Unstructured Road Extraction in UAV Images based on Lightweight Model

There is no unified planning standard for unstructured roads,and the morphological structures of these roads are complex and varied.It is important to maintain a balance between accuracy and speed for unstructured road extraction models.Unstructured road extraction algorithms based on deep learning have problems such as high model complexity,high computational cost,and the inability to adapt to current edge computing devices.Therefore,it is best to use lightweight network models.Considering the need for lightweight models and the characteristics of unstructured roads with different pattern shapes,such as blocks and strips,a TMB(Triple Multi-Block)feature extraction module is proposed,and the overall structure of the TMBNet network is described.The TMB module was compared with SS-nbt,Non-bottleneck-1D,and other modules via experiments.The feasibility and effectiveness of the TMB module design were proven through experiments and visualizations.The comparison experiment,using multiple convolution kernel categories,proved that the TMB module can improve the segmentation accuracy of the network.The comparison with different semantic segmentation networks demonstrates that the TMBNet network has advantages in terms of unstructured road extraction.

Ultra-lightweight CNN design based on neural architecture search and knowledge distillation: A novel method to build the automatic recognition model of space target ISAR images

In this paper,a novel method of ultra-lightweight convolution neural network(CNN)design based on neural architecture search(NAS)and knowledge distillation(KD)is proposed.It can realize the automatic construction of the space target inverse synthetic aperture radar(ISAR)image recognition model with ultra-lightweight and high accuracy.This method introduces the NAS method into the radar image recognition for the first time,which solves the time-consuming and labor-consuming problems in the artificial design of the space target ISAR image automatic recognition model(STIIARM).On this basis,the NAS model’s knowledge is transferred to the student model with lower computational complexity by the flow of the solution procedure(FSP)distillation method.Thus,the decline of recognition accuracy caused by the direct compression of model structural parameters can be effectively avoided,and the ultralightweight STIIARM can be obtained.In the method,the Inverted Linear Bottleneck(ILB)and Inverted Residual Block(IRB)are firstly taken as each block’s basic structure in CNN.And the expansion ratio,output filter size,number of IRBs,and convolution kernel size are set as the search parameters to construct a hierarchical decomposition search space.Then,the recognition accuracy and computational complexity are taken as the objective function and constraint conditions,respectively,and the global optimization model of the CNN architecture search is established.Next,the simulated annealing(SA)algorithm is used as the search strategy to search out the lightweight and high accuracy STIIARM directly.After that,based on the three principles of similar block structure,the same corresponding channel number,and the minimum computational complexity,the more lightweight student model is designed,and the FSP matrix pairing between the NAS model and student model is completed.Finally,by minimizing the loss between the FSP matrix pairs of the NAS model and student model,the student model’s weight adjustment is completed.Thus the ultra-lightweight and high accuracy STIIARM is obtained.The proposed method’s effectiveness is verified by the simulation experiments on the ISAR image dataset of five types of space targets.

Cephalopods Classification Using Fine Tuned Lightweight Transfer Learning Models

Cephalopods identification is a formidable task that involves hand inspection and close observation by a malacologist.Manual observation and iden-tification take time and are always contingent on the involvement of experts.A system is proposed to alleviate this challenge that uses transfer learning techni-ques to classify the cephalopods automatically.In the proposed method,only the Lightweight pre-trained networks are chosen to enable IoT in the task of cephalopod recognition.First,the efficiency of the chosen models is determined by evaluating their performance and comparing thefindings.Second,the models arefine-tuned by adding dense layers and tweaking hyperparameters to improve the classification of accuracy.The models also employ a well-tuned Rectified Adam optimizer to increase the accuracy rates.Third,Adam with Gradient Cen-tralisation(RAdamGC)is proposed and used infine-tuned models to reduce the training time.The framework enables an Internet of Things(IoT)or embedded device to perform the classification tasks by embedding a suitable lightweight pre-trained network.Thefine-tuned models,MobileNetV2,InceptionV3,and NASNet Mobile have achieved a classification accuracy of 89.74%,87.12%,and 89.74%,respectively.Thefindings have indicated that thefine-tuned models can classify different kinds of cephalopods.The results have also demonstrated that there is a significant reduction in the training time with RAdamGC.

