Image recognition and empirical application of desert plant species based on convolutional neural network

In recent years,deep convolution neural network has exhibited excellent performance in computer vision and has a far-reaching impact.Traditional plant taxonomic identification requires high expertise,which is time-consuming.Most nature reserves have problems such as incomplete species surveys,inaccurate taxonomic identification,and untimely updating of status data.Simple and accurate recognition of plant images can be achieved by applying convolutional neural network technology to explore the best network model.Taking 24 typical desert plant species that are widely distributed in the nature reserves in Xinjiang Uygur Autonomous Region of China as the research objects,this study established an image database and select the optimal network model for the image recognition of desert plant species to provide decision support for fine management in the nature reserves in Xinjiang,such as species investigation and monitoring,by using deep learning.Since desert plant species were not included in the public dataset,the images used in this study were mainly obtained through field shooting and downloaded from the Plant Photo Bank of China(PPBC).After the sorting process and statistical analysis,a total of 2331 plant images were finally collected(2071 images from field collection and 260 images from the PPBC),including 24 plant species belonging to 14 families and 22 genera.A large number of numerical experiments were also carried out to compare a series of 37 convolutional neural network models with good performance,from different perspectives,to find the optimal network model that is most suitable for the image recognition of desert plant species in Xinjiang.The results revealed 24 models with a recognition Accuracy,of greater than 70.000%.Among which,Residual Network X_8GF(RegNetX_8GF)performs the best,with Accuracy,Precision,Recall,and F1(which refers to the harmonic mean of the Precision and Recall values)values of 78.33%,77.65%,69.55%,and 71.26%,respectively.Considering the demand factors of hardware equipment and inference time,Mobile NetworkV2 achieves the best balance among the Accuracy,the number of parameters and the number of floating-point operations.The number of parameters for Mobile Network V2(MobileNetV2)is 1/16 of RegNetX_8GF,and the number of floating-point operations is 1/24.Our findings can facilitate efficient decision-making for the management of species survey,cataloging,inspection,and monitoring in the nature reserves in Xinjiang,providing a scientific basis for the protection and utilization of natural plant resources.

Real-Time Violent Action Recognition Using Key Frames Extraction and Deep Learning

Violence recognition is crucial because of its applications in activities related to security and law enforcement.Existing semi-automated systems have issues such as tedious manual surveillances,which causes human errors and makes these systems less effective.Several approaches have been proposed using trajectory-based,non-object-centric,and deep-learning-based methods.Previous studies have shown that deep learning techniques attain higher accuracy and lower error rates than those of other methods.However,the their performance must be improved.This study explores the state-of-the-art deep learning architecture of convolutional neural networks(CNNs)and inception V4 to detect and recognize violence using video data.In the proposed framework,the keyframe extraction technique eliminates duplicate consecutive frames.This keyframing phase reduces the training data size and hence decreases the computational cost by avoiding duplicate frames.For feature selection and classification tasks,the applied sequential CNN uses one kernel size,whereas the inception v4 CNN uses multiple kernels for different layers of the architecture.For empirical analysis,four widely used standard datasets are used with diverse activities.The results confirm that the proposed approach attains 98%accuracy,reduces the computational cost,and outperforms the existing techniques of violence detection and recognition.

