基于改进YOLO-v3的风力机叶片表面损伤检测识别

为对风力机叶片损伤状态进行有效检测,提出一种基于改进YOLO-v3算法的风力机叶片表面损伤检测识别技术。根据风力机叶片损伤区域特点,对网络中锚框(anchor)的尺度进行调整优化;在特征提取网络后引入基于注意力机制的挤压与激励网络(squeeze and excitation networks,SENet)结构,使YOLO-v3算法更加关注与目标相关的特征通道,提升网络性能。结果表明,改进后算法的平均精度为84.42%,较原YOLO-v3算法提升了6.14%,检测时间减少了21 ms,改进后的YOLO-v3算法能较好地识别出风力机叶片表面损伤。

基于YOLO-V3算法的加油站不安全行为检测

为控制加油站火灾爆炸风险目标,结合事故统计和故障树分析方法,提出一种基于YOLO-V3算法的加油站不安全行为检测模型。首先在收集90起加油站火灾爆炸事故的基础上,统计分析加油站火灾爆炸事故的点火源;其次构建加油站火灾爆炸故障树,计算各基本事件的结构重要度,并确定加油站危险性较高的不安全行为;然后采用现场采集和模拟的方法收集加油站不安全行为图像数据,利用数据增强方法构建加油站不安全行为图像数据集;最后基于深度学习的方法构建加油站不安全行为检测模型,经过1000次训练迭代后得到最终模型。研究结果表明:引起加油站火灾爆炸事故的不安全行为主要有抽烟、打电话等;训练得到的检测模型在测试集上对抽烟、打电话和正常行为检测类别的平均检测精度分别为67%、85%和77%,模型的平均检测精度均值为84%。

基于改进YOLO-v3的无人机遥感图像农村地物分类

随着新农村的建设,农业用地的规划和利用也变得至关重要。针对传统地物分类方法效率低、自动化程度不高等问题,提出基于YOLO-v3改进模型的农村地物检测分类方法。该方法在YOLO-v3的Res4结构的基础上添加SPP层,有效地提升了模型对多尺寸目标的适应能力,在一定程度上提高了模型的泛化能力。同时,在FPN层添加PAN结构,增加了定位信息的语义特征,对于模型的检测精度提升明显。实验结果表明,提出的改进YOLO-v3模型在Air数据集的mAP达到了0.726,相较YOLO-v3模型,在精度、检测效率和模型的泛化能力上都有所提升。

Improvement of Binocular Reconstruction Algorithm for Measuring 3D Pavement Texture Using a Single Laser Line Scanning Constraint

The dense and accurate measurement of 3D texture is helpful in evaluating the pavement function.To form dense mandatory constraints and improve matching accuracy,the traditional binocular reconstruction technology was improved threefold.First,a single moving laser line was introduced to carry out global scanning constraints on the target,which would well overcome the difficulty of installing and recognizing excessive laser lines.Second,four kinds of improved algorithms,namely,disparity replacement,superposition synthesis,subregion segmentation,and subregion segmentation centroid enhancement,were established based on different constraint mechanism.Last,the improved binocular reconstruction test device was developed to realize the dual functions of 3D texture measurement and precision self-evaluation.Results show that compared with traditional algorithms,the introduction of a single laser line scanning constraint is helpful in improving the measurement’s accuracy.Among various improved algorithms,the improvement effect of the subregion segmentation centroid enhancement method is the best.It has a good effect on both overall measurement and single pointmeasurement,which can be considered to be used in pavement function evaluation.

Structural plane recognition from three-dimensional laser scanning points using an improved region-growing algorithm based on the robust randomized Hough transform

