Bidirectional parallel multi-branch convolution feature pyramid network for target detection in aerial images of swarm UAVs

In this paper,based on a bidirectional parallel multi-branch feature pyramid network(BPMFPN),a novel one-stage object detector called BPMFPN Det is proposed for real-time detection of ground multi-scale targets by swarm unmanned aerial vehicles(UAVs).First,the bidirectional parallel multi-branch convolution modules are used to construct the feature pyramid to enhance the feature expression abilities of different scale feature layers.Next,the feature pyramid is integrated into the single-stage object detection framework to ensure real-time performance.In order to validate the effectiveness of the proposed algorithm,experiments are conducted on four datasets.For the PASCAL VOC dataset,the proposed algorithm achieves the mean average precision(mAP)of 85.4 on the VOC 2007 test set.With regard to the detection in optical remote sensing(DIOR)dataset,the proposed algorithm achieves 73.9 mAP.For vehicle detection in aerial imagery(VEDAI)dataset,the detection accuracy of small land vehicle(slv)targets reaches 97.4 mAP.For unmanned aerial vehicle detection and tracking(UAVDT)dataset,the proposed BPMFPN Det achieves the mAP of 48.75.Compared with the previous state-of-the-art methods,the results obtained by the proposed algorithm are more competitive.The experimental results demonstrate that the proposed algorithm can effectively solve the problem of real-time detection of ground multi-scale targets in aerial images of swarm UAVs.

An Improved Data-Driven Topology Optimization Method Using Feature Pyramid Networks with Physical Constraints

Deep learning for topology optimization has been extensively studied to reduce the cost of calculation in recent years.However,the loss function of the above method is mainly based on pixel-wise errors from the image perspective,which cannot embed the physical knowledge of topology optimization.Therefore,this paper presents an improved deep learning model to alleviate the above difficulty effectively.The feature pyramid network(FPN),a kind of deep learning model,is trained to learn the inherent physical law of topology optimization itself,of which the loss function is composed of pixel-wise errors and physical constraints.Since the calculation of physical constraints requires finite element analysis(FEA)with high calculating costs,the strategy of adjusting the time when physical constraints are added is proposed to achieve the balance between the training cost and the training effect.Then,two classical topology optimization problems are investigated to verify the effectiveness of the proposed method.The results show that the developed model using a small number of samples can quickly obtain the optimization structure without any iteration,which has not only high pixel-wise accuracy but also good physical performance.

Multi-scale object detection by top-down and bottom-up feature pyramid network

While moving ahead with the object detection technology, especially deep neural networks, many related tasks, such as medical application and industrial automation, have achieved great success. However, the detection of objects with multiple aspect ratios and scales is still a key problem. This paper proposes a top-down and bottom-up feature pyramid network(TDBU-FPN),which combines multi-scale feature representation and anchor generation at multiple aspect ratios. First, in order to build the multi-scale feature map, this paper puts a number of fully convolutional layers after the backbone. Second, to link neighboring feature maps, top-down and bottom-up flows are adopted to introduce context information via top-down flow and supplement suboriginal information via bottom-up flow. The top-down flow refers to the deconvolution procedure, and the bottom-up flow refers to the pooling procedure. Third, the problem of adapting different object aspect ratios is tackled via many anchor shapes with different aspect ratios on each multi-scale feature map. The proposed method is evaluated on the pattern analysis, statistical modeling and computational learning visual object classes(PASCAL VOC)dataset and reaches an accuracy of 79%, which exhibits a 1.8% improvement with a detection speed of 23 fps.

PAN-DeSpeck:A Lightweight Pyramid and Attention-Based Network for SAR Image Despeckling