Brittleness Generation Mechanism and Failure Model of High Strength Lightweight Aggregate Concrete

The brittleness generation mechanism of high strength lightweight aggregate con-crete(HSLWAC) was presented, and it was indicated that lightweight aggregate was the vulnerable spot, initiating brittleness. Based on the analysis of the brittleness failure by the load-deflection curve, the brittleness presented by HSLWAC was more prominent compared with ordinary lightweight aggregate concrete of the same strength grade. The model of brittleness failure was also established.

基于像素差异度注意力机制的轻量化YOLOv5行人检测算法

针对实时行人检测场景存在遮挡、形态姿势不同的行人目标,YOLOv5模型对于这些目标检测有明显的漏检问题,提出一种像素差异度注意力机制(pixel difference attention,PDA),不同于传统的通道注意力机制用全局均值池化(global average pooling,GAP)、全局最大值池化(global max pooling,GMP)来概括整张特征图的信息,全局池化将空间压缩成一个值来表征整个通道,造成了空间信息的流失,PDA将空间信息沿高和宽分别压缩,并将其分别与通道信息联系起来做注意力加权操作,同时提出一种新的通道描述指标表征通道信息,增强空间信息与通道信息的交互,使模型更容易关注到综合了空间和通道维度上的特征图的重要信息,在主干网络末端插入PDA后使模型平均精度(mean average precision,mAP)0.5提升了2.4个百分点,mAP0.5:0.95提升了4.4个百分点;针对实时检测场景的部署和检测速度要求模型拥有较少的参数量和计算量,因此提出了新的轻量化特征提取模块AC3代替原YOLOv5模型中的C3模块,该模块使插入PDA后的改进模型在精度仅仅损失0.2个百分点的情况下,参数量(parameters,Param.)减少了20%左右,浮点运算量(giga floating-point operations,GFLOPs)减少了30%左右。实验结果表明,最终的改进模型比YOLOv5s原模型在VOC行人数据集上mAP0.5提升了2.2个百分点,mAP0.5:0.95提升了3.1个百分点,且参数量减少了20%左右,浮点运算量减少了30%左右,在GTX1050上的检测速度(frames per second,FPS)提升了4。

Identification of Weather Phenomena Based on Lightweight Convolutional Neural Networks

Weather phenomenon recognition plays an important role in the field of meteorology.Nowadays,weather radars and weathers sensor have been widely used for weather recognition.However,given the high cost in deploying and maintaining the devices,it is difficult to apply them to intensive weather phenomenon recognition.Moreover,advanced machine learning models such as Convolutional Neural Networks(CNNs)have shown a lot of promise in meteorology,but these models also require intensive computation and large memory,which make it difficult to use them in reality.In practice,lightweight models are often used to solve such problems.However,lightweight models often result in significant performance losses.To this end,after taking a deep dive into a large number of lightweight models and summarizing their shortcomings,we propose a novel lightweight CNNs model which is constructed based on new building blocks.The experimental results show that the model proposed in this paper has comparable performance with the mainstream non-lightweight model while also saving 25 times of memory consumption.Such memory reduction is even better than that of existing lightweight models.

Thermal Infrared Salient Human Detection Model Combined with Thermal Features in Airport Terminal

Target detection in low light background is one of the main tasks of night patrol robots for airport terminal.However,if some algorithms can run on a robot platform with limited computing resources,it is difficult for these algorithms to ensure the detection accuracy of human body in the airport terminal. A novel thermal infrared salient human detection model combined with thermal features called TFSHD is proposed. The TFSHD model is still based on U-Net,but the decoder module structure and model lightweight have been redesigned. In order to improve the detection accuracy of the algorithm in complex scenes,a fusion module composed of thermal branch and saliency branch is added to the decoder of the TFSHD model. Furthermore,a predictive loss function that is more sensitive to high temperature regions of the image is designed. Additionally,for the sake of reducing the computing resource requirements of the algorithm,a model lightweight scheme that includes simplifying the encoder network structure and controlling the number of decoder channels is adopted. The experimental results on four data sets show that the proposed method can not only ensure high detection accuracy and robustness of the algorithm,but also meet the needs of real-time detection of patrol robots with detection speed above 40 f/s.

