Lightweight Cross-Modal Multispectral Pedestrian Detection Based on Spatial Reweighted Attention Mechanism

Multispectral pedestrian detection technology leverages infrared images to provide reliable information for visible light images, demonstrating significant advantages in low-light conditions and background occlusion scenarios. However, while continuously improving cross-modal feature extraction and fusion, ensuring the model’s detection speed is also a challenging issue. We have devised a deep learning network model for cross-modal pedestrian detection based on Resnet50, aiming to focus on more reliable features and enhance the model’s detection efficiency. This model employs a spatial attention mechanism to reweight the input visible light and infrared image data, enhancing the model’s focus on different spatial positions and sharing the weighted feature data across different modalities, thereby reducing the interference of multi-modal features. Subsequently, lightweight modules with depthwise separable convolution are incorporated to reduce the model’s parameter count and computational load through channel-wise and point-wise convolutions. The network model algorithm proposed in this paper was experimentally validated on the publicly available KAIST dataset and compared with other existing methods. The experimental results demonstrate that our approach achieves favorable performance in various complex environments, affirming the effectiveness of the multispectral pedestrian detection technology proposed in this paper.

New Fusion Approach of Spatial and Channel Attention for Semantic Segmentation of Very High Spatial Resolution Remote Sensing Images

The semantic segmentation of very high spatial resolution remote sensing images is difficult due to the complexity of interpreting the interactions between the objects in the scene. Indeed, effective segmentation requires considering spatial local context and long-term dependencies. To address this problem, the proposed approach is inspired by the MAC-UNet network which is an extension of U-Net, densely connected combined with channel attention. The advantages of this solution are as follows: 4) The new model introduces a new attention called propagate attention to build an attention-based encoder. 2) The fusion of multi-scale information is achieved by a weighted linear combination of the attentions whose coefficients are learned during the training phase. 3) Introducing in the decoder, the Spatial-Channel-Global-Local block which is an attention layer that uniquely combines channel attention and spatial attention locally and globally. The performances of the model are evaluated on 2 datasets WHDLD and DLRSD and show results of mean intersection over union (mIoU) index in progress between 1.54% and 10.47% for DLRSD and between 1.04% and 4.37% for WHDLD compared with the most efficient algorithms with attention mechanisms like MAU-Net and transformers like TMNet.

一种基于SAM-MSFF网络的低照度目标检测方法

由于低照度图像具有对比度低、细节丢失严重、噪声大等缺点,现有的目标检测算法对低照度图像的检测效果不理想.为此,本文提出一种结合空间感知注意力机制和多尺度特征融合(Spatial-aware Attention Mechanism and Multi-Scale Feature Fusion,SAM-MSFF)的低照度目标检测方法 .该方法首先通过多尺度交互内存金字塔融合多尺度特征,增强低照度图像特征中的有效信息,并设置内存向量存储样本的特征,捕获样本之间的潜在关联性;然后,引入空间感知注意力机制获取特征在空间域的长距离上下文信息和局部信息,从而增强低照度图像中的目标特征,抑制背景信息和噪声的干扰;最后,利用多感受野增强模块扩张特征的感受野,对具有不同感受野的特征进行分组重加权计算,使检测网络根据输入的多尺度信息自适应地调整感受野的大小.在ExDark数据集上进行实验,本文方法的平均精度(mean Average Precision,mAP)达到77.04%,比现有的主流目标检测方法提高2.6%~14.34%.

Bilateral U-Net semantic segmentation with spatial attention mechanism

Aiming at the problem that the existing models have a poor segmentation effect on imbalanced data sets with small-scale samples,a bilateral U-Net network model with a spatial attention mechanism is designed.The model uses the lightweight MobileNetV2 as the backbone network for feature hierarchical extraction and proposes an Attentive Pyramid Spatial Attention(APSA)module compared to the Attenuated Spatial Pyramid module,which can increase the receptive field and enhance the information,and finally adds the context fusion prediction branch that fuses high-semantic and low-semantic prediction results,and the model effectively improves the segmentation accuracy of small data sets.The experimental results on the CamVid data set show that compared with some existing semantic segmentation networks,the algorithm has a better segmentation effect and segmentation accuracy,and its mIOU reaches 75.85%.Moreover,to verify the generality of the model and the effectiveness of the APSA module,experiments were conducted on the VOC 2012 data set,and the APSA module improved mIOU by about 12.2%.