SAR images commonly suffer fromspeckle noise,posing a significant challenge in their analysis and interpretation.Existing convolutional neural network(CNN)based despeckling methods have shown great performance in removing speckle noise.However,these CNN-basedmethods have a fewlimitations.They do not decouple complex background information in amulti-resolutionmanner.Moreover,they have deep network structures thatmay result in many parameters,limiting their applicability tomobile devices.Furthermore,extracting key speckle information in the presence of complex background is also a major problem with SAR.The proposed study addresses these limitations by introducing a lightweight pyramid and attention-based despeckling(PAN-Despeck)network.The primary objective is to enhance image quality and enable improved information interpretation,particularly on mobile devices and scenarios involving complex backgrounds.The PAN-Despeck network leverages domainspecific knowledge and integrates Gaussian Laplacian image pyramid decomposition for multi-resolution image analysis.By utilizing this approach,complex background information can be effectively decoupled,leading to enhanced despeckling performance.Furthermore,the attention mechanism selectively focuses on key speckle features and facilitates complex background removal.The network incorporates recursive and residual blocks to ensure computational efficiency and accelerate training speed,making it lightweight while maintaining high performance.Through comprehensive evaluations,it is demonstrated that PAN-Despeck outperforms existing image restoration methods.With an impressive average peak signal-to-noise ratio(PSNR)of 28.355114 and a remarkable structural similarity index(SSIM)of 0.905467,it demonstrates exceptional performance in effectively reducing speckle noise in SAR images.The source code for the PAN-DeSpeck network is available on GitHub.

Deep Pyramidal Residual Network for Indoor-Outdoor Activity Recognition Based on Wearable Sensor

Recognition of human activity is one of the most exciting aspects of time-series classification,with substantial practical and theoretical impli-cations.Recent evidence indicates that activity recognition from wearable sensors is an effective technique for tracking elderly adults and children in indoor and outdoor environments.Consequently,researchers have demon-strated considerable passion for developing cutting-edge deep learning sys-tems capable of exploiting unprocessed sensor data from wearable devices and generating practical decision assistance in many contexts.This study provides a deep learning-based approach for recognizing indoor and outdoor movement utilizing an enhanced deep pyramidal residual model called Sen-PyramidNet and motion information from wearable sensors(accelerometer and gyroscope).The suggested technique develops a residual unit based on a deep pyramidal residual network and introduces the concept of a pyramidal residual unit to increase detection capability.The proposed deep learning-based model was assessed using the publicly available 19Nonsens dataset,which gathered motion signals from various indoor and outdoor activities,including practicing various body parts.The experimental findings demon-strate that the proposed approach can efficiently reuse characteristics and has achieved an identification accuracy of 96.37%for indoor and 97.25%for outdoor activity.Moreover,comparison experiments demonstrate that the SenPyramidNet surpasses other cutting-edge deep learning models in terms of accuracy and F1-score.Furthermore,this study explores the influence of several wearable sensors on indoor and outdoor action recognition ability.

FROM UNWEIGHTED TO WEIGHTED GENERALIZED FAREY ORGANIZED TREE AND THE PYRAMID NETWORKS

Generalized Farey tree network(GFTN)and generalized Farey organized pyramid network(GFOPN)model are proposed,and their topological characteristics are studied by both theoreticalanalysis and numerical simulations,which are in good accordance with each other.Then weightedGFTN is studied using cumulative distributions of its Farey number value,edge weight,and nodestrength.These results maybe helpful for future theoretical develonment of hvbrid models.

结合主动光源和改进YOLOv5s模型的夜间柑橘检测方法

【目的】解决夜间环境下遮挡和较小柑橘难以准确识别的问题,实现采摘机器人全天候智能化作业。【方法】提出一种结合主动光源的夜间柑橘识别方法。首先,通过分析主动光源下颜色特征不同的夜间柑橘图像,选择最佳的光源色并进行图像采集。然后,提出一种夜间柑橘检测模型BI-YOLOv5s,该模型采用双向特征金字塔网络(Bi-FPN)进行多尺度交叉连接和加权特征融合,提高对遮挡和较小果实的识别能力;引入Coordinate attention(CA)注意力机制模块,进一步加强对目标位置信息的提取;采用融入Transformer结构的C3TR模块,在减少计算量的同时更好地提取全局信息。【结果】本文提出的BI-YOLOv5s模型在测试集上的精准率、召回率、平均准确率分别为93.4%、92.2%和97.1%,相比YOLOv5s模型分别提升了3.2、1.5和2.3个百分点。在所采用的光源色环境下,模型对夜间柑橘识别的正确率为95.3%,相比白光环境下提高了10.4个百分点。【结论】本文提出的方法对夜间环境下遮挡和小目标柑橘的识别具有较高的准确性,可为夜间果蔬智能化采摘的视觉精准识别提供技术支持。