Using an improved lightweight YOLOv8 model for real-time detection of multi-stage apple fruit in complex orchard environments

For the purpose of monitoring apple fruits effectively throughout the entire growth period in smart orchards.A lightweight model named YOLOv8n-ShuffleNetv2-Ghost-SE was proposed.The ShuffleNetv2 basic modules and down-sampling modules were alternately connected,replacing the Backbone of YOLOv8n model.The Ghost modules replaced the Conv modules and the C2fGhost modules replaced the C2f modules in the Neck part of the YOLOv8n.ShuffleNetv2 reduced the memory access cost through channel splitting operations.The Ghost module combined linear and non-linear convolutions to reduce the network computation cost.The Wise-IoU(WIoU)replaced the CIoU for calculating the bounding box regression loss,which dynamically adjusted the anchor box quality threshold and gradient gain allocation strategy,optimizing the size and position of predicted bounding boxes.The Squeeze-and-Excitation(SE)was embedded in the Backbone and Neck part of YOLOv8n to enhance the representation ability of feature maps.The algorithm ensured high precision while having small model size and fast detection speed,which facilitated model migration and deployment.Using 9652 images validated the effectiveness of the model.The YOLOv8n-ShuffleNetv2-Ghost-SE model achieved Precision of 94.1%,Recall of 82.6%,mean Average Precision of 91.4%,model size of 2.6 MB,parameters of 1.18 M,FLOPs of 3.9 G,and detection speed of 39.37 fps.The detection speeds on the Jetson Xavier NX development board were 3.17 fps.Comparisons with advanced models including Faster R-CNN,SSD,YOLOv5s,YOLOv7‑tiny,YOLOv8s,YOLOv8n,MobileNetv3_small-Faster,MobileNetv3_small-Ghost,ShuflleNetv2-Faster,ShuflleNetv2-Ghost,ShuflleNetv2-Ghost-CBAM,ShuflleNetv2-Ghost-ECA,and ShuflleNetv2-Ghost-CA demonstrated that the method achieved smaller model and faster detection speed.The research can provide reference for the development of smart devices in apple orchards.

基于深度学习的轻量化炮孔智能检测方法

在隧道(巷道)钻爆法施工过程中,智能装药可以取代人工作业,减少装药作业中危险事故的发生。然而,隧道中光线条件差、炮孔目标小和掌子面裂隙等因素会造成智能装药时炮孔的错检和漏检,同时车载计算机有限的算力也是制约炮孔识别大模型使用的难点。MCIW-2深度学习模型,可以解决在隧道掘进作业环境中的高精度炮孔检测和实时性部署问题。模型根据采集到的炮孔图像尺寸特征采取自适应锚框聚类算法优化检测框的长宽比尺寸参数;采用了具有动态非单调聚焦机制的损失函数WIoU(Wise Intersection over Union),通过优化边框回归的损失应对低质量炮孔图片的挑战实现了高精度检测;采用了MobileNetv3-Small网络与CBAM(Convolutional Block Attention Module)注意力机制构建了主干网络结构,减少了模型参数保证了检测准确率,满足车载设备的轻量化部署需求。经实验证明,MCIW-2模型在炮孔识别精确率方面达到了96.18%,检测速度达到了59 fps。与基准YOLO(You Only Look Once)系列目标检测模型文件最小的模型相比,所构建的轻量化炮孔智能检测模型减小了75.86%,模型文件仅为2.80 Mb,优于YOLO系列的基准目标检测模型。使用MCIW-2深度学习模型对工作面现场视频进行测试,实现了快速、精确地检测炮孔,测试结果表明,该模型适用于智能装药工程的轻量化部署需求,具有良好的适应性,在综合性能方面具有显著优势。