基于PCSA-YOLOv7 Former的输电线路连接金具及其锈蚀检测方法

输电线路分布情况复杂且故障难以有效检测,其中连接金具长期暴露于复杂环境下易受到恶劣环境的影响出现锈蚀等故障。针对输电线路连接金具部件具有尺度多样性和存在着锈蚀故障检测精度低的问题,提出了一种基于双重注意力嵌入重构和Swin Transformer的输电线路连接金具组件及其锈蚀故障检测方法:PCSA-YOLOv7 Former。实验结果表明:该方法在构建的TLCF数据集上的综合检测性能领先于12类当前先进的目标检测算法,其中在测试集上的mAP_(0.5)达到94.9%,该方法相比于基线模型YOLOv7,其F1和mAP0.5指标分别提升了2.6个百分点和2.2个百分点,说明该方法能够更全面地理解输电线路连接金具图像中的多尺度语义信息并学习到不易区分的微小细节表征。

基于SA/WGAN的新能源场景生成方法

随着新能源渗透率逐年提高,其出力的随机性与波动特性难以准确预测,给电力系统的运行、规划和调度提出了严峻的挑战,因此新能源的不确定性建模受到越来越多的关注。为了更有效地获得新能源出力场景中的时序特征,提出了一种基于数据驱动的新能源场景生成方法,通过采用SA/WGAN模型,把自注意力机制和带有梯度惩罚的生成对抗网络判别器结合,构建基于两种模型结合的深度学习模型,有效突显新能源出力场景中时序特性,增强场景生成中非线性拟合能力。算例结果表明,所提模型的新能源生成场景相较于原始WGAN和WGAN-LSTM的场景生成结果,可以有效提高精准度,同时具备了WGAN-GP训练结果稳定和SA计算速度快的优势,更高效地生成与真实新能源场景分布接近的场景。

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.

Effect of Neurofeedback on Visual-Spatial Attention in Male Children with Reading Disabilities: An Event-Related Potential Study

Recent studies describe a number of difficulties associated with attention deficit in children with reading disabilities. Information about visual-spatial attention mainly arises from studies using event-related potentials (ERPs) during Posner’s spatial cueing paradigm. This study aims to use neurofeedback with a special protocol for treating children with reading disabilities, and moreo-ver, to evaluate visual-spatial attention ability by means of Posner paradigm task and ERPs. The study was conducted in a single subject design in 20 sessions. Participants were 2 male children, aged between 10 - 12 years old, who completed twelve 30-min neurofeedback sessions. Repeated measurements were performed during the baseline, treatment, and post treatment phases. Results showed some improvement in Posner paradigm parameters (correct response, valid and invalid reaction times). Furthermore, grand average ERPs for both of the participants in each of the four conditions (Valid-right, Invalid-right, Valid-left and Invalid-left) were analyzed. The analysis of P3 component showed a reduction in latency, indicating an improvement in the timing of cognitive processes. In addition, the graphs showed a decrease in amplitude level, which meant easier processing than before.

