Detection of the movement direction by the cells with directional receptive fields in the primary visual cortex of the cat

The study was performed on neurons with direction selective (DS) receptive fields (RFs) in the primary visual cortex of the cat. Preferred directions (PDs) of these cells to a single light spot and a system of two identical light spots moving across the RF with a given angle between them were compared. Directional interactions appeared when the angles between the directions of the two moving spots were 30o or 60o. PD for 56% of the cells coincided with bisectors of these angles. These cells responded to a combination of the two moving stimuli as if only one stimulus moved in the RF in an intermediate direction. This direction coincided with PD of the DS neuron to a single spot. Also, the investigation revealed that DS neurons responded to stimuli moving at such angles as 180o (to preferred and opposite directions simultaneously). In the further experiment we investigated responses of the DS cells in the primary visual cortex of RF. The angle between the directions of the two moving spots was 60o. These cells responded to a combination of the two moving stimuli as if only one stimulus moved in RF in an intermediate direction. The more relative luminance of one of spots in pair was, the closer the intermediate direction approached to the direction of this spot).

Local field potentials,spiking activity,and receptive fields in human visual cortex

The concept of receptive field(RF) is central to sensory neuroscience. Neuronal RF properties have been substantially studied in animals,while those in humans remain nearly unexplored. Here, we measured neuronal RFs with intracranial local field potentials(LFPs) and spiking activity in human visual cortex(V1/V2/V3). We recorded LFPs via macro-contacts and discovered that RF sizes estimated from lowfrequency activity(LFA, 0.5–30 Hz) were larger than those estimated from low-gamma activity(LGA, 30–60 Hz) and high-gamma activity(HGA, 60–150 Hz). We then took a rare opportunity to record LFPs and spiking activity via microwires in V1 simultaneously. We found that RF sizes and temporal profiles measured from LGA and HGA closely matched those from spiking activity. In sum, this study reveals that spiking activity of neurons in human visual cortex could be well approximated by LGA and HGA in RF estimation and temporal profile measurement, implying the pivotal functions of LGA and HGA in early visual information processing.

Coal rock image recognition method based on improved CLBP and receptive field theory

Rapid coal-rock identification is one of the key technologies for intelligent and unmanned coal mining.Currently,the existing image recognition algorithms cannot satisfy practical needs in terms of recognition speed and accuracy.In view of the evident differences between coal and rock in visual attributes such as color,gloss and texture,the complete local binary pattern(CLBP)image feature descriptor is introduced for coal and rock image recognition.Given that the original algorithm oversimplifies local texture features by ignoring imaging information from higher-order pixels and the concave and convex areas between adjacent sampling points,this paper proposes a higher-order differential median CLBP image feature descriptor to replace the original CLBP center pixel gray with a local gray median,and replace the binary differential with a second-order differential.Meanwhile,for the high dimensionality of CLBP descriptor histogram and feature redundancy,deep learning perceptual field theory is introduced to realize data nonlinear dimensionality reduction and deep feature extraction.With relevant experiments conducted,the following conclusion can be drawn:(1)Compared with that of the original CLBP,the recognition accuracy of the improved CLBP algorithm is greatly improved and finally stabilized above 94.3%under strong noise interference;(2)Compared with that of the original CLBP model,the single image recognition time of the coal rock image recognition model fusing the improved CLBP and the receptive field theory is 0.0035 s,a reduction of 71.0%;compared with the improved CLBP model(without the fusion of receptive field theory),it can shorten the recognition time by 97.0%,but the accuracy rate still maintains more than 98.5%.The method offers a valuable technical reference for the fields of mineral development and deep mining.

Stability analysis of a liquid crystal elastomer self-oscillator under a linear temperature field

Self-oscillating systems abound in the natural world and offer substantial potential for applications in controllers,micro-motors,medical equipments,and so on.Currently,numerical methods have been widely utilized for obtaining the characteristics of self-oscillation including amplitude and frequency.However,numerical methods are burdened by intricate computations and limited precision,hindering comprehensive investigations into self-oscillating systems.In this paper,the stability of a liquid crystal elastomer fiber self-oscillating system under a linear temperature field is studied,and analytical solutions for the amplitude and frequency are determined.Initially,we establish the governing equations of self-oscillation,elucidate two motion regimes,and reveal the underlying mechanism.Subsequently,we conduct a stability analysis and employ a multi-scale method to obtain the analytical solutions for the amplitude and frequency.The results show agreement between the multi-scale and numerical methods.This research contributes to the examination of diverse self-oscillating systems and advances the theoretical analysis of self-oscillating systems rooted in active materials.