基于跨模态注意力融合的煤炭异物检测方法

为解决原煤智能化洗选过程中煤流中夹杂的异物对比度低、相互遮挡导致异物图像检测时特征提取不充分的问题,提出了一种基于跨模态注意力融合的煤炭异物检测方法。通过引入Depth图像构建RGB图像与Depth图像的双特征金字塔网络(DFPN),采用浅层的特征提取策略提取Depth图像的低级特征,用深度边缘与深度纹理等基础特征辅助RGB图像深层特征,以有效获得2种特征的互补信息,从而丰富异物特征的空间与边缘信息,提高检测精度;构建了基于坐标注意力与改进空间注意力的跨模态注意力融合模块(CAFM),以协同优化并融合RGB特征与Depth特征,增强网络对特征图中被遮挡异物可见部分的关注度,提高被遮挡异物检测精度;使用区域卷积神经网络(R-CNN)输出煤炭异物的分类、回归与分割结果。实验结果表明:在检测精度方面,该方法的AP相较两阶段模型中较优的Mask transfiner高3.9%;在检测效率方面,该方法的单帧检测时间为110.5 ms,能够满足异物检测实时性需求。基于跨模态注意力融合的煤炭异物检测方法能够以空间特征辅助色彩、形状与纹理等特征,准确识别煤炭异物之间及煤炭异物与输送带之间的差异,从而有效提高对复杂特征异物的检测精度,减少误检、漏检现象,实现复杂特征下煤炭异物的精确检测与像素级分割。

Intelligent identification of oceanic eddies in remote sensing data via Dual-Pyramid UNet

海洋涡旋是大洋中重要的组成部分,对海洋能量和物质的输送至关重要.海洋涡旋的检测和表征无论是对于海洋气象学,海洋声学还是海洋生物学等领域都具有重要的研究价值.本文基于UNet架构,并结合金字塔分割注意力(PSA)模块和空洞空间卷积池化金字塔(ASPP)构造了Dual-Pyramid UNet模型,以平面异常和海表面温度数据中进行海洋涡旋的识别.实验在北大西洋和南大西洋两个涡旋活跃区域进行并选用多个评价指标对识别结果进行评价以证明模型的优异性能.

基于YOLOv5s和超声图像的儿童肠套叠特征检测模型

为帮助医生快速寻找到儿童腹部超声中肠套叠的病变特征并实现肠套叠超声诊后数据的快速质检,文章将目标检测算法应用于儿童腹部超声图像检测肠套叠“同心圆”征.首先探索了基于YOLOv5s的儿童肠套叠检测模型,发现该模型检测肠套叠“同心圆”征的精确度、召回率、F 1分数、mAP@0.5、FPS以及参数量等方面均优于Faster RCNN.进一步,为解决肉眼难以观察的“同心圆”征的检测问题,使用双向特征金字塔网络,并将注意力机制加入YOLOv5s网络,形成基于YOLOv5s_BiFPN_SE框架的儿童肠套叠“同心圆”征检测模型.该模型检测的精确率、召回率、F 1分数、mAP@0.5分别达到了91.33%、90.73%、91.03%、88.77%,性能更优于YOLOv5s.

基于YOLOv3的金属表面缺陷检测研究

为了解决金属表面缺陷检测的漏检、误检等问题,提出了一种改进YOLOv3算法。首先,使用动态激活函数替换主干特征提取网络中所有残差块的激活函数,并加入了混合注意力机制,强化其对复杂缺陷目标的特征提取能力。然后,在特征金字塔网络部分新增一个104×104的特征层,并将浅层网络与深层网络进行逐层特征融合,增强算法对小缺陷目标检测的敏感性。最后,利用K-Means++聚类算法替换K-Means聚类算法,筛选出适用于金属表面缺陷检测的最优先验框尺寸,使目标定位更加准确。实验结果表明,改进YOLOv3算法的每秒检测帧数(frames per second,FPS)可达到32.3,平均精度均值(mean average precision,mAP)可达到78.69%,检测性能得到了明显提升。