基于DSA-UFLD模型的车道线检测算法

车道线检测是保证自动驾驶安全性与稳定性的关键,为提高车道线检测的准确性,本文基于UFLD(Ultra Fast Structure-aware Deep Lane Detection)算法,结合DenseNet-121网络和空间注意力(Spatial Attention)机制,设计了一种DSA-UFLD模型实现车道线检测。在图像增强方面,使用图像亮度自适应增强算法提高欠曝图像的清晰度;在网络优化方面,用迁移学习模型DenseNet-121代替ResNet18提取图像特征,利用密集连接加强特征重用,并引入空间注意力机制提取图像的关键信息,其次在上采样中用转置卷积代替双线性插值,通过学习参数,更好地实现解码;在损失函数方面,通过改进结构损失,将车道线约束为二次曲线,改善了弯道场景下车道线的检测效果。实验结果表明,DSA-UFLD算法在保证检测速度的同时,提高了车道线的识别准确率,具有一定的应用价值。

SAF-Net:自注意力融合网络的视网膜血管分割

眼底图像中的自动血管分割在各种心血管和眼科疾病的筛查、诊断、治疗和评估中发挥着重要作用。然而,由于注释良好的数据有限、血管大小不一、血管结构复杂,视网膜血管分割已成为一项长期存在的挑战。因此,提出了一种自注意力融合网络,它将空间和通道注意力并行地结合起来处理视网膜血管分割问题。分别从空间维度和通道维度进行特征提取,专注于高频信息提取。该网络将两个注意模块的输出相加,以进一步改进特征表示,从而获得更精确的分割结果。在公开数据集DRIVE、CHASE_DB1和STARE上验证了该算法,实验结果表明,与近几年的视网膜血管分割算法相比,提出的视网膜血管分割算法具有优越性。

基于Xception和SA的YOLOv5建筑裂缝检测方法

裂缝检测对于建筑的维修和加固、延长其使用寿命具有重要意义。针对建筑裂缝种类多和尺寸小造成裂缝检测精度低、速度慢的问题,提出了一种改进的YOLOv5裂缝检测算法,在提高检测裂缝精度的同时也提升了检测裂缝的速度。首先,引入轻量级网络Xception对主干网络轻量化,减少主干网络参数量以提升检测裂缝的速度;其次,使用空洞空间金字塔池化ASPP(Atrous Spatial Pyramid Pooling)模块替换SPP(Spatial Pyramid Pooling)模块,扩大感受野范围,加强主干网络提取裂缝特征的能力,避免因对主干网络轻量化而造成检测裂缝的精度降低;最后,添加SA(Shuffle Attention)注意力机制,进一步加强网络提取裂缝特征的能力,提高裂缝检测的精度。通过在自制数据集上进行的实验表明,改进的算法mAP比原算法提高了1.6%,速度为50.8 f/s,比原算法提高了2.7 f/s,满足建筑裂缝检测的精度和实时性要求,同时将改进算法与Faster R-CNN、Mobile-SSD、YOLOv4-tiny等算法进行对比,证明了该算法的优越性,更适合部署到硬件平台上。

面向交通流量预测的时空Graph-CoordAttention网络

交通预测是城市智能交通系统的一个重要研究组成部分,使人们的出行更加效率和安全。由于复杂的时间和空间依赖性,准确预测交通流量仍然是一个巨大的挑战。近年来,图卷积网络(GCN)在交通预测方面表现出巨大的潜力,但基于GCN的模型往往侧重于单独捕捉时间和空间的依赖性,忽视了时间和空间依赖性之间的动态关联性,不能很好地融合它们。此外,以前的方法使用现实世界的静态交通网络来构建空间邻接矩阵,这可能忽略了动态的空间依赖性。为了克服这些局限性,并提高模型的性能,提出了一种新颖的时空Graph-CoordAttention网络(STGCA)。具体来说,提出了时空同步模块,用来建模不同时刻的时空依赖交融关系。然后,提出了一种动态图学习的方案,基于车流量之间数据关联,挖掘出潜在的图信息。在4个公开的数据集上和现有基线模型进行对比实验,STGCA表现了优异的性能。