The staggered distribution of joints and fissures in space constitutes the weak part of any rock mass.The identification of rock mass structural planes and the extraction of characteristic parameters are the basis of rock-mass integrity evaluation,which is very important for analysis of slope stability.The laser scanning technique can be used to acquire the coordinate information pertaining to each point of the structural plane,but large amount of point cloud data,uneven density distribution,and noise point interference make the identification efficiency and accuracy of different types of structural planes limited by point cloud data analysis technology.A new point cloud identification and segmentation algorithm for rock mass structural surfaces is proposed.Based on the distribution states of the original point cloud in different neighborhoods in space,the point clouds are characterized by multi-dimensional eigenvalues and calculated by the robust randomized Hough transform(RRHT).The normal vector difference and the final eigenvalue are proposed for characteristic distinction,and the identification of rock mass structural surfaces is completed through regional growth,which strengthens the difference expression of point clouds.In addition,nearest Voxel downsampling is also introduced in the RRHT calculation,which further reduces the number of sources of neighborhood noises,thereby improving the accuracy and stability of the calculation.The advantages of the method have been verified by laboratory models.The results showed that the proposed method can better achieve the segmentation and statistics of structural planes with interfaces and sharp boundaries.The method works well in the identification of joints,fissures,and other structural planes on Mangshezhai slope in the Three Gorges Reservoir area,China.It can provide a stable and effective technique for the identification and segmentation of rock mass structural planes,which is beneficial in engineering practice.

Asymmetric image encryption algorithm based on a new three-dimensional improved logistic chaotic map

Based on some analyses of existing chaotic image encryption frameworks and a new designed three-dimensional improved logistic chaotic map(3D-ILM),an asymmetric image encryption algorithm using public-key Rivest–Shamir–Adleman(RSA)is presented in this paper.In the first stage,a new 3D-ILM is proposed to enhance the chaotic behavior considering analysis of time sequence,Lyapunov exponent,and Shannon entropy.In the second stage,combined with the public key RSA algorithm,a new key acquisition mathematical model(MKA)is constructed to obtain the initial keys for the 3D-ILM.Consequently,the key stream can be produced depending on the plain image for a higher security.Moreover,a novel process model(NPM)for the input of the 3D-ILM is built,which is built to improve the distribution uniformity of the chaotic sequence.In the third stage,to encrypt the plain image,a pre-process by exclusive OR(XOR)operation with a random matrix is applied.Then,the pre-processed image is performed by a permutation for rows,a downward modulo function for adjacent pixels,a permutation for columns,a forward direction XOR addition-modulo diffusion,and a backward direction XOR addition-modulo diffusion to achieve the final cipher image.Moreover,experiments show that the the proposed algorithm has a better performance.Especially,the number of pixels change rate(NPCR)is close to ideal case 99.6094%,with the unified average changing intensity(UACI)close to 33.4634%,and the information entropy(IE)close to 8.

一种改进型1-3-2压电复合材料的研究

高质量的压电换能器需要具备较高的机电耦合系数和灵敏度。该文在传统型1-3-2压电复合材料的基础上提出了一种改进型1-3-2压电材料,提高了压电换能器的机电耦合系数和换能器的接收灵敏度。通过有限元仿真分析了不同间距对改进型1-3-2压电材料敏感元件的谐振频率、反谐振频率及机电耦合系数的影响,并与传统1-3-2型压电复合材料进行了对比。结果表明,与传统型1-3-2压电复合材料相比,在相同间距条件下,改进型压电材料的机电耦合系数约大0.03。制做的3种不同间距改进型压电材料表明,间距为1 mm的改进型压电材料的机电耦合系数较大,约为0.68。

基于YOLO-v3算法的电力基建施工现场管控技术

研究针对传统电力基建项目工作量大、时效性差、效率低等问题,提出了基于YOLO-v3算法的施工现场管控技术,其核心为YOLO-v3目标检测算法,结合检测对象特征,优化了网络结构及参数,搭建了电力基建施工现场管控系统,试验结果证实,该算法能够实现对施工流程的优化,提升设备错误识别率,检测精度高,可为电力基建施工现场管控提供新的思路。

基于注意力YOLO-V3的合成孔径雷达舰船检测识别一体化方法

传统的合成孔径雷达舰船检测识别需要分两步实现,检测识别精度和效率难以满足实际应用需求。本文结合注意力机制和YOLO-V3网络提出了注意力YOLO-V3网络实现合成孔径雷达舰船检测识别一体化。同时,利用公开的AIR-SARShip-1.0数据集和OpenSARShip数据集构建了大场景舰船检测识别数据集,用于验证目标检测识别性能。实验结果表明,本文提出的注意力YOLO-V3网络可以获得较高的检测识别精度,证明了本文方法的有效性。

