CAW-YOLO:Cross-Layer Fusion and Weighted Receptive Field-Based YOLO for Small Object Detection in Remote Sensing

In recent years,there has been extensive research on object detection methods applied to optical remote sensing images utilizing convolutional neural networks.Despite these efforts,the detection of small objects in remote sensing remains a formidable challenge.The deep network structure will bring about the loss of object features,resulting in the loss of object features and the near elimination of some subtle features associated with small objects in deep layers.Additionally,the features of small objects are susceptible to interference from background features contained within the image,leading to a decline in detection accuracy.Moreover,the sensitivity of small objects to the bounding box perturbation further increases the detection difficulty.In this paper,we introduce a novel approach,Cross-Layer Fusion and Weighted Receptive Field-based YOLO(CAW-YOLO),specifically designed for small object detection in remote sensing.To address feature loss in deep layers,we have devised a cross-layer attention fusion module.Background noise is effectively filtered through the incorporation of Bi-Level Routing Attention(BRA).To enhance the model’s capacity to perceive multi-scale objects,particularly small-scale objects,we introduce a weightedmulti-receptive field atrous spatial pyramid poolingmodule.Furthermore,wemitigate the sensitivity arising from bounding box perturbation by incorporating the joint Normalized Wasserstein Distance(NWD)and Efficient Intersection over Union(EIoU)losses.The efficacy of the proposedmodel in detecting small objects in remote sensing has been validated through experiments conducted on three publicly available datasets.The experimental results unequivocally demonstrate the model’s pronounced advantages in small object detection for remote sensing,surpassing the performance of current mainstream models.

Multimodal Medical Image Fusion Methods Based on Improved Discrete Wavelet Transform

Objective This paper proposed a novel algorithm of discrete wavelet transform(DWT) which is used for multimodal medical image fusion. Methods The source medical images are initially transformed by DWT followed by fusing low and high frequency sub-images. Then, the "coefficient absolute value" that can provide clear and detail parts is adapted to fuse high-frequency coefficients, where as the "region energy ratio" which can efficiently preserve most information of source images is employed to fuse low-frequency coefficients. Finally, the fused image is reconstructed by inverse wavelet transform. Results Visually and quantitatively experimental results indicate that the proposed fusion method is superior to traditional wavelet transform and the existing fusion methods. Conclusion The proposed method is a feasible approach for multimodal medical image fusion which can obtain more efficient and accurate fusions results even in the noise environment.

Attention-Based CNN Fusion Model for Emotion Recognition During Walking Using Discrete Wavelet Transform on EEG and Inertial Signals

Walking as a unique biometric tool conveys important information for emotion recognition.Individuals in different emotional states exhibit distinct walking patterns.For this purpose,this paper proposes a novel approach to recognizing emotion during walking using electroencephalogram(EEG)and inertial signals.Accurate recognition of emotion is achieved by training in an end-to-end deep learning fashion and taking into account multi-modal fusion.Subjects wear virtual reality head-mounted display(VR-HMD)equipment to immerse in strong emotions during walking.VR environment shows excellent imitation and experience ability,which plays an important role in awakening and changing emotions.In addition,the multi-modal signals acquired from EEG and inertial sensors are separately represented as virtual emotion images by discrete wavelet transform(DWT).These serve as input to the attention-based convolutional neural network(CNN)fusion model.The designed network structure is simple and lightweight while integrating the channel attention mechanism to extract and enhance features.To effectively improve the performance of the recognition system,the proposed decision fusion algorithm combines Critic method and majority voting strategy to determine the weight values that affect the final decision results.An investigation is made on the effect of diverse mother wavelet types and wavelet decomposition levels on model performance which indicates that the 2.2-order reverse biorthogonal(rbio2.2)wavelet with two-level decomposition has the best recognition performance.Comparative experiment results show that the proposed method outperforms other existing state-of-the-art works with an accuracy of 98.73%.

基于多源数据融合的配电网拓扑识别方法研究

针对目前配电网拓扑识别时多源融合数据利用率低的问题,提出了一种基于多源数据融合的配电网拓扑识别方法。首先,设计了一种多源数据时间尺度对齐方法。其次,提出了一种基于线性外推的伪测量数据生成方法,从而提高拓扑识别方法的数据精度。最后,建立了多源数据融合配电网离散化和线性化最优拓扑识别方法。在试验阶段,以IEEE 33馈线系统为例验证所提方法。试验结果表明,当节点注入功率数据的实时测量误差为30%、伪测量误差为5%时,所提方法拓扑识别准确率为70.98%,较无融合方法提升了5.86%。所提方法对提高配电网拓扑识别准确率具有一定指导作用。