RF-SA-GRU模型的股价预测研究

针对股票具有多因子、高随机性和非平稳性等复杂特征,利用门控循环单元(GRU)网络直接进行股价预测效果较差的问题。在融合自注意力机制(SA)和GRU,构建SA-GRU模型的基础上,引入降维处理技术随机森林(RF)算法,针对股票收盘价筛选其他因子,将经过降维的股票因子数据作为SA-GRU模型的输入。基于双层GRU网络提取股票因子间的依赖关系,再利用SA加强对重要因子的关注和因子内部的联系,得到加入注意力权重后的股票因子数据,通过全连接层输出股价预测值,从而构建RF-SA-GRU混合模型。选取涉及18个基础行业的18只股票进行股价预测,实验显示RF-SA-GRU模型在18只股票上均取得好的预测效果,且预测精度和稳定性均优于其他模型。此外,选取3个指数进行收盘点位预测,实验显示RF-SA-GRU模型在股指预测方面依旧具有更好的预测性能。

基于SASK和双分支结构的服装图像识别方法

服装图像具有明暗不一、尺度各异的特性,这使得已有识别方法表现不佳。为解决此问题,本文基于空间注意力选择核(space attention selective kernel, SASK)模块和双分支结构搭建神经网络模型对服装图像进行识别。首先,结合跳跃连接、稠密连接和多尺度、通道拆分的思想,设计双分支神经网络,充分提取服装对象的整体特征。其次,基于空间注意力机制,设计SASK模块,使网络可以更多地关注服装对象的形态特征信息,从而提升识别效果。实验结果表明,本文所提方法不但在典型服装数据集上能够取得优于现有主流方法的识别精度,而且在具有明暗不一、尺度各异特性的其他图像数据集上同样表现良好。

MVCE-Net: Multi-View Region Feature and Caption Enhancement Co-Attention Network for Visual Question Answering

Visual question answering(VQA)requires a deep understanding of images and their corresponding textual questions to answer questions about images more accurately.However,existing models tend to ignore the implicit knowledge in the images and focus only on the visual information in the images,which limits the understanding depth of the image content.The images contain more than just visual objects,some images contain textual information about the scene,and slightly more complex images contain relationships between individual visual objects.Firstly,this paper proposes a model using image description for feature enhancement.This model encodes images and their descriptions separately based on the question-guided coattention mechanism.This mechanism increases the feature representation of the model,enhancing the model’s ability for reasoning.In addition,this paper improves the bottom-up attention model by obtaining two image region features.After obtaining the two visual features and the spatial position information corresponding to each feature,concatenating the two features as the final image feature can better represent an image.Finally,the obtained spatial position information is processed to enable the model to perceive the size and relative position of each object in the image.Our best single model delivers a 74.16%overall accuracy on the VQA 2.0 dataset,our model even outperforms some multi-modal pre-training models with fewer images and a shorter time.

基于VSA-UNet的电气设备紫外图像分割

提高电气设备紫外图像分割精确度对设备放电程度的准确评估具有重要意义。由于存在噪声干扰与紫外光斑形状、大小不规则等问题,目标分割区域存在过分割和欠分割现象,因此提出一种基于多模块的VSA-UNet(VGG16Net, Improved SENet, and ASPP based U-Net)分割网络。为强化网络特征提取能力,减少过分割现象,使用VGG16Net的卷积层代替U-Net网络的编码部分;将编码部分末端卷积层替换成空洞空间金字塔池化(Atrous Spatial Pyramid Pooling, ASPP)模块,获取紫外图像的多尺度信息,解决大区域的欠分割问题;在跳跃连接部分加入改进SENet模块,加强有用信息的提取,补充细节损失,提升整体网络性能。基于自建紫外图像数据集的实验表明,改进网络在分割紫外图像时平均交并比(Mean Intersection over Union, MIoU)达到81.78%,平均精确率为95.97%。与U-Net网络相比,提出的VSA-UNet模型明显提升了紫外图像分割的准确性。

