Two-Layer Attention Feature Pyramid Network for Small Object Detection

Effective small object detection is crucial in various applications including urban intelligent transportation and pedestrian detection.However,small objects are difficult to detect accurately because they contain less information.Many current methods,particularly those based on Feature Pyramid Network(FPN),address this challenge by leveraging multi-scale feature fusion.However,existing FPN-based methods often suffer from inadequate feature fusion due to varying resolutions across different layers,leading to suboptimal small object detection.To address this problem,we propose the Two-layerAttention Feature Pyramid Network(TA-FPN),featuring two key modules:the Two-layer Attention Module(TAM)and the Small Object Detail Enhancement Module(SODEM).TAM uses the attention module to make the network more focused on the semantic information of the object and fuse it to the lower layer,so that each layer contains similar semantic information,to alleviate the problem of small object information being submerged due to semantic gaps between different layers.At the same time,SODEM is introduced to strengthen the local features of the object,suppress background noise,enhance the information details of the small object,and fuse the enhanced features to other feature layers to ensure that each layer is rich in small object information,to improve small object detection accuracy.Our extensive experiments on challenging datasets such as Microsoft Common Objects inContext(MSCOCO)and Pattern Analysis Statistical Modelling and Computational Learning,Visual Object Classes(PASCAL VOC)demonstrate the validity of the proposedmethod.Experimental results show a significant improvement in small object detection accuracy compared to state-of-theart detectors.

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.

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.

Dual Attention Based Feature Pyramid Network

Object detection could be recognized as an essential part of the research to scenarios such as automatic driving and pedestrian detection, etc. Among multiple types of target objects, the identification of small-scale objects faces significant challenges. We would introduce a new feature pyramid framework called Dual Attention based Feature Pyramid Network(DAFPN), which is designed to avoid predicament about multi-scale object recognition. In DAFPN, the attention mechanism is introduced by calculating the topdown pathway and lateral pathway, where the spatial attention, as well as channel attention, would participate, respectively, such that the pyramidal feature maps can be generated with enhanced spatial and channel interdependencies, which bring more semantical information for the feature pyramid. Using the COCO data set, which consists of a considerable quantity of small-scale objects, the experiments are implemented. The analysis results verify the optimized performance of DAFPN compared with the original Feature Pyramid Network(FPN) specifically for the identification on a small scale. The proposed DAFPN is promising for object detection in an era full of intelligent machines that need to detect multi-scale objects.

Neighborhood fusion-based hierarchical parallel feature pyramid network for object detection

In order to improve the detection accuracy of small objects,a neighborhood fusion-based hierarchical parallel feature pyramid network(NFPN)is proposed.Unlike the layer-by-layer structure adopted in the feature pyramid network(FPN)and deconvolutional single shot detector(DSSD),where the bottom layer of the feature pyramid network relies on the top layer,NFPN builds the feature pyramid network with no connections between the upper and lower layers.That is,it only fuses shallow features on similar scales.NFPN is highly portable and can be embedded in many models to further boost performance.Extensive experiments on PASCAL VOC 2007,2012,and COCO datasets demonstrate that the NFPN-based SSD without intricate tricks can exceed the DSSD model in terms of detection accuracy and inference speed,especially for small objects,e.g.,4%to 5%higher mAP(mean average precision)than SSD,and 2%to 3%higher mAP than DSSD.On VOC 2007 test set,the NFPN-based SSD with 300×300 input reaches 79.4%mAP at 34.6 frame/s,and the mAP can raise to 82.9%after using the multi-scale testing strategy.

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.

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。

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。

基于改进YOLOv7模型的血细胞检测分类

目的探讨改进YOLOv7算法在血细胞图像不同类型细胞自动检测分类中的应用,以提高血细胞识别分类的准确度。方法将滑动窗口变换器模块引入YOLOv7,同时采用加权双向特征金字塔网络结构,使网络能够获取并传递更加丰富的特征信息,使用斯库拉交并比损失代替完全交并比损失,实现更加精准的目标框定位。结果通过不同算法在BCCD血细胞数据集上展开实验可得,改进的YOLOv7模型对红细胞、白细胞和血小板的识别准确度分别达到89.3%、98.5%和91.5%,平均准确度达93.1%,相比于原YOLOv7模型提升了2.6%。通过与已发表的血细胞人工智能检测算法进行对比可知,本文算法具有更高的准确度。结论改进的YOLOv7模型可以有效应用于血细胞识别分类任务,为血细胞的检测提供重要的参考价值。