基于YOLO神经网络构建压力性损伤自动检测和分期的人工智能模型

背景随着人口老龄化,压力性损伤(PI)的发病率逐渐增加,这不仅严重影响了患者的生存质量,还增加了医保支出。然而,PI的早期发现和准确分期极大地依赖于专业培训。目的构建并测试一个用于PI自动检测和分期的人工智能模型,以提高PI诊断的实时性、准确性和客观性。方法选取常熟市第一人民医院压疮电子化管理系统中2021年1月—2024年2月的693张PI图像,将图像随机划分为训练集(551张)和测试集(142张),并按照2019年美国压疮咨询委员会(NPUAP)制订的PI预防和治疗指南分为6期,包括:Ⅰ期154张、Ⅱ期188张、Ⅲ期160张、Ⅳ期82张、深部组织损伤期57张、不可分期52张。利用基于5种不同版本的YOLOv8[nano(n)、small(s)、medium(m)、large(l)和extra large(x)]神经网络和迁移学习,建立针对PI的深度学习目标检测模型。模型评价指标包括精确度、准确率、灵敏度、特异度及检测速度等。最后,通过Ultralytics Hub平台将模型部署到手机应用程序(App)中,实现AI模型在临床工作中的应用。结果在对包含142张PI图像的测试集进行评估时,YOLOv8l版本在确保高精确度(0.827)的同时,也展现了较快的推理速度(68.49帧/s),与其他YOLO版本相比,在精确度与速度之间取得了最佳的平衡。具体而言,其在所有类别上的整体准确率为93.18%,灵敏度为76.52%,特异度为96.29%,假阳性率为3.72%。在6个PI分期中,模型预测Ⅰ期的准确率最高,达到95.97%;预测Ⅱ期、Ⅲ期、Ⅳ期、深部组织损伤期、不可分期分别取得了91.28%、91.28%、91.95%、95.30%和93.29%的准确率。就处理速度而言,YOLOv8l处理142张图像的总耗时为2.07 s,平均每秒可处理68.49张PI图像。结论基于YOLOv8l网络的AI模型能够快速、准确地对PI进行检测和分期。将该模型部署到手机App中,能够在临床实践中便携使用,具有很大的临床应用潜力。

Non-Intrusive Load Identification Model Based on 3D Spatial Feature and Convolutional Neural Network

Load identification method is one of the major technical difficulties of non-intrusive composite monitoring. Binary V-I trajectory image can reflect the original V-I trajectory characteristics to a large extent, so it is widely used in load identification. However, using single binary V-I trajectory feature for load identification has certain limitations. In order to improve the accuracy of load identification, the power feature is added on the basis of the binary V-I trajectory feature in this paper. We change the initial binary V-I trajectory into a new 3D feature by mapping the power feature to the third dimension. In order to reduce the impact of imbalance samples on load identification, the SVM SMOTE algorithm is used to balance the samples. Based on the deep learning method, the convolutional neural network model is used to extract the newly produced 3D feature to achieve load identification in this paper. The results indicate the new 3D feature has better observability and the proposed model has higher identification performance compared with other classification models on the public data set PLAID.

基于深度学习方法的YOLO目标检测综述

目标检测是计算机视觉中的一项重要任务,其目标是从图像或视频中检测出并定位感兴趣的目标对象。这与图像分类不同,目标检测不仅需要确定图像中是否存在特定对象,还需要准确地标定对象的位置。YOLO(You Only Look Once)是将目标检测问题转化为一个回归问题,从而实现了从端到端的一种检测方法。与传统的两阶段的目标检测算法相比,单阶段的目标检测算法在速度上有很大的提升,从而实现的速度与准确性的平衡。该文主要是对YOLO系列算法的网络结构以及相关改进进行了详细的阐述。首先是对YOLO算法基本思想进行相关阐述,然后对YOLO中相关网络架构进行的相关阐述,包括YOLO V1,YOLO V2,YOLO V3,YOLO V4,YOLO V5,以及YOLOX YOLO V7,YOLO V8。

基于YOLO的钢缆表面损坏检测

为了解决检测钢缆表面损坏时检测设备资源有限、时间过长等问题,将深度学习的先进技术以及卷积神经网络(CNN)应用于钢缆表面损坏检测.提出了一种基于YOLO的缺陷检测网络模型,将GhostNet融入主干网络,并基于ShuffleNet及注意力机制提出了新的特征提取模块(ShuffleC3),再对Head部分进行剪枝改进.实验结果表明,改进后网络相比基线YOLOv5s的平均精度提高1.1%,参数量和计算量分别降低了43.4%和31%,模型大小减少了42.3%.可以在降低网络计算成本的同时,保持较高的识别精确度,更好地满足了对钢缆材料表面损坏检测的要求.

