A Simple and Effective Surface Defect Detection Method of Power Line Insulators for Difficult Small Objects

Insulator defect detection plays a vital role in maintaining the secure operation of power systems.To address the issues of the difficulty of detecting small objects and missing objects due to the small scale,variable scale,and fuzzy edge morphology of insulator defects,we construct an insulator dataset with 1600 samples containing flashovers and breakages.Then a simple and effective surface defect detection method of power line insulators for difficult small objects is proposed.Firstly,a high-resolution featuremap is introduced and a small object prediction layer is added so that the model can detect tiny objects.Secondly,a simplified adaptive spatial feature fusion(SASFF)module is introduced to perform cross-scale spatial fusion to improve adaptability to variable multi-scale features.Finally,we propose an enhanced deformable attention mechanism(EDAM)module.By integrating a gating activation function,the model is further inspired to learn a small number of critical sampling points near reference points.And the module can improve the perception of object morphology.The experimental results indicate that concerning the dataset of flashover and breakage defects,this method improves the performance of YOLOv5,YOLOv7,and YOLOv8.In practical application,it can simply and effectively improve the precision of power line insulator defect detection and reduce missing detection for difficult small objects.

A Novel Tensor Decomposition-Based Efficient Detector for Low-Altitude Aerial Objects With Knowledge Distillation Scheme

Unmanned aerial vehicles(UAVs) have gained significant attention in practical applications, especially the low-altitude aerial(LAA) object detection imposes stringent requirements on recognition accuracy and computational resources. In this paper, the LAA images-oriented tensor decomposition and knowledge distillation-based network(TDKD-Net) is proposed,where the TT-format TD(tensor decomposition) and equalweighted response-based KD(knowledge distillation) methods are designed to minimize redundant parameters while ensuring comparable performance. Moreover, some robust network structures are developed, including the small object detection head and the dual-domain attention mechanism, which enable the model to leverage the learned knowledge from small-scale targets and selectively focus on salient features. Considering the imbalance of bounding box regression samples and the inaccuracy of regression geometric factors, the focal and efficient IoU(intersection of union) loss with optimal transport assignment(F-EIoU-OTA)mechanism is proposed to improve the detection accuracy. The proposed TDKD-Net is comprehensively evaluated through extensive experiments, and the results have demonstrated the effectiveness and superiority of the developed methods in comparison to other advanced detection algorithms, which also present high generalization and strong robustness. As a resource-efficient precise network, the complex detection of small and occluded LAA objects is also well addressed by TDKD-Net, which provides useful insights on handling imbalanced issues and realizing domain adaptation.

Management of Penetrating Cranioencephalic Trauma Caused by Sharp Metal Objects—Therapeutic and Evolutionary Aspects: 12 Cases at the Renaissance University Hospital in N’Djamena

Introduction: Cranioencephalic trauma caused by bladed weapons is rare, and that caused by sharp objects is exceptional. The aim of our study was to describe the clinical, therapeutic and evolutionary aspects. Materials and method: This was a descriptive and analytical study over a 48-month period at CHU la Renaissance from January 1, 2018 to December 31, 2021, concerning patients admitted for penetrating cranioencephalic trauma by pointed object. Results: Twelve cases, all male, of penetrating cranioencephalic sharp-force trauma were identified. The mean age was 34 ± 7 years, with extremes of 11 and 60 years. Farmers and herders accounted for 31% and 25% of cases respectively. The average admission time was 47 hours. Brawls were the circumstances of occurrence in 81.2% of cases. Knives (33%), arrows (25%) and iron bars (16.6%) were the objects used. Altered consciousness was present in 43.8% of cases, and focal deficit in 50%. Scannographic lesions were fracture and/or embarrhment (12 cases), intra-parenchymal haematomas (6 cases) and presence of object in place (4 cases). Surgery was performed in 11 patients. Postoperative outcome was favorable in 9 patients. After 12 months, 2 patients were declared unfit. Conclusion: Penetrating head injuries caused by sharp objects are common in Chad. Urgent surgery can prevent disabling after-effects.

Patterns of Interactions of the Complex City System:Emotional Urban Objects as Triggering Agents-A Secondary Publication

This article presents an analysis of the patterns of interactions resulting from the positive and negative emotional events that occur in cities,considering them as complex systems.It explores,from the imaginaries,how certain urban objects can act as emotional agents and how these events affect the urban system as a whole.An adaptive complex systems perspective is used to analyze these patterns.The results show patterns in the processes and dynamics that occur in cities based on the objects that affect the emotions of the people who live there.These patterns depend on the characteristics of the emotional charge of urban objects,but they can be generalized in the following process:(1)immediate reaction by some individuals;(2)emotions are generated at the individual level which begins to generalize,permuting to a collective emotion;(3)a process of reflection is detonated in some individuals from the reading of collective emotions;(4)integration/significance in the community both at the individual and collective level,on the concepts,roles and/or functions that give rise to the process in the system.Therefore,it is clear that emotions play a significant role in the development of cities and these aspects should be considered in the design strategies of all kinds of projects for the city.Future extensions of this work could include a deeper analysis of specific emotional events in urban environments,as well as possible implications for urban policy and decision making.