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。

基于改进YOLO算法的无人机图像草原火灾检测研究

草原火灾一旦发生,受风力、地势等因素的影响迅速向四周无规则蔓延,形成面积不断扩大的条状燃烧带。为了提高草原火灾检测效率,结合无人机拍摄草原火灾的图像特征,研究基于改进YOLO算法的草原火灾检测方法。首先,针对火灾区域狭长、火灾区域占比小的特点,对YOLO算法的Neck部分进行优化,提出一种具有全链接结构的特征提取网络FC-FP Neck,使语义特征和定位特征充分融合,提高网络的特征提取能力;其次,结合阈值分割技术提出一种改进的自适应加权损失函数,提升模型的收敛速度,同时解决火灾检测敏感度不足,容易造成误检的问题。在公开小目标检测数据集AI-TOD上测试改进算法的可行性,平均准确率提高了7.28%,平均精度提高了12.46%;在自建草原火灾数据集上平均精度达到了90.24%,平均准确率达到了87.33%。实验表明改进后的算法提高了草原火灾检测效率。

集成全局局部特征交互与角动量机制的端到端多目标跟踪算法

针对多目标跟踪(MOT)算法性能对于检测准确度和数据关联策略的依赖性问题,该文提出一种新的端到端算法。在检测方面,首先基于特征金字塔网络,提出空间残差特征金字塔模块(SRFPN),以提升特征融合和信息传递的效率。随后,引入全局局部特征交互模块(GLFIM)来平衡局部细节和全局上下文信息,增强多尺度特征的专注度,提高模型对目标尺度变化的适应性。在关联方面,引入角动量机制(AMM),充分考虑目标运动方向,以提升连续帧之间目标匹配的精确性。在MOT17和UAVDT数据集上进行实验验证,所提跟踪器的检测性能和关联性能均显著提升,并且在目标遮挡、尺度变化和杂乱背景等复杂场景下表现出良好的鲁棒性。

基于ResNet101多特征融合的新型冠状病毒感染图像分类方法

新型冠状病毒感染自爆发以来一直威胁着人类健康.针对现有对新型冠状病毒医学图像分类方法忽略了对深度神经网络前层特征的利用以及特征信息丢失不利于小区域的分类问题,本文提出了一种多特征融合利用的BAFPN-ResNet101模型.该模型以ResNet101为主干网络,引入了使用双线性插值法和通道注意力改进的特征金字塔结构,在主干网络与特征金字塔结构横向连接中使用通道注意力增强特征赋予不同的权重,然后利用特征金字塔结构将高层特征与低层特征融合.在公开数据集Chest X-ray(Covid-19&Pneumonia)上测试,实验结果显示,BAFPN-ResNet101模型在三分类实验中对识别新型冠状病毒感染胸部X射线的准确率、精确率、召回率分为97.41%、98.36%、97.20%.与其他方法相比,本文所提方法有效的利用了神经网络前层特征,对新型冠状病毒感染胸部X射线图像能够精确的识别,具有良好的泛化能力和性能.

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.

基于渐进式GAN逆映射的人脸超分辨率重建

为了缓解生成对抗网络(generative adversarial network,GAN)自身存在的训练不稳定问题,增强图像超分辨率重建的效果,提出一种基于GAN逆映射的图像超分辨率重建算法。通过渐进式网络增加模型的稳定性,通过逆映射金字塔充分学习低分辨人脸图像的语义特征,实现准确的隐空间转换,通过半空间特征调制进行图像增强。对所提算法进行实验验证,该算法在Celeb A数据集上重建8倍后的图像峰值信噪比为27.18 dB,相比超分辨率生成对抗网络(super-resolution generative adversarial network,SRGAN),提高了2.44 dB,模型的收敛速度也更快。实验结果表明,通过GAN逆映射和渐进的方式进行图像超分辨率重建具有较好的效果和更高的稳定性。

基于改进YOLOv7-DeepSort的红外视频多目标跟踪

针对红外图像纹理弱及多目标遮挡导致跟踪精度低的问题,构建了基于改进YOLOv7模型和多目标跟踪算法DeepSort的融合红外目标跟踪模型MSB-YOLOv7-DeepSort。采用SE(squeeze and excitation)通道注意力机制和双向特征金字塔网络提高红外目标的特征提取质量;利用轻量化网络MobileNetV3替换YOLOv7骨干网络,提升融合模型的推理速度。实验结果表明,MSB-YOLOv7-DeepSort模型在跟踪准确度、跟踪精确度、正确目标跟踪比例和帧率等方面均具有较好的性能。