Advancing Crowd Object Detection: A Review of YOLO, CNN and ViTs Hybrid Approach*

One of the most basic and difficult areas of computer vision and image understanding applications is still object detection. Deep neural network models and enhanced object representation have led to significant progress in object detection. This research investigates in greater detail how object detection has changed in the recent years in the deep learning age. We provide an overview of the literature on a range of cutting-edge object identification algorithms and the theoretical underpinnings of these techniques. Deep learning technologies are contributing to substantial innovations in the field of object detection. While Convolutional Neural Networks (CNN) have laid a solid foundation, new models such as You Only Look Once (YOLO) and Vision Transformers (ViTs) have expanded the possibilities even further by providing high accuracy and fast detection in a variety of settings. Even with these developments, integrating CNN, YOLO and ViTs, into a coherent framework still poses challenges with juggling computing demand, speed, and accuracy especially in dynamic contexts. Real-time processing in applications like surveillance and autonomous driving necessitates improvements that take use of each model type’s advantages. The goal of this work is to provide an object detection system that maximizes detection speed and accuracy while decreasing processing requirements by integrating YOLO, CNN, and ViTs. Improving real-time detection performance in changing weather and light exposure circumstances, as well as detecting small or partially obscured objects in crowded cities, are among the goals. We provide a hybrid architecture which leverages CNN for robust feature extraction, YOLO for rapid detection, and ViTs for remarkable global context capture via self-attention techniques. Using an innovative training regimen that prioritizes flexible learning rates and data augmentation procedures, the model is trained on an extensive dataset of urban settings. Compared to solo YOLO, CNN, or ViTs models, the suggested model exhibits an increase in detection accuracy. This improvement is especially noticeable in difficult situations such settings with high occlusion and low light. In addition, it attains a decrease in inference time in comparison to baseline models, allowing real-time object detection without performance loss. This work introduces a novel method of object identification that integrates CNN, YOLO and ViTs, in a synergistic way. The resultant framework extends the use of integrated deep learning models in practical applications while also setting a new standard for detection performance under a variety of conditions. Our research advances computer vision by providing a scalable and effective approach to object identification problems. Its possible uses include autonomous navigation, security, and other areas.

一种基于YOLO v5的克氏原螯虾性别检测方法

针对传统人工判别克氏原螯虾性别效率低、成本高的问题,提出了一种基于YOLO v5的克氏原螯虾性别检测模型,实现了克氏原螯虾性别特征的自动判别。采用自主设计装置拍摄克氏原螯虾图像,使用Labelme工具进行基于雄虾交接器检测和基于区域特征检测两种方法的数据标注,在Pytorch框架下以Resnet-18为特征提取网络训练二分类模型,基于YOLO v5训练交接器检测和区域特征检测两种模型。结果表明:基于区域特征检测的模型具有较高的检测性能和准确性,能够高效、低成本地提取克氏原螯虾性别特征,对克氏原螯虾品种改良具有重要意义。

基于深度学习的YOLO目标检测综述

目标检测是计算机视觉领域的一个基础任务和研究热点。YOLO将目标检测概括为一个回归问题,实现端到端的训练和检测,由于其良好的速度-精度平衡,近几年一直处于目标检测领域的领先地位,被成功地研究、改进和应用到众多不同领域。该文对YOLO系列算法及其重要改进、应用进行了详细调研。首先,系统地梳理了YOLO家族及重要改进,包含YOLOv1-v4,YOLOv5,Scaled-YOLOv4,YOLOR和最新的YOLOX。然后,对YOLO中重要的基础网络,损失函数进行了详细的分析和总结。其次,依据不同的改进思路或应用场景对YOLO算法进行了系统的分类归纳。例如,注意力机制、3D、航拍场景、边缘计算等。最后,总结了YOLO的特点,并结合最新的文献分析可能的改进思路和研究趋势。

基于改进YOLO和迁移学习的水下鱼类目标实时检测

为了实现非限制环境中水下机器人基于视频图像的水下鱼类目标快速检测,提出基于改进YOLO和迁移学习的水下鱼类目标实时检测算法.针对YOLO网络的不足,设计适合水下机器人嵌入式系统计算能力的精简YOLO网络(Underwater-YOLO).利用迁移学习方法训练Underwater-YOLO网络,克服海底鱼类已知样本集有限的限制.利用基于限制对比度自适应直方图均衡化的水下图像增强预处理算法,克服水下图像的降质问题.利用基于帧间图像结构相似度的选择性网络前向计算策略,提高视频帧检测速率.实验表明,文中算法能实现在非限制环境下海底鱼类目标的实时检测.相比YOLO,文中算法对海底鱼类小目标和重叠目标具有更好的检测性能.