基于多尺度特征融合的功耗建模分析方法

在数字化浪潮推动下,5G和6G技术的快速发展正引领移动通信系统步入新阶段.先进的硬件设备和加密芯片为不断增长的数据处理需求和日益关注的安全保障提供了强有力的支持.在这一背景下,搭载现代密码技术的各类硬件设备逐渐演变为不可或缺的生活基石.这些设备已经具备抵御传统密码分析的能力.近年来,学术界的研究重点之一是对设备在实际运行过程中产生的物理泄漏进行分析.这一领域被称为侧信道分析(Side-Channel Analysis,SCA).深度学习驱动的侧信道分析已被广泛认可为一种有效的方法,针对当前神经网络模型的功耗曲线数量需求大、鲁棒性差和收敛速度慢等问题,本文提出一种基于CNNbest的多尺度特征融合侧信道分析方法.首先,重构特征提取网络结构,以解决深层特征向量容易过度解释噪声细节的问题和模型过拟合问题.而后,使用滤波器阵列执行离散小波变换(Dis‐crete Wavelet Transform,DWT)分析方法构造多解析度时频,提升数据质量.最后,引入轻量级的结合通道空间的卷积块注意力模块(Convolutional Block Attention Module,CBAM),以提高功耗曲线关键特征的学习效率.实验结果表明,本文方法对侧信道分析所需的功耗曲线较原模型减少了88.27%,显著提高了分析性能,能够满足侧信道建模和分析的要求.

A Triple-Channel Encrypted Hybrid Fusion Technique to Improve Security of Medical Images

Assuring medical images protection and robustness is a compulsory necessity nowadays.In this paper,a novel technique is proposed that fuses the wavelet-induced multi-resolution decomposition of the Discrete Wavelet Transform(DWT)with the energy compaction of the Discrete Wavelet Transform(DCT).The multi-level Encryption-based Hybrid Fusion Technique(EbhFT)aims to achieve great advances in terms of imperceptibility and security of medical images.A DWT disintegrated sub-band of a cover image is reformed simultaneously using the DCT transform.Afterwards,a 64-bit hex key is employed to encrypt the host image as well as participate in the second key creation process to encode the watermark.Lastly,a PN-sequence key is formed along with a supplementary key in the third layer of the EbHFT.Thus,the watermarked image is generated by enclosing both keys into DWT and DCT coefficients.The fusions ability of the proposed EbHFT technique makes the best use of the distinct privileges of using both DWT and DCT methods.In order to validate the proposed technique,a standard dataset of medical images is used.Simulation results show higher performance of the visual quality(i.e.,57.65)for the watermarked forms of all types of medical images.In addition,EbHFT robustness outperforms an existing scheme tested for the same dataset in terms of Normalized Correlation(NC).Finally,extra protection for digital images from against illegal replicating and unapproved tampering using the proposed technique.

Multiresolution image fusion scheme based on fuzzy region feature

This paper proposes a novel region based image fusion scheme based on multiresolution analysis. The low frequency band of the image multiresolution representation is segmented into important regions, sub-important regions and background regions. Each feature of the regions is used to determine the region’s degree of membership in the multiresolution representation, and then to achieve multiresolution representation of the fusion result. The final image fusion result can be obtained by using the inverse multiresolution transform. Experiments showed that the proposed image fusion method can have better performance than existing image fusion methods.

Multimodal Medical Image Registration and Fusion for Quality Enhancement

For the last two decades,physicians and clinical experts have used a single imaging modality to identify the normal and abnormal structure of the human body.However,most of the time,medical experts are unable to accurately analyze and examine the information from a single imaging modality due to the limited information.To overcome this problem,a multimodal approach is adopted to increase the qualitative and quantitative medical information which helps the doctors to easily diagnose diseases in their early stages.In the proposed method,a Multi-resolution Rigid Registration(MRR)technique is used for multimodal image registration while Discrete Wavelet Transform(DWT)along with Principal Component Averaging(PCAv)is utilized for image fusion.The proposed MRR method provides more accurate results as compared with Single Rigid Registration(SRR),while the proposed DWT-PCAv fusion process adds-on more constructive information with less computational time.The proposed method is tested on CT and MRI brain imaging modalities of the HARVARD dataset.The fusion results of the proposed method are compared with the existing fusion techniques.The quality assessment metrics such as Mutual Information(MI),Normalize Crosscorrelation(NCC)and Feature Mutual Information(FMI)are computed for statistical comparison of the proposed method.The proposed methodology provides more accurate results,better image quality and valuable information for medical diagnoses.