Discrete Wavelet Multi-scale Decomposition of the Temporal Gravity Variations in North China

On the basis of the absolute and relative gravity observations in North China,spatial dynamic variation of regional gravity fields is obtained. A multi-scale decomposition technique is used to separate anomalies at different depths,and give some explanation to gravity variation at different time space scales. Gravity variation trends in North China are improved. Based on this result and the analysis of wavelet power spectrum,the images of the depth of wavelet approximation and detail are obtained. The results obtained are of scientific significance for the deep understanding of potential seismic risk in North China from gravity variations in different time space scales.

基于双通路视觉系统的自适应轮廓检测模型

在轮廓检测领域,背景纹理的干扰容易造成轮廓提取不完整。针对这一问题,本文提出了一种基于双通路视觉系统的自适应轮廓检测模型。首先从皮层下通路的信息采集与评估过程出发,对图像整体的显著性进行评估,以此获得轮廓信息的可能性分布;然后采用自适应尺度的高斯导函数对经典视觉通路中感受野的动态特性进行模拟,加强了模型对轮廓细节的捕获;最后在外周抑制算法的基础上,结合像素的空间分布对所有边缘的稀疏性进行度量,更加准确地区分了轮廓和纹理边缘。实验结果表明,本文模型可以有效抑制背景纹理,提升轮廓连续性,具有较好的轮廓检测性能。

基于改进YOLOv5的遥感图像目标检测

目前目标检测技术虽然已经趋于成熟,但是对遥感图像的检测仍存在不少挑战。针对遥感图像的背景复杂、目标尺度差异大、目标方向任意等特点造成目标检测精度低下的问题,提出一种基于改进YOLOv5的遥感图像目标检测算法。首先,构建一种联合注意力的多尺度特征增强网络,充分融合高低层特征,使特征层具有语义信息的同时包含丰富的细节信息,并在融合过程中利用设计的特征聚焦模块帮助模型选择关键特征,抑制无关信息。其次,使用感受野模块(RFB)对融合后的特征图进行更新,扩大特征图的感受野,减少特征信息损失。最后,对目标增加旋转角度,并采用圆形平滑标签将回归问题转化成分类问题,提高遥感目标定位的准确性。在用于航拍图像目标检测的大规模数据集(DOTA)上的实验结果表明,与YOLOv5算法相比,所提算法的交并比(Io U)为0.5和0.5~0.95时的平均精度均值(m AP@0.5和m AP@0.5∶0.95)分别提高了7.3和3.3个百分点,能够明显提高复杂背景下遥感图像目标的检测精度,并改善对遥感目标的漏检和误检情况。

基于Transformer的多尺度遥感语义分割网络

为了提升遥感图像语义分割效果,本文针对分割目标类间方差小、类内方差大的特点,从全局上下文信息和多尺度语义特征2个关键点提出一种基于Transformer的多尺度遥感语义分割网络(muliti-scale Transformer network,MSTNet)。其由编码器和解码器2个部分组成,编码器包含基于Transformer改进的视觉注意网络(visual attention network,VAN)主干和基于空洞空间金字塔池化(atrous spatial pyramid pooling, ASPP)结构改进的多尺度语义特征提取模块(multi-scale semantic feature extraction module, MSFEM)。解码器采用轻量级多层感知器(multi-layer perception,MLP)配合编码器设计,充分分析所提取的包含全局上下文信息和多尺度表示的语义特征。MSTNet在2个高分辨率遥感语义分割数据集ISPRS Potsdam和LoveDA上进行验证,平均交并比(mIoU)分别达到79.50%和54.12%,平均F1-score(m F1)分别达到87.46%和69.34%,实验结果验证了本文所提方法有效提升了遥感图像语义分割的效果。