基于改进YOLOv5s的轻量级绝缘子缺失检测

针对现有绝缘子缺失检测模型计算复杂度高和小目标难以检测等问题,提出一种基于改进的YOLOv5s轻量级检测模型。首先,移除主干网络中的C3模块来减少模型的参数量。其次,在多尺度特征融合网络中引入卷积块注意力机制来提高复杂背景下模型的特征提取能力。同时,采用加权双向特征金字塔网络结构对特征进行双向跨尺度加权融合,提升网络在遮挡物、相似目标干扰下目标的检测性能。最后,选用SIoU损失函数提升网络的收敛速度和检测精度。实验结果表明,所提模型的平均精准率为96.8%,浮点运算数为2.8 GFLOPS,而原始YOLOv5s在保证97.4%的平均精准率下的浮点运算数为16.3 GFLOPS。相较于原始模型,所提模型对小目标、遮挡目标以及模糊等场景有着较强的鲁棒性,且在保证近似检测精度的同时极大减少了计算量。

基于深度学习的油田在线视频目标检测

油田背景复杂多变,摄像头悬挂较高,导致物体在监控画面中的比例较小,加大了检测难度。从油田实际场景出发,深入研究了SSD算法检测小目标准确率比较低的问题并对其改进,提出了RP-SSD算法,通过在特征金子塔中增加上采样模块和预测模块,更好地融合前后卷积层产生的特征图,并使用空洞卷积扩大了前面卷积层的感受野,提高了对小目标检测的准确率。采用Pascal VOC验证改进算法的有效性,同时选取了faster R-CNN、SSD300、DSSD321作为对照试验。试验结果表明,RP-SSD在小目标检测方面性能显著提高,可以达到实时检测的要求。

基于超分辨率图像重建的轻量化目标检测算法研究

利用面向边缘的卷积模块、像素注意力机制和重参数化技术使超分辨率重建算法图像分辨率得到提升,使图像特征细节表现更为优越;利用YOLOv4目标检测算法并结合Focus结构、双向特征金字塔网络和轻量级子通道注意力机制,提高中、低分辨率图像目标检测精度。经实验研究,基于超分辨率重建的轻量化目标检测算法对图像目标具有较好的检测效果,有效提升了图像的检测精度,对提升图像中的细小目标检测精度具有一定的参考意义。

基于Transformer的跨尺度交互学习伪装目标检测

伪装目标检测(COD)旨在精确且高效地检测出与背景高度相似的伪装物体,其方法可为物种保护、医学病患检测和军事监测等领域提供助力,具有较高的实用价值.近年来,采用深度学习方法进行伪装目标检测成为一个比较新兴的研究方向.但现有大多数COD算法都是以卷积神经网络(CNN)作为特征提取网络,并且在结合多层次特征时,忽略了特征表示和融合方法对检测性能的影响.针对基于卷积神经网络的伪装目标检测模型对被检测目标的全局特征提取能力较弱问题,提出一种基于Transformer的跨尺度交互学习伪装目标检测方法.该模型首先提出了双分支特征融合模块,将经过迭代注意力的特征进行融合,更好地融合高低层特征;其次引入了多尺度全局上下文信息模块,充分联系上下文信息增强特征;最后提出了多通道池化模块,能够聚焦被检测物体的局部信息,提高伪装目标检测准确率.在CHAMELEON、CAMO以及COD10K数据集上的实验结果表明,与当前主流的伪装物体检测算法相比较,该方法生成的预测图更加清晰,伪装目标检测模型能取得更高精度.