结合轻量化与多尺度融合的交通标志检测算法

交通标志检测在自动驾驶领域具有重要的应用价值,及时准确地检测交通目标对提高驾驶安全性和预防交通事故具有重要意义。针对交通标志尺寸小,易受遮挡,在复杂环境下容易出现漏检、错检等问题,在YOLOv8的结构基础上提出一种结合轻量化与多尺度融合的交通标志检测网络架构M-YOLO,构建M-YOLOs模型来应对高精度需求的检测任务,并调整网络深度得到更轻量化的M-YOLOn模型来解决不同环境下的检测需求。首先针对交通标志目标尺寸小、图像特征流失的问题,通过增加小目标检测层,保留更多的特征信息,提高网络对于小目标的特征学习能力。提出高效多尺度特征金字塔融合网络MPANet,将浅层特征图进行降维与跳跃连接,从而融合更多的图像特征信息。然后提出融合稀疏注意力和空间注意力的BRSA注意力模块,有效提取全局和局部的位置信息,减少复杂背景下对于关键信息的干扰。最后设计两种轻量高效的BBot模块和C2fGhost模块,以提高模型运算速度并减少参数量。实验结果表明,M-YOLO相较于YOLOv8,参数量降低约1/3。在TT100K数据集和GTSDB数据集上,M-YOLOs检测精度分别提升了9.7和2.1个百分点,M-YOLOn检测精度分别提升了14.5和2.6个百分点,在轻量化的同时具备更高的检测效果。M-YOLO架构解决了浅层特征图在特征提取过程中信息丢失的问题,并显著降低模型特征提取过程中冗余的计算开销,在实景采集的数据集上证实效果有效,表明在交通标志检测任务中具有应用价值。

基于改进MobileNet V3的矿物智能识别模型

针对当前矿物识别领域存在的精度不佳、适应性差、携带不便等问题,提出了一种基于改进MobileNet V3的矿物智能识别模型(CA-MobileNet V3)。为获得研究所需的有效数据集,通过由mindat. org网站和自行拍摄方式获取的矿物图像创建了一个包含19种矿物的数据集,对其进行数据增强处理,并按照8:1:1的比例划分为训练集、验证集和测试集。为提升模型对图像信息的特征提取能力,引入协调注意力机制,用以替代轻量型MobileNet V3模型的原始SE注意力机制,以提高矿物识别准确率。最后,采用迁移学习方法预训练CA-MobileNet V3模型,以加速模型收敛、提高泛化能力、避免过拟合。在训练过程中,将CA-MobileNet V3与mobilenet v3、MobileNet V3、ShuffleNet V2、Efficient Net V2等模型进行了性能比较。结果表明:各迁移模型均展现出显著的收敛速度优势,而CA-MobileNet V3矿物智能识别模型的Top1-准确率、Top2-准确率、f_1-score值分别达到93.90%、98.58%和93.89%,在所有模型中效果最佳,且模型大小仅为4.61 MB,属于轻量化模型。为验证模型有效性,t-SNE可视化分析被用于不同模型的识别效果比较,进一步印证了CA-MobileNet V3模型的优越性。

面向边缘计算的矿区障碍检测模型研究

近年来,随着矿用卡车自动驾驶技术的兴起,使得矿区道路行车障碍物检测变得至关重要,基于深度学习的目标检测模型应用于矿区道路障碍检测取得了显著的效果,为矿用卡车自动驾驶技术的完善提供了可能。为解决现有模型应用于矿区障碍物检测,往往存在算法庞大与部署成本较高的问题,提出一种面向边缘计算平台的改进YOLOv8矿区道路障碍检测模型,该模型针对资源有限的边缘计算设备进行优化部署,以实现对障碍物的快速、精准检测。该模型在特征提取阶段,引入深度可分离卷积和通道注意力机制,提高模型对障碍物整体特征提取能力,从而提升对不同尺寸障碍物的检测精度;特征融合阶段采用BiFPN网络结构,轻量化颈部网络并自适应地调整融合权重,减少冗余信息,提高特征的表达能力;使用局部卷积PConv对检测头进行重新设计,减少网络参数量以提高检测效率;最后,通过引入Inner-CIoU函数对边界框损失进行优化,加快模型收敛速度并提升边界框定位效果。实验结果显示,该网络在所使用的矿区障碍物数据集上,mAP@0.5仅下降0.05的前提下,模型参数减少了44%,推理时间缩短了34%。相比其他轻量型检测网络,该模型在实验硬件设备上的检测速度更快,且在精度和轻量化之间实现了更好的平衡,为障碍物检测模型的实际部署提供了可行方案。