Improved Z^(1/3) Law of Nuclear Charge Radius

原子费用半径的一条改进 Z 1/3 法律被介绍。在现在可得到的计算、试验性的原子费用半径之间的比较证明这个新公式比另外的常规公式好。

Improved Polarization Retention of BiFeO3 Thin Films Using GdScO3(110)Substrates

Epitaxial ferroelectric one direction over the thin fihns on single-crystal substrates generally show a preferred domain orientation in other in demonstration of a poor polarization retention. This behavior will affect their application in nonvolatile ferroelectric random access memories where bipolar polarization states are used to store the logic 0 and 1 data. Here the retention characteristics of BiFe03 thin films with Srftu03 bottom electrodes on both GdSc03 （110） and SrTiO3 （100） substrates are studied and compared, and the results of piezoresponse force microscopy provide a long time retention property of the films on two substrates. It is found that bismuth ferrite thin films grown on GdScO3 substrates show no preferred domain variants in comparison with the preferred downward polarization orientation toward bottom electrodes on SrTi03 substrates. Tile retention test from a positive-up domain to a negative-down domain using a signal generator and an oscilloscope coincidentally shows bistable polarization states on the GdSeOa substrate over a measuring time of 500s, unlike the preferred domain orientation on SrTi03, where more than 65~o of upward domains disappear after 1 s. In addition, different sizes of domains have been written and read by using the scanning tip of piezoresponse force microscopy, where the polarization can stabilize over one month. This study paves one route to improve the polarization retention property through the optimization of the lattice-mismatched stresses between films and substrates.

Edge detection of gravity anomaly with an improved 3D structure tensor

Edge detection plays an important role in geological interpretation of potential field data,which can indicate the subsurface faults,contact,and other tectonic features.A variety of methods have been proposed to detect and enhance the edges.3 D structure tensor can well delineate the edges of geological bodies,however,it is sensitive to noise and additional false edges need to be removed artificially.In order to overcome these disadvantages,this paper redefines the 3 D structure tensor with a Gaussian envelop and proposes a new normalized edge detector,which can remove the additional false edges and reduce the influence of noise effectively,and balance the edges of different amplitude anomalies completely.This method has been tested on the synthetic and measured gravity data,showing that the new improved method achievesbetter results and reveals more details.

达罗他胺中间体2-氯-4(1 H-吡唑-3-基)苯甲腈的合成工艺

2-氯-4(1H-吡唑-3-基)苯甲腈是抗前列腺癌新药达罗他胺的重要中间体片段。本文以4-溴-2-氯苯甲腈和1-(2-四氢吡喃基)-1 H-吡唑-5-硼酸频哪酯为原料,经Suzuki偶联和水解脱保护两步反应,在50 g反应规模时,以大于95%的总收率和大于99%的纯度得到2-氯-4(1H-吡唑-3-基)苯甲腈。该反应原料安全易得,产物分离简单,反应收率和产物纯度高,特别是第一步Suzuki偶联反应母液可循环套用,节约了Pd催化剂和生产成本,适合工业化生产。

Clinical application of improved 2D computer-assisted fluoroscopic navigation through simulating a 3D vertebrae image to guide pedicle screw internal fixation

Objective To study the effect of using improved 2D computer-assisted fluoroscopic navigation through simulating 3D vertebrae image to guide pedicle screw internal fixation.Methods Posterior pedicle screw internal fixation,distraction

一种基于YOLO-V3算法的水下目标识别跟踪方法

为协助水下平台完成自主拍摄任务,针对水中成像模糊,物体多自由度运动的特点,提出一种基于YOLO-V3算法的目标识别模型。通过降采样重组,多级融合、优化聚类候选框、重新定义损失函数等方式优化网络结构,提高了目标识别的准确率,同时提升算法的计算速度。将具有旋转不变性的特征描述应用于跟踪水中多自由度运动的物体,通过评价结果修正跟踪状态。实验表明,该方法能够自主识别和跟踪目标,具有自适应能力,对输入像素为416*416的图片,处理速度达到15帧/秒以上,置信度为0.5时的平均准确度值达到75.1,满足实时性和准确性要求。