基于改进YOLOV3-Tiny的海面船舰目标快速检测

为实现海面船舰目标的快速、准确检测,提出一种改进的船舰目标检测算法。在网络结构方面根据船舰目标的特点,对浅层信息进行强化重构以降低小目标的漏检率,同时引入改进的残差网络增加网络深度和降低网络参数计算量,并且采用金字塔网络进行多尺度特征融合,以兼顾图像中大小船舰目标的检测性能。在网络训练中利用迁移学习策略进行网络模型的训练,以克服船舰图像样本集有限的问题。在视频检测中利用帧间图像结构相似度进行选择性网络前向计算,以提高视频帧检测速率。实验结果表明,该算法海面船舰目标检测的准确率达到92.4%,较YOLOV3-Tiny提高7个百分点,召回率达到88.6%,且在CPU平台上船舰目标的检测速度达到12 frame/s。

基于改进YOLO V3的钢轨伤损B显图像识别研究

针对钢轨探伤普遍存在的判伤时间长、漏报率高等问题,提出一种改进的YOLO V3算法。首先对YOLO V3网络结构进行改进,包括增加极小尺度检测层、添加SPP模块和SE模块等,然后对B显图像数据进行数据增强和杂波滤除处理,采用K-means聚类算法对数据集中的边界框进行聚类分析,获得12个先验框;其次对改进的YOLO V3网络进行参数调整,使用B显图像数据集对改进YOLO V3模型进行训练,最终实现对B显图像中的核伤、轨底伤损、表面伤损、异常螺孔四类异常数据集和断面、接头、螺孔、焊缝四类正常数据集的定位和识别功能。试验对17601张B显图片进行检测。结果表明,提出的钢轨伤损识别模型的平均精度为92.3%,检测速度达到44 ms/张,能够较为准确快速地检测钢轨伤损。

基于YOLO模型的小麦外观分类算法研究

小麦种植广泛且营养丰富,其品质问题需要重点关注。小麦品质的衡量指标主要是不完善粒占比。为此,需要对小麦颗粒进行分类识别。提出了1种基于你只看一次(YOLO)模型的小麦外观自动分类算法,创新性地将YOLO模型应用于小麦外观分类场景。对采集得到的小麦样本图像切割、筛选、扩充和标记,构建了完善粒与不完善粒图像库。对YOLO网络进行了训练,利用训练后的模型对麦粒图像进行了测试,实现了完善粒、不完善粒分别为91.7%、87.1%的分类准确率。这种自动分拣麦粒的检验方法避免了人工视觉疲劳后的误判,而且检测效率显著提高,为小麦外观分类研究提供了新的思路。

实时目标检测算法YOLO的批再规范化处理

实时目标检测YOLO(you only look once)算法存在检测精度低和网络模型训练速度慢等问题,对此,结合批再规范化算法处理小批样本以及非独立同分布数据的优势,引入批再规范化处理对YOLO网络结构予以改进,即把卷积层中经卷积运算产生的特征图看做神经元,并对其进行规范化处理。同时,在网络结构中移除dropout,并增大网络训练的学习率。实验结果表明,该改进算法相对于原YOLO算法具有更高的检测精度、更快的实时检测速度,并且通过适当设置批样本大小可使网络模型在训练时间和硬件设备方面成本有一定的降低。

基于改进YOLO V3的肺结节检测方法

针对肺结节占CT图像比例小、形状不规则及直接应用YOLO V3算法进行肺结节检测效果不佳的问题,提出基于改进YOLO V3的肺结节检测方法。首先进行重采样和肺实质分割等预处理操作。然后修改YOLO V3的基础网络结构,调整骨干网络和检测网络的结构单元数量;使用Mish激活函数替换Leaky ReLU激活函数,引入含有空洞卷积的感受野模块层;修改损失函数。最后使用改进的YOLO V3方法进行肺结节检测,完成对比实验。在LIDC-IDRI数据集上得到了88.89%的准确率和94.73%的高敏感度,实验结果表明该方法能够有效检测肺结节。