基于金字塔池化网络的质子交换膜燃料电池气体扩散层组分推理方法

针对质子交换膜燃料电池气体扩散层(gas diffusion layer composition,GDL)形貌划分与制备工艺改进问题,提出了一种基于金字塔池化网络(pyramid scene parsing network,PSPNet)与多层感知器(multi-layer perception,MLP)的气体扩散层组分识别与比例推理方法:首先将带标签的气体扩散层扫描电镜(scanning electron microscope,SEM)图片输入神经网络,得到特征图;得到的图像特征层进入金字塔池化模块后,获取SEM图像的深层和浅层特征;随后将深层和浅层特征图层融合输入全卷积网络(fully convolutional network,FCN)模块,得到预测图像;最后统计各个组分上的像素点比例,通过MLP完成组分比例推理。结果表明:所提方法组分识别像素准确率达81.24%;在5%偏差范围内,比例推理准确率为88.89%。该方法解决了气体扩散层多组分无法区分、比例无法获知的问题,可有效应用于气体扩散层的质检、数值重构以及制备工艺改进。

基于改进DBNet和SVTR算法的连铸板坯号检测与识别

针对钢铁连铸产线板坯号识别字符区域小、光照变化复杂、板坯号图像质量差等问题,提出了一种基于深度学习的连铸板坯号检测与识别两阶段算法。首先,基于采集的连铸产线板坯图像,制备用于板坯号检测与识别的数据集;其次,在板坯号检测阶段,基于DBNet算法设计一种AD-PAN特征融合结构,以增强检测算法的多尺度特征融合能力和扩大感受野,提高板坯号定位精度;再次,在板坯号识别阶段,引入SPIN矫正网络和SVTR板坯号识别网络进行端到端训练,使其能够主动转换输入亮度,并改善字符间以及字符与背景间色彩失真的问题。最后,在自制的板坯号检测与识别数据集上进行了对比实验。实验结果表明,本研究提出的算法能够有效定位辊道上不同位置的板坯,并且在复杂背景下对板坯号进行鲁棒识别。其中,板坯号检测Hmean数值为97.92%,板坯号识别的准确率为97.33%,验证了本文所提算法具有较高的板坯号检测与识别精度。

基于双支路卷积网络的步态识别方法

针对步态识别易受拍摄视角、外观变化等影响的问题,提出一种基于双支路卷积网络的步态识别方法。首先,提出随机裁剪随机遮挡的数据增强方法RRDA(Restricted Random Data Augmentation),以扩展外观变化的数据样本,提高模型遮挡的鲁棒性;其次,采用结合注意力机制的两路复合卷积层(C-Conv)提取步态特征,一个分支通过水平金字塔映射(HPM)提取行人外观全局和最具辨识度的信息;另一分支通过多个并行的微动作捕捉模块(MCM)提取短时间的步态时空信息;最后,将两个分支的特征信息相加融合,再通过全连接层实现步态识别。基于平衡样本特征的区分能力和模型的收敛性构造联合损失函数,以加速模型的收敛。在CASIA-B步态数据集上进行实验,所提方法在3种行走状态下的平均识别率分别达到97.40%、93.67%和81.19%,均高于GaitSet方法、CapsNet方法、双流步态方法和GaitPart方法;在正常行走状态下比GaitSet方法的识别准确率提升了1.30个百分点,在携带背包状态下提升了2.87个百分点,在穿着外套状态下提升了10.89个百分点。实验结果表明,所提方法是可行、有效的。

食道病灶检测的多尺度细节增强金字塔网络

针对食道卢戈染色内窥镜(Lugol’s chromoendoscopy,LCE)检查图像中病变类间相似度高和类内尺度变化大等问题,提出了一种以Sparse R-CNN作为基底网络并搭载多尺度细节增强金字塔网络(multi-scale detail enhancement pyramid network,MDEPN)结构的多类食道病灶检测方法。为了改善Sparse R-CNN中的特征金字塔网络(feature pyramid network,FPN)结构在对多尺度特征进行融合时存在的信息丢失和语义差异问题,MDEPN结构首先使用Gabor调制卷积模块对不同尺度特征进行增强,利用Gabor对方向和尺度的强关注度提高了特征图中纹理信息的表达能力;其次使用方向通道池化模块提取不同尺度特征的局部特征方向相似性和局部与全局特征的相关性,减轻了不同尺度特征融合时的语义差异。在自建的多类食道LCE病灶数据集上进行测试,结果表明该方法的mAP0.50检测精度达到了65.0%,相同条件下,比基准模型Sparse R-CNN提升了2.4个百分点,并超过了对比的其余主流检测方法。所设计的MDEPN模块可作为一种独立的结构融入其他检测模型中以提升性能,具有一定的通用性。