IDD-YOLOv7:一种用于输电线路绝缘子多缺陷的轻量化检测方法

YOLO目标检测算法是当前基于图像的输电线路绝缘子缺陷检测的主流方法,然而现有模型复杂度较大,亟需合理有效的参数压缩方法作为前提条件,来为解决无人机边缘设备部署的困境问题奠定基础;同时,无人机航拍的绝缘子缺陷图像背景复杂、缺陷尺寸较小,容易出现误检、漏检等问题。为此,提出了一种用于输电线路绝缘子多缺陷检测的Insulator Defect Detection-YOLOv7(IDD-YOLOv7)模型,以降低模型复杂度,提高模型鲁棒性。首先,在多尺度特征融合的过程中加入坐标注意力(Coordinate Attention)机制,抑制复杂背景的干扰,提升模型对小目标的全局感知能力;之后,设计C3GhostNetV2模块,用于捕获不同空间像素之间的远程依赖性,在增强模型表达能力的同时降低模型的参数量和浮点运算量;最后,提出Focal-CIoU损失函数,提高模型高质量anchor的贡献,加快模型的收敛速度。实验结果表明,本文方法与基线模型相比mAP^(50)提升了3.8%,查准率和召回率分别提升了1.7%和7.6%,参数量和浮点运算量分别下降了18.3%和14.0%,绝缘子自爆、破损、闪络缺陷的AP^(50)分别提升了0.8%、4.5%、6.3%。

改进YOLOv8n的花生品质检测方法

花生品质筛选在农业生产和食品安全中具有重要意义。针对传统花生品质筛选方法效率低的问题,提出改进YOLOv8n算法的轻量化花生品质检测模型LE-YOLO(lightweight and efficient)。提出一种分组重序颈部模块(grouped shuffling bottleneck,GSBottleneck),增加了模型非线性拟合能力,减少了模型推理时间;设计了残差分组重序模块(residual group shuffling block,ResGSBlock),并结合GSConv(grouped shuffle convolution)构建轻量颈部网络(lightweight neck,LW-Neck),减少了模型计算成本,提升了模型推理速度;提出自适应特征优化模块(adaptive feature optimization block,AFOB),增强了通道间信息交互和模型表征能力。在DW花生数据集上进行实验验证,相较于YOLOv8n算法,LE-YOLO的计算量减少了1 GFlops,FPS提升了25%,平均精度均值mAP@0.5达到了98%,验证了该算法在检测精度和速度上的良好性能,为花生品质筛选提供了一种有效的方法。

视觉深度学习模型压缩加速综述

近年来,深度学习模型规模越来越大,在嵌入式设备等资源受限环境中,大规模视觉深度学习模型难以实现高效推理部署。模型压缩加速可以有效解决该挑战。尽管已经出现相关工作的综述,但相关工作集中在卷积神经网络的压缩加速,缺乏对视觉Transformer模型压缩加速方法的整理和对比分析。因此,本文以视觉深度学习模型压缩技术为核心,对卷积神经网络和视觉Transformer模型2个最重要的视觉深度模型进行了相关技术手段的整理,并对技术热点和挑战进行了总结和分析。本文旨在为研究者提供一个全面了解模型压缩和加速领域的视角,促进深度学习模型压缩加速技术的发展。

基于改进YOLOv7的钢轨缺陷检测方法

针对铁路轨道缺陷检测精度低,漏检率高,实时性不足的问题,本文提出了一种基于YOLO-FCA的钢轨缺陷检测算法。首先,将YOLOv7的主干网络替换成FasterNet轻量网络,并加入CloAttention注意力模块,减少参数量和计算负载的同时提高缺陷检测的精度。其次,提出MS-ASFF,获取高层语义信息和保留低层详细特征,增强模型检测的准确性和鲁棒性。最后,在不影响精度的情况下进行网络剪枝,使模型更加轻量化,极大地提升了模型的检测速度。在公共数据集上进行实验,结果表明,YOLO-FCA相比原始模型YOLOv7模型的mAP提高了4.1%,达到80.7%,同时检测速度提升了38.5%,达到212.5 FPS。实验结果表明,YOLO-FCA能够高效且准确地定位检测钢轨缺陷。