基于多尺度特征融合的绝缘子缺陷程度检测

针对绝缘子不同程度缺陷特征相似、像素信息少、不同程度缺陷检测效果不佳的问题,提出了一种基于多尺度特征融合的绝缘子缺陷程度检测网络(multi-scale feature fusion defect degree detection network,MFFD3Net)。该网络采用重构的ResNeSt50架构提高了对绝缘子缺陷程度数据集的特征提取能力。设计了基于反卷积的多尺度特征融合模块,丰富了不同尺寸特征图的表达能力,提高了对不同尺度目标的检测性能。同时,在输入检测模块的浅层特征图后增加多感受野的特征提取模块(receptive field block,RFB),使得更多绝缘子缺陷信息进入有效感受野,对最终特征图产生影响,提升不同程度绝缘子缺陷的检测精度。MFFD3Net在绝缘子缺陷程度数据集上的全类平均精度达到85.02%,其中绝缘子轻微破损与绝缘子轻微闪络小目标的检测精度分别为78.37%、79.98%,能够完成不同程度绝缘子缺陷的识别与定位。因此,该文提出的MFFD3Net对于完善电力系统故障预警、保障电网安全稳定运行具有重要意义。

基于改进U^(2)-Net网络的金属涂层剥落与腐蚀图像分割方法

针对金属涂层缺陷图像分割中存在特征提取能力弱和分割精度低的问题,提出了一种改进的U^(2)-Net分割模型。首先,在U型残差块(RSU)中嵌入改进的增大感受野模块(receptive field block light,RFB_l),组成新的特征提取层,增强对细节特征的学习能力,解决了网络由于感受野受限造成分割精度低的问题;其次,在U^(2)-Net分割模型的解码阶段引入有效的边缘增强注意力机制(contour enhanced attention,CEA),抑制网络中的冗余特征,获取具有详细位置信息的特征注意力图,增强了边界与背景信息的差异性,从而达到更精确的分割效果。实验结果表明,该模型在两个金属涂层剥落与腐蚀数据集上的平均交并比、准确率、查准率、召回率和F_1-measure分别达到80.36%、96.29%、87.43%、84.61%和86.00%,相比于常用的SegNet、U-Net以及U^(2)-Net分割网络的性能都有较大提升。

基于改进SSD模型的柑橘叶片病害轻量化检测模型

针对当前目标检测算法存在模型占比大,对柑橘叶片病害检测速度较慢、精度较低等问题,提出了一种基于改进SSD(single shot multibox detector)的柑橘叶片病害轻量化检测方法。引入了轻量化卷积神经网络MobileNetV2作为SSD网络的骨架,以减小模型规模、提高检测速度。引入感受野模块(receptive field block,RFB)来扩大浅层特征感受野,以提高模型对小目标的检测效果。并引入CA(coordinate attention)注意力机制,以强化不同深度的特征信息,进一步提升柑橘叶片病害的识别精度。结果表明,与VGG16-SSD相比,改进模型(MR-CA-SSD)在柑橘叶片病害检测上平均精度均值(mAP)提升4.4百分点,模型占比减小52.3 MB,每秒检测帧数提升3.15。MR-CA-SSD综合性能也优于YOLOv4、CenterNet、Efficientnet-YoloV3等模型。该改进模型可实现对柑橘叶片病害的快速准确诊断,有助于对病害部位及时精准施药。

基于改进YOLOv5s的面向自动驾驶场景的道路目标检测算法

在复杂道路场景中检测车辆、行人、自行车等目标时,存在因多尺度目标及部分遮挡易造成漏检及误检等情况,提出一种基于改进YOLOv5s的面向自动驾驶场景的道路目标检测算法。首先,利用深度可分离卷积替换部分普通卷积,减少模型的参数量以提升检测速度。其次,在特征融合网络中引入基于感受野模块(receptive field block,RFB)改进的RFB-s,通过模仿人类视觉感知,增强特征图的有效感受野区域,提高网络特征表达能力及对目标特征的可辨识性。最后,使用自适应空间特征融合(adaptively spatial feature fusion,ASFF)方式以提升PANet对多尺度特征融合的效果。实验结果表明,在PASCAL VOC数据集上,所提算法检测平均精度均值相较于YOLOv5s提高1.71个百分点,达到84.01%,在满足自动驾驶汽车实时性要求的前提下,在一定程度上减少目标检测时的误检及漏检情况,有效提升模型在复杂驾驶场景下的检测性能。