Improved Blending Attention Mechanism in Visual Question Answering

Visual question answering(VQA)has attracted more and more attention in computer vision and natural language processing.Scholars are committed to studying how to better integrate image features and text features to achieve better results in VQA tasks.Analysis of all features may cause information redundancy and heavy computational burden.Attention mechanism is a wise way to solve this problem.However,using single attention mechanism may cause incomplete concern of features.This paper improves the attention mechanism method and proposes a hybrid attention mechanism that combines the spatial attention mechanism method and the channel attention mechanism method.In the case that the attention mechanism will cause the loss of the original features,a small portion of image features were added as compensation.For the attention mechanism of text features,a selfattention mechanism was introduced,and the internal structural features of sentences were strengthened to improve the overall model.The results show that attention mechanism and feature compensation add 6.1%accuracy to multimodal low-rank bilinear pooling network.

一种面向口腔移植骨分割的SA-UNet网络

在牙齿种植治疗中,口腔移植骨分割对于辅助医生诊断有重要参考价值。口腔CBCT图像具有对比度较低,移植骨边缘模糊等诸多特征,严重制约着现有深度分割网络的应用。研究以U-Net为基准网络,通过设计一种新颖的轻量级Sharp-Attention模块,提出了一种改进的SA-UNet网络模型。具体地,在Sharp模块中,带锐化卷积核的Depthwise卷积操作通过锐化浅层特征以加强特征细节。CBAM模块提升模型对于图像低层信息的关注度。进而,采用新型联合损失函数,缓解样本比例失衡带来的影响。最后,在口腔移植骨数据集上验证了模型的有效性。在模型复杂度方面,与基准网络U-Net相比,在几乎没有增加计算开销的情况下,图像分割精度得到了有效的提升;在分割精度方面,与现有的主流医学分割模型对比,在IoU、Dice系数、Hausdorff距离三个评价指标上的表现最佳,得分达到了0.8665、0.9262、0.5092。

基于深度学习的Attention U-Net语义分割模型研究

针对当前深度神经网络在处理图像分割过程中普遍存在的处理耗时长、实时性低和分割准确率不高的问题,提出了一种融入注意力机制的U-Net网络对GAN扩充的数据集进行训练的模型,试验结果表明:相较于U-Net++、SegNet和DeepLabV1等传统模型,提出模型的平均损失约为129%,与U-Net++、DeepLabV1模型较为接近;平均精确度约为95.4%,比U-Net++提高了1.7%,比SegNet提高了6%,比DeepLabV1提高了1.7%。

基于融合注意力机制LSTM网络的地下水位自适应鲁棒预测

地下水水位是旱天污水管网地下水入渗量的重要影响因素,快速精准地预测地下水水位能有效提升旱天污水管网地下水入渗量估算准确度,辅助优化管网病害治理与维护策略。针对目前城市复杂水文预测存在的准确度低、灵敏度低、泛化能力弱等问题,本文提出了一种新的鲁棒自适应水位预测算法。首先,对水文数据进行预处理,解决了数据时间跨度大、噪声多、缺失及异常、非平稳等问题。其次,针对不同输入特征对预测指标的影响,在模型训练阶段提出一种新的空间变量注意机制,可快速识别与水位关联的关键变量,并对输入特征赋予不同的影响权重。然后,针对不同序列长度对预测效果的影响,还设计了自适应时间注意力机制,帮助网络自适应地找出与不同时间序列长度预测指标相关的编码器隐藏状态,以更好地捕捉时间上的依赖关系。在此基础上,以上下文向量作为输入,提出一种融合注意力机制的长短时记忆网络水文预测算法。最后,通过意大利Petrignano水文数据验证了所提算法的有效性,并与GRU、Elman、LSTM、VA–LSTM和S–LSTM等方法进行预测性能比较。结果表明,基于融合注意力机制的LSTM网络在面临大规模、噪点多的复杂数据时有优于其它几种算法的预测效果,表明该算法具有强自适应性和鲁棒性。本文研究结果可以为市政排水策略合理调整、及时控制提供参考。