图像采集环境简单等问题,本文构建一个车辆数据集VeDT-MSS,用于城市以及乡村监控场景下4种车辆类别(小汽车、卡车、公交车和摩托车)的检测以及跟踪研究。该数据集具有交通场景多样化、卡车的类内多样性大、摩托车标注实例占比高以及背景复杂程度高4个显著特性。为了验证该数据集的有效性,在目标检测以及多目标跟踪任务上进行了大量的基线实验。实验结果表明,VeDT-MSS数据集在评估现有算法的鲁棒性和泛化性方面具有实用性。该数据集的提出对促进车辆检测与跟踪研究具有相当的潜力,并为计算机视觉社区评估算法性能提供一个新的数据选择。

基于连续路网环境的实体化主体路径规划算法

为提高规划主体在复杂环境中运动的通过可行性和安全可靠性,解决路网环境通常不连续和主体大小普遍未计算的问题,基于连续路网环境提出了一种实体化主体路径规划算法。首先根据环境信息和主体大小,采用融合膨胀的策略构建实体化主体连续环境模型(model continuous environment with subject objective, MCESO),然后采取路网优先(road network priority, RNP)策略,在实体化主体连续环境下利用骨架提取技术得到路网信息,最后以经典A*算法为例,将上述模型融合改进,提出一种路径规划MCESO-RNP-A*算法。仿真实验结果表明,建模方案和规划算法能够使得实体化主体在连续路网环境下安全顺利到达规划指定目标点,并且在大范围环境下相较MCE-A*算法生成路径的时间可降低约30%,验证了算法的可行性和有效性。

基于YOLOv5的路面病害图像识别方法研究

在公路养护中,道路路面病害现有的检测方法多为自动化采集、人工识别,这极大地降低了公路的养护效率。为提高公路路面病害识别效率,提出了一种基于改进YOLOv5的路面病害图像识别算法,在YOLOv5的主干中引入CA注意力机制及SPPCSPC结构,CA提高了模型的感受野,精确定位目标的感兴趣区域,SPPCSPC结构使算法能适应不同的分辨率图像,提高识别速度;在锚框上,将YOLOv5的k-means改为k-means++,锚框更符合数据集中真实标记框大小;试验结果表明,在9种病害类型、56 879张病害图像的数据集中,所提出的方法相比于原模型在精度上提高了8.1%,在检测速度上提高了12.8%,与FasterR-CNN、YOLOv3等方法相比均有所提高。