基于改进SwiftNet的堆场图像实时分割网络

在堆场环境下,实时图像语义分割可以提供直观的场景类别信息。为节约工控机等边缘设备的硬件资源以及为多源信息融合提供图像语义类别信息,提出一种轻量化的实时语义分割网络模型。首先提出基于空间注意力引导的上采样融合模块,通过引入空间注意力和残差注意力结构设计一种轻量化的解码器,在上采样过程中还原空间细节,抑制冗余信息,进而融合不同来源的特征图;其次提出一种轻量化的级联空洞空间金字塔模块,利用级联的空洞卷积单元增大网络感受野,有效提取多尺度特征;最后使用通道分离、通道混洗、通道池化等操作,降低多尺度聚合过程中的计算开销。在公开数据集Camvid上,该模型的平均交并比(MIoU)为70.1%,推理速度为146.3帧/s,分割精度和推理速度优于ENet、ICNet等模型,消融实验结果也证明了所提各模块的有效性;在实际堆场图像数据集上,该模型的MIoU为93.5%,推理速度为123.8帧/s,证明模型结构具有良好的泛化性能。

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%.

多感受野特征自适应融合及动态损失调整的初烤烟叶等级检测

初烤烟叶等级的快速准确检测对开发烟叶智能分级设备以促进农产品精细化管理有着重要意义。针对相似度较高但等级不同的初烤烟叶难以区分的问题,本文提出多感受野特征自适应融合及动态损失调整的初烤烟叶等级检测网络(Flue-cured Tobacco Leaf Grade Detection Network,FTGDNet)。首先,FTGDNet采用CSPNet作为特征提取主干网络,采用GhostNet作为辅助特征提取网络以增强模型的特征提取能力;其次,在主干网络末端嵌入显式视觉中心瓶颈模块(Explicit Visual Center Bottleneck module,EVCB)以实现全局特征信息与局部细节特征信息融合;然后,构建多感受野特征自适应融合模块(Multi-Receptive Field Feature Adaptive Fusion module,MRFA_d),利用注意力特征融合机制(Attention Feature Fusion,AFF)将不同感受野特征图进行自适应加权融合,在增强模型局部感受野的同时突出有效通道信息;最后,设计了一种新的定位损失函数(More Complete IoU Loss,MCIoU_Loss),结合预测框与真实框面积损失以解决在回归定位过程中二者宽高比相等且中心点重合时CIoU_Loss性能退化导致定位精度下降问题,此外,引入矩形相似度衰减系数在训练过程中对真实框与预测框的相似度判别项进行动态调整,加快模型拟合。实验结果表明,FTGDNet对十个等级的初烤烟叶的验证精度达到90.0%,测试精度达到87.4%,且推理时间仅为12.6 ms。相较于多种先进目标检测算法,FTGDNet具有更高的检测精度和更快的检测速度,可为高精度初烤烟叶等级检测提供关键技术支撑。

多尺度残差挤压和激励的双U舌图分割网络

在图像分割中,单次卷积和频繁的池化操作容易产生冗余信息或遗漏关键信息.本文设计了一种多尺度的残差挤压和激励注意力的双U形分割网络(MRSEA-DUNet)来解决上述问题.首先,该网络由两个U形的网络组成,分别是预编码网络和精确分割网络.为避免频繁的卷积和池化操作导致信息丢失或产生无效信息,提出了具有不同大小感受野的阶梯卷积模块(SCM),并采用并行结构,可以在不同尺度上捕获更丰富、更详细的特征.其次,还设计了一种残差挤压和激励注意力模块(RSEAM),可以通过空间和通道提高有效特征增益,消除冗余信息,并且提高了模型的整体鲁棒性.最后,为了减少了降采样操作的数量,简化了纵向复杂度.实验结果表明,本文MRSEA-DUNet模型的精度、Jaccard系数和Dice系数分别达到0.995 4、 0.979 4和0.989 5,均优于其他7种主流模型,优化了分割效果.