基于改进轻量级沙漏模型的2D单人姿态估计研究与应用

提出一种基于改进轻量级沙漏模型的2D单人人体姿态估计方法。使用逆残差卷积来构建改进的轻量级沙漏模型,从而降低参数数量与计算量,使用多尺度特征融合以提高轻量级模型在遮挡情况下的关键点检测能力。引入知识蒸馏方法,使得改进的模型在略微降低检测准确度时,能大幅降低训练和部署所需要的计算资源。MPII数据集和实际应用中的检测结果表明,改进的轻量级沙漏模型能有效检测人体骨骼关键点,实时性好、鲁棒性强,能在一定程度上克服遮挡问题。

基于轻量化YOLO v8s-GD的自然环境下百香果快速检测模型

为了提高百香果检测精度,并将深度学习模型部署在移动平台上,实现快速实时推理,本文提出一种基于改进YOLO v8s的轻量化百香果检测模型(YOLO v8s-GD)。使用聚集和分发机制(GD)替换颈部特征融合网络,提高模型对百香果图像特征信息跨层融合能力和模型泛化能力;通过基于层自适应幅度的剪枝(LAMP)修剪模型,损失一定精度换取减小模型体积,减少模型参数量,以实现在嵌入式设备上快速检测;运用知识蒸馏学习策略弥补因剪枝而损失的检测精度,提高模型检测性能。实验结果表明,对于自然环境下采集的百香果数据集,改进后模型参数量和内存占用量相比原YOLO v8s基线模型分别降低63.88%和62.10%,精确率(Precision)和平均精度(AP)相较于原模型分别提高0.9、2.3个百分点,优于其他对比模型。在Jetson Nano和Jetson Tx2嵌入式设备上实时检测帧率(FPS)分别为5.78、19.38 f/s,为原模型的1.93、1.24倍。因此,本文提出的改进后模型能够有效检测复杂环境下百香果目标,为实际场景中百香果自动采摘等移动端检测设备部署和应用提供理论和技术支持。

基于边塌陷减面的实景三维模型轻量化技术

实景三维模型由于其丰富的场景展现能力,广泛应用在数字孪生和地理测绘等领域。然而,丰富的三维场景和细节所包含的数据量十分庞大,给实景三维模型的存储、传输、渲染与展示带来了极大的挑战。针对上述问题,本文提出了一种面向实景三维模型的轻量化处理方法,首先引入模型预处理技术,去除模型噪音和非流行边;然后通过边塌陷减面的轻量化算法,精简模型拓扑结构;最后加入反转检测算法,防止边塌陷过程中出现面反转的情况。对张家界景区4个真实场景的测试结果表明,该技术可以在保留模型整体外观和场景细节的基础上,压缩至原始模型大小的3.7%~10.9%,使得复杂场景的实景三维模型能够在计算机中更加快速真实地反映或显示世界的地理地貌或城市建筑。

基于边缘计算的轻量化识别方法

“新零售”模式的出现,对传统零售业的转型以及提升用户消费体验具有重要意义。然而,目前市场上的无人水果秤大多存在一些问题,如识别率低、模型结构复杂、部署困难、模型推理实时性差等。针对这些问题,提出一种基于边缘计算的轻量化识别方法。选用MobileNext作为主干网络,引入轻量型的注意力模块CBAM改进MobileNext中的SandGlass模块。利用Ghost模块替换SandGlass模块中的标准1×1卷积,以压缩模型的参数量和运算量。在此基础上,使用迁移学习的策略搭配NAdam优化器训练改进后的MobileNext模型,进一步提高模型的识别精度。在Fruit Recognition数据集上的实验结果表明,该方法在水果识别任务中达到了98.95%的识别准确率,优于原MobileNext、MobileNetV2和EfficientNet-B0等轻量级模型。相较于原MobileNext模型,改进后的MobileNext模型识别准确率提高了1.17个百分点,参数量仅为1.775×106,推理时间仅为16.5 ms。在实际的零售场景中,所提方法只需很小的参数量和运算量就能实现较好的识别效果,并能够部署在边缘设备上。