香豆素-3-羧酸的绿色合成及其光谱性质研究

对“香豆素-3-羧酸的制备”实验方案做了改进:以绿色无毒的L-脯氨酸为催化剂,在无溶剂的条件下制得中间体,采用“一锅煮”不分离的方法得到高产率的香豆素-3-羧酸。运用红外光谱、核磁共振等手段表征结构,研究了紫外吸收光谱和荧光光谱性质。改进后的实验方案绿色环保、产率高、重现性好、成本低、综合性强,有助于培养学生探索、创新的研究精神和团队协作能力,提升学生分析整理数据,运用理论知识解决问题的综合实验技能,适合推广至本科生高年级教学。

基于改进YOLO-v3的眼机交互模型研究及实现

针对嵌入式眼-机交互技术中所采用的传统眼行为识别方法准确率低、速度慢等问题,并结合所研制眼机交互系统硬件特点及应用场景,提出一种基于改进YOLO-v3的眼机交互模型。该模型通过去除13×13特征分辨率的检测模块、增加浅层网络的层数以及采用K-means聚类算法选取初始先验框,提高了网络像素特征提取细粒度并加快了检测速度,进而结合人眼特征参数提取方法和眼行为识别算法,构建出了眼机交互模型并进行实验。实验结果表明,该模型对不同眼行为的识别率达91.30%,改进的YOLO-v3网络的平均检测准确率(mean average precision,mAP)为99.9%,识别速度达22.8 FPS,相比原YOLO-v3方法检测时间缩短了11.4%。

基于改进YOLO-V3网络的百香果实时检测

针对目前流行的目标检测模型对真实果园中百香果检测的抗干扰能力不理想问题,本文提出基于改进的YOLO-V3网络对真实果园中百香果进行实时检测。首先,剔除YOLO-V3模型的大物体预测尺度,将3尺度预测降为2尺度预测,用于加快物体的检测速度;其次,在中型物体预测尺度后添加DenseNet网络,用于增强网络特征传播,提高模型的检测精度;最后,利用改进的YOLO-V3网络对百香果数据集进行多次训练,得到最优预训练模型。实验结果表明:改进的YOLO-V3网络实时检测效果好,对目标的平均检测精度高达97.5%以上,并且检测速度达到38幅/s,为实时检测百香果提供了有效方法。

基于轻量化YOLO-v3的绿熟期番茄检测方法

准确识别定位绿熟期番茄果实是实现其自动采摘的必要前提。由于绿熟期番茄的表面颜色仍为青色与叶片、枝干颜色接近,特别是存在叶片、枝干遮挡和果实重叠类型的图像,传统的图像检测处理方法不能准确进行定位。为解决此问题,采用改进的深度学习目标检测算法YOLO-v3进行番茄检测,将原算法的骨干网络DarkNet-53改为更轻量化的Mobilenet-v1。结果表明:轻量化YOLO-v3算法将模型大小缩小为原来的39.38%,训练速度提高3.88倍,验证集的平均精度均值达到98.69%,测试集的平均精度均值达到98.28%。所采用的轻量化YOLO-v3检测算法可实现对绿熟期番茄的实时目标检测,更适合在移动设备和嵌入式端进行部署,为更加高效的番茄自动采摘奠定基础。

基于YOLO-v3模型压缩的卫星图像船只实时检测

常见的目标检测模型由于模型参数量较大,往往难以部署在无人机、卫星等移动嵌入式设备上。为了对船只进行实时监测,将目标检测模型部署在计算能力较弱的设备上,对基于计算机视觉的卫星图像船只目标检测方法进行研究。针对卫星图像中船舰的形状长宽比例特点,采用K-means++聚类算法选取初始的锚点框;接着对模型进行多尺度训练,将多尺度金字塔图像作为模型训练的输入;将YOLO-v3目标检测算法的批归一化层的尺度因子作为通道重要性的度量指标,对YOLO-v3模型进行剪枝压缩。实验结果表明,采用的模型剪枝和压缩方法能有效地对模型进行压缩,模型的参数量减少了91.5%,模型检测时间缩短了60%,极大地减少了系统计算性能的开销。当采用的初始锚点框个数为6个时,平均准确率(mAP)达到77.31%,满足了卫星图像船舰实时性检测的需求。