改进YOLOX的夜间安全帽检测算法

安全帽检测是保障建筑施工现场安全的一个有效手段。为保证暗光条件下图像分辨度,塔机吊钩摄像头夜间经常需采集灰度图像。由于摄像头晃动和人员走动,安全帽目标区域还经常会出现模糊现象。为解决模糊灰度图像中目标特征丢失所导致的检测精度下降问题,以YOLOX为基准模型,提出一种用于夜间安全帽检测的特征增强和回归权重自适应YOLOX(feature enhancement and regression weight adaptive,FERWA-YOLOX)算法。算法在输入层增加了融合不同大小感受野的多尺度残差(multi-scale residuals,MSR)模块,在同层网络中融合更多局部特征,降低目标局部模糊带来的影响;在解耦头的分类分支增加并行池化通道注意力(parallel pooling channel attention,PPCA)模块,弥补因目标颜色特征丢失所导致的网络分类能力的下降;设计了一种带双惩罚项的损失函数(double penalty items-Siou,DPI-Siou),自适应地降低形状固定目标的形状损失和模糊目标在回归时的权重,提高网络的检测精度。实验结果表明,FERWA-YOLOX较原YOLOX算法,mAP提升了4.88个百分点,参数量仅提升0.5 MB,且满足夜间实时检测需求。

基于改进Yolov5s的水稻叶病检测方法

水稻叶病防治在提高水稻产量中具有重要作用,针对水稻叶病人工检查速度慢、主观性高的问题,提出一种基于改进Yolov5s的水稻叶病目标检测方法。采用K-means聚类算法得到先验框尺寸,增强检测模型对水稻叶病的适应性;将轻量级空间注意力与通道注意力融合,对高层语义特征信息增强,增强模型对病害信息的感知度;并结合特征金字塔网络,融合多尺度感受野获取目标上下文信息,有效地增强模型对目标周围特征的提取,提高目标检测的准确度。试验结果表明:改进后的Yolov5s算法平均检测精度(IOU=0.5)提高4.3%,F1值提高5.3%,帧率FPS为58.7 f/s。有效提升Yolov5s算法对水稻叶病的检测精度,达到实时检测的需求。

基于改进UNet3+的岩心图像颗粒提取算法

在石油勘探过程中,岩心颗粒是研究地质层序、评估油气含量以及认识地质构造的有效资料,对岩心颗粒图像进行颗粒提取有利于地质研究人员后续的深入分析.岩心颗粒图像通常存在颗粒边缘模糊、背景与颗粒色彩复杂的问题.为了改善岩心颗粒提取的效果,本文设计了一种基于改进UNet3+的岩心图像颗粒提取算法.该算法在UNet3+的每个编码层后加入感受野模块(RFB)来扩大网络的感受野,从而有效地解决网络因感受野受限而导致的分割精度低的问题,并在RFB模块后嵌入了卷积块注意力模块(CBAM)使网络更加精确地聚焦于目标区域,提高目标区域的特征权重.实验结果表明,改进后的算法在岩心颗粒图像上具有良好的分割效果,相比原始UNet3+网络,分别在mIoU、mPA和FWIoU上提升了5.43%、2.99%和5.34%.

面向无人机视角下小目标检测的YOLOv8s改进模型

从无人机视角进行目标检测,面临图像目标小、分布密集、类别不均衡等难点,且由于无人机的硬件条件限制了模型的规模,导致模型的准确率偏低。提出一种融合多种注意力机制的YOLOv8s改进模型,在骨干网络中引入感受野注意力卷积和CBAM(concentration-based attention module)注意力机制改进卷积模块,解决注意力权重参数在感受野特征中共享问题的同时,在通道和空间维度加上注意力权重,增强特征提取能力;通过引入大型可分离卷积注意力思想,改造空间金字塔池化层,增加不同层级特征间的信息交融;优化颈部结构,增加具有丰富小目标语义信息的特征层;使用inner-IoU损失函数的思想改进MPDIoU(minimum point distance based IoU)函数,以innerMPDIoU代替原损失函数,提升对困难样本的学习能力。实验结果表明,改进后的YOLOv8s模型在VisDrone数据集上mAP、P、R分别提升了16.1%、9.3%、14.9%,性能超过YOLOv8m,可以有效应用于无人机平台上的目标检测任务。