基于融合注意力和任务解耦的路面裂缝检测

针对路面裂缝自动化检测中存在裂缝漏检和定位不准的问题,提出一种路面裂缝实时检测模型CrackNet。基于YOLOv5结构设计,在特征融合网络插入融合注意力模块,重点关注特定通道和空间位置裂缝信息,有效解决部分裂缝漏检问题;在多尺度预测阶段引入任务空间分离头模块,利用分治策略将分类和回归任务解耦,模型优化方向更加自由。实验结果表明,该方法mAP为71%,速度为42 FPS,优于基准模型,有效改善了裂缝漏检和定位不准的问题。

基于两枚不同指纹融合模糊金库的身份认证算法

基于单一生物特征模糊金库证易于受到相关攻击而导致生物特征模板泄露的安全性问题,提出一种基于两枚不同手指指纹的特征融合模糊金库的身份认证方案。这种身份认证方案采用了分别来自两枚不同手指指纹的细节点与方向场进行融合的方法,基于Diffie-Hellman密钥交换协议思想。实验结果表明该身份认证方案在指纹特征模板的安全性保护上比基于单一指纹特征模板有显著提高。

基于分数阶小波与引导滤波的多聚焦图像融合方法

针对多聚焦图像融合中存在易丢失细节信息、图像边缘处产生伪影等问题,提出了一种基于离散分数阶小波变换(DFRWT)结合引导滤波的多聚焦图像融合新方法。首先,采用DFRWT将多聚焦源图像进行多尺度分解,得到低频部分与高频部分。其次,为了使图像信息有效地融合,根据小波模系数的能量在不同阶数下的分布特征,选取最适合分数阶阶数,在低频部分应用拉普拉斯能量并获得初始决策,再用引导滤波修正决策图得到融合规则;高频部分采用分数阶空间频率的融合规则。最后,通过DFRWT逆变换获得融合后的图像。新方法与现有5种算法进行视觉对比和定量评估,仿真实验表明,本文方法有效抑制了Gibbs效应和边缘处的伪影效应,视觉效果和客观评价均令人满意,融合图像的质量优于已有的几类经典算法。

基于离散小波分解与重构的多源土壤含水量数据融合方法与评估

为提高土壤含水量格点数据的区域适用性、准确性,该研究提出了基于离散小波多尺度分解与重构的多源土壤含水量数据融合方法,利用2016-2018年6-9月ESA-CCI、SMAP、ERA5-Land数据集以及地面站点观测的土壤含水量数据,在以黄河流域为主体的主要农业气候区开展了融合方法可行性和适用性研究。结果表明,融合方法能有效捕获融合数据源的多尺度特征信息,通过多源多尺度逐层特征信息权重融合与重构,能有效改进单一数据源在不同农业气候区域的适用性、时空结构和波动特征的准确性。融合结果总体评估的均方根误差、偏差(Bias)和相关系数(r)分别为0.053 m^(3)/m^(3)、0.001 m^(3)/m^(3)和0.721,时空分解评估的综合表现均优于单一融合数据源的评估指标,多尺度时空波动频谱结构特征与观测时空序列更吻合,特别在25 d时间尺度以内时空波动吻合度改进最为明显。该研究获得了较理想的区域土壤含水量改进预期,可为区域生态环境监测、农业可持续发展、水土保持、防灾减灾等科学研究和业务应用提供可行有效的方法参考。

基于加权感受野和跨层融合的遥感小目标检测

针对遥感图像中小目标特征易丢失、易受背景噪声影响和定位难的问题,本文对YOLOX-S目标检测模型进行改进。使用二维离散余弦变换对CBAM注意力模块进行改进并加入到主干网络当中,提高网络对小目标的关注度;其次提出一种加权多重感受野空间金字塔池化模块,提升模型对多尺度目标尤其是小尺度目标的感知能力;采用跨层特征融合的思想,提出一种跨层注意力融合模块,使深层结构中尽可能保留更多的小目标特征;最后使用EIoU损失加强对小目标的定位能力。由大量实验分析可知,在RSOD数据集上,改进模型的APs值相对于基准模型提高了5.1%,在DIOR数据集上提高了2.4%,参数量仅增加了1.01 M,检测速度达到93.6 fps,满足实时性的检测要求。此外,相对于当前最新的目标检测模型,本文改进模型也具有一定优势。

A Review on Discrete Element Method Simulation in Laser Powder Bed Fusion Additive Manufacturing

Laser powder bed fusion(LPBF)is a popular metal additive manufacturing technique.Generally,the materials employed for LPBF are discrete and particulate metal matters.Thus,the discontinuous behaviors exhibited by the powder materials cannot be simulated solely using conventional continuum-based computational approaches,such as finite-element or finite-difference methods.The discrete element method(DEM)is a proven numerical method to model discrete matter,such as powder particles,by tracking the motion and temperature of individual particles.Recently,DEM simulation has gained popularity in LPBF studies.However,it has not been widely applied.This study reviews the existing applications of DEM in LPBF processing,such as powder spreading and fusion.A review of the existing literature indicates that DEM is a promising approach in the study of the kinetic and thermal fluid behaviors of powder particles in LPBF additive manufacturing.