适用于嵌入式平台的E-YOLO人脸检测网络研究

针对现有人脸检测深度学习算法计算量大,难以移植到嵌入式平台,无法满足移动设备实时性和便捷性需求的问题,提出一种基于YOLO(You Only Look Once)算法的适用于嵌入式平台的小型人脸检测网络E-YOLO(Enhance-YOLO)。借鉴YOLO算法的思想,将人脸检测问题转换为回归问题,将待检测的图像均分为S×S个单元格,每个单元格检测落在单元格内的目标。通过修改YOLO网络模型中的卷积神经网络结构,提高其检测的准确性,同时减少网络结构中卷积核的数目,降低模型的大小。实验结果表明,E-YOLO模型大小为43MB,视频的检测帧率为26FPS,在WIDERFACE和FDDB数据集上均有较高的准确率和检测速度,可以实现在嵌入式平台下的实时人脸检测。

胎体钢丝帘线缺陷的CD-YOLO分割算法应用

针对目前国内大环境下子午线轮胎胎体钢丝帘线缺陷检测的识别困难、效率低下的问题,提出以下几点的设计方案,引入YOLOv5神经网络降低检测成本,并且在YOLOv5中引入交叉注意力机制(CBAM)和深度可分离卷积机制,增强特征图像的表达能力,降低网络整体参数量。搭建由Python语言编写的软件平台,控制下位机的各项参数,同时将网络作为接口写入软件,完成可自动化连续目标检测的功能,可用于投入子午线轮胎的实际检测。实验对比数据显示,检测方法的精准度达到了96.17%,传输速度达到了52.93 fps。

基于YOLO算法与深度学习的证件质量检测系统

针对证件生产过程中表面人工质检时存在的易疲劳、易漏检、检测效率低等难题,提出一种基于深度学习结合机器视觉的证件质量检测方法。首先采用摄像头采集证件表面图像,对证件照片图像进行仿射变换、滤波、特征提取等处理,然后根据个人信息生成打印标准图像,与证件表面图像进行图像配准、形态学相减和模版匹配操作,检测出证件表面的文字不正确、文字打印不完整、重影等缺陷,最后通过改进的YOLO目标检测网络检测出照片打印不完整、覆膜不完整、杂质、黑边等缺陷。

基于YOLOv3的手势识别技术

基于YOLOv3的手势识别检测系统使用darknet53.conv.74模型进行训练与学习,通过对输入图像进行平滑以及二值化处理分离不必要图像信息,提高识别准确率,实现视频实时手势识别模型,然后利用Python Tkinter模块开发出图形交互界面。结果表明,模型在识别精确度上能达到76.76%,有着目前主流深度学习目标检测算法相当的精确度,在识别速度上优于其他目前主流深度学习目标检测算法,在处理自然交互信息方面具有优势,为人机交互提供有效手段。

基于YOLO算法的眼底图像视盘定位方法

视盘的各个参数是衡量眼底健康状况和病灶的重要指标,视盘的检测和定位对于观察视盘的形态尤为重要。在以往的视盘定位研究中,主要根据视盘的形状、亮度、眼底血管的走向等特征使用图像处理的方法对眼底图像中视盘进行定位。由于人为因素影响较大,特征提取时间较长,且视盘定位效率低,因此提出一种基于YOLO算法的眼底图像视盘定位方法。利用YOLO算法将眼底图像划分为N×N的格子,每个格子负责检测视盘中心点是否落入该格子中,通过多尺度的方式和残差层融合低级特征对视盘进行定位,得到不同大小的边界框,最后通过非极大抑制的方式筛选出得分最高的边界框。通过在3个公开的眼底图像数据集(DRIVE、DRISHTI-GS1和MESSIDOR)上,对所提出的视盘定位方法进行测试,定位准确率均为100%,实验同时定位出视盘的中心点坐标,与标准中心点的平均欧氏距离分别为22.36 px、2.52 px、21.42 px,验证了该方法的准确性和通用性。