基于离散小波变换的多模态医学图像融合改进算法的研究

目的提出一种改进的离散小波变换算法,并将其用于多模态医学图像融合。方法将源图像经过离散小波变换分解为高频和低频子图像;高频部分采用方向绝对值取大,能有效地保存图像的细节信息,低频部分使用区域能量比融合规则,保存了图像的绝大部分信息;用离散小波逆变换将融合子图像重构成融合图像。结果由3组医学图像融合效果比较可知,该算法在主观视觉效果和客观评价指标方面均优于现存的其他算法。结论该医学图像融合算法快速准确,在噪声环境和临床实例中均表现优越,可以获得较高质量的融合图像,具有较高的临床应用价值。

一种结合sobel算子和小波变换的图像边缘检测方法

提出了一种基于数据融合的边缘检测方法。该方法对原始图像分别采用sobel算子和基于离散小波变换两种方法提取边缘,然后将两种方法的检测结果进行数据融合,得到一幅新的边缘图像。实验证明,融合后的图像边缘集合了两种检测方法的优点,是一种有效的图像边缘检测方法。

一种基于小波方向对比度的多聚焦图像融合方法

人类视觉系统对于图像的局部对比度非常敏感,如果把小波变换和方向对比度结合起来,融合效果可能更好。在研究了方向对比度后提出了一种新的基于小波方向对比度的多聚焦图像融合方法。首先对参加融合的两幅图像进行小波多尺度分解,然后在每幅图像的每个分解层上,分别计算高频子带每个像素的邻域均值和低频子带的邻域均值之比,其中该分解层的低频子带是由上个分解层的低频子带和高频子带求2维离散小波逆变换得到,采用两者之比较大者所对应的高频子带系数作为融合后对应的小波系数,然后从最高分解层到最低分解层依次对得到的高频小波系数和该分解层的低频小波系数求2维离散小波逆变换,最终得到融合后的图像。这种方法考虑了邻域内像素的相关性,减少了融合像素的错误选取。实验结果表明,该方法的融合效果比针对每个像素求小波方向对比度的多聚焦图像融合方法的融合效果得到提高。

基于离散小波框架变换的彩色多聚焦图像融合算法

提出了一种基于离散小波框架变换的彩色多聚焦图像融合算法。首先求取各彩色多聚焦图像的灰度分量,再对各灰度分量进行离散小波框架变换,根据离散小波框架变换系数求取各图像中像素的清晰度指标,然后根据各图像中像素的清晰度指标对属于清晰区域的像素进行组合,从而得到融合后的图像。试验结果表明本文所提出的算法能够较好地解决彩色多聚焦图像融合问题。

基于平移不变剪切波变换的医学图像融合

传统的基于剪切波变换的融合方法在融合图像的奇异处易产生伪吉布斯现象.为此,文中提出了一种基于平移不变剪切波变换的医学图像融合新方法.该方法利用平移不变剪切波变换将待融合的医学图像分解成低频子带和高频子带,并使用基于区域系数绝对值和权重的规则融合低频系数;对于高频子带,提出一种基于支持向量值激励的自生成神经网络的高频子带融合策略;最后利用逆平移不变剪切波变换重建融合后的图像.视觉比较和融合结果量化分析表明,文中提出的方法不仅能够有效克服伪吉布斯现象,而且以熵、互信息、平均梯度和QAB/F作为标准时其融合结果比小波、轮廓波和非下采样轮廓波变换等传统方法更好.

基于多小波变换的图像融合研究

多小波是小波理论的扩展 ,在图像处理方面具有单小波所不具有的优点。它能够为图像提供一种比小波多分辨分析更加精确的分析方法。在研究了多小波变换的特性后 ,提出了一种基于离散多小波变换的图像融合方法 ,并将由不同传感器获得的不同分辨率的遥感图像数据利用此方法进行了融合。这种方法不仅能够完好地显示源图像各自的信息 ,而且能很好地将源图像的细节融合在一起。通过实验结果证明 。