Numerical Investigations on Harbor Oscillations Induced by Falling Objects

In this paper,the open-sourced computational fluid dynamics software,OpenFOAM~?,is used to study the fluctuation phenomenon of the water body inside a horizontally one-dimensional enclosed harbor basin with constant water depth triggered by falling wedges with various horizontal falling positions,initial falling velocities and masses.Based on both Fourier transfo rm analysis and wavelet spectrum analysis for the time series of the free surface elevations inside the harbor basin,it is found for the first time that the wedge falling inside the harbor can directly trigger harbor resonance.The influences of the three factors(including the horizontal falling position,the initial falling velocity,and the mass)on the response amplitudes of the lowest three resonant modes are also investigated.The results show that when the wedge falls on one of the nodal points of a resonant mode,the mode would be remarkably suppressed.Conversely,when the wedge falls on one of the anti-nodal points of a resonant mode,the mode would be evidently triggered.The initial falling velocity of the wedge mainly has a remarkable effect on the response amplitude of the most significant mode,and the latter shows a gradual increase trend with the increase of the former.While for the other two less significant modes,their response amplitudes fluctuate around certain constant values as the initial falling velocity rises.In general,the response amplitudes of all the lowest three modes are shown to gradually increase with the mass of the wedge.

德国Orion公司启动循环炭黑项目

据橡胶技术网2023年11月9日报道,近日,德国Orion工程炭公司(以下简称“Orion公司”)宣布,正在德国投资1280万欧元,用于进一步开发和展示碳中和的炭黑生产工艺。据悉,Orion公司将该项目命名为“清洁炭黑研发项目”,将得到德国政府和欧盟640万欧元资金支持,这一技术旨在提高该公司使用可回收原料生产炭黑的产量和收率、大幅减少工艺对环境的碳足迹,从而降低生产材料的成本。这一创新的研究项目有望加速炭黑生产行业向循环经济的转型,满足轮胎行业对可持续材料日益增长的需求,同时这一领域的技术突破可能会对能源整合和废弃轮胎的分子级回收产生深远影响。作为该计划的一部分,Orion公司将在其位于德国Cologne工厂的主要创新中心专门为该项目建造1个研发实验室。

基于FME Objects的空间数据格式转换方法研究

地理信息数据广泛应用于大测绘、自然资源、建设规划等行业领域的信息分析与存储。因其数据叠加分析与跨专业融合学习的需要,满足数据的定向需求与统一性。本文基于FME Objects的引用库,运用C#语言研究了如何精确、完整实现数据格式转换的程序方法,探寻了含非图形属性文件的转换函数表达方式,解析了程序实现的基础结构。经过诸多数据的转换验证,此系统能够提高数据格式的转换效率且能保证图形要素与属性的完整性,并可生成全面的转换日志与简易的质检文本,为各行业地理信息数据的统一整理提供便利。

Optimizing Storage for Energy Conservation in Tracking Wireless Sensor Network Objects

The amount of needed control messages in wireless sensor networks(WSN)is affected by the storage strategy of detected events.Because broadcasting superfluous control messages consumes excess energy,the network lifespan can be extended if the quantity of control messages is decreased.In this study,an optimized storage technique having low control overhead for tracking the objects in WSN is introduced.The basic concept is to retain observed events in internal memory and preserve the relationship between sensed information and sensor nodes using a novel inexpensive data structure entitled Ordered Binary Linked List(OBLL).Whenever an object passes over the sensor area,the recognizing sensor can immediately produce an OBLL along the object’s route.To retrieve the entire information,the OBLL can be traversed with logarithmic complexity which is much less than the traversing complexity of existing linked list structures.Performance evaluation and simulations were carried out to ensure that the suggested technique minimizes the number of messages and thus saving energy and extending the network life.

Application of 3D Scanned Big Data of Large-scale Cultural Heritage Objects Based on Noise-robust Transparent Visualization

Three-dimensional(3D) scanning technology has undergone remarkable developments in recent years.Data acquired by 3D scanning have the form of 3D point clouds.The 3D scanned point clouds have data sizes that can be considered big data.They also contain measurement noise inherent in measurement data.These properties of 3D scanned point clouds make many traditional CG/visualization techniques difficult.This paper reviewed our recent achievements in developing varieties of high-quality visualizations suitable for the visual analysis of 3D scanned point clouds.We demonstrated the effectiveness of the method by applying the visualizations to various cultural heritage objects.The main visualization targets used in this paper are the floats in the Gion Festival in Kyoto(the float parade is on the UNESCO Intangible Cultural Heritage List) and Borobudur Temple in Indonesia(a UNESCO World Heritage Site).

New Fragile Watermarking Technique to Identify Inserted Video Objects Using H.264 and Color Features

The transmission of video content over a network raises various issues relating to copyright authenticity,ethics,legality,and privacy.The protection of copyrighted video content is a significant issue in the video industry,and it is essential to find effective solutions to prevent tampering and modification of digital video content during its transmission through digital media.However,there are stillmany unresolved challenges.This paper aims to address those challenges by proposing a new technique for detectingmoving objects in digital videos,which can help prove the credibility of video content by detecting any fake objects inserted by hackers.The proposed technique involves using two methods,the H.264 and the extraction color features methods,to embed and extract watermarks in video frames.The study tested the performance of the system against various attacks and found it to be robust.The evaluation was done using different metrics such as Peak-Signal-to-Noise Ratio(PSNR),Mean Squared Error(MSE),Structural Similarity Index Measure(SSIM),Bit Correction Ratio(BCR),and Normalized Correlation.The accuracy of identifying moving objects was high,ranging from 96.3%to 98.7%.The system was also able to embed a fragile watermark with a success rate of over 93.65%and had an average capacity of hiding of 78.67.The reconstructed video frames had high quality with a PSNR of at least 65.45 dB and SSIMof over 0.97,making them imperceptible to the human eye.The system also had an acceptable average time difference(T=1.227/s)compared with other state-of-the-art methods.

图像引导和点云空间约束的公路洒落物检测定位方法

公路洒落物是影响交通安全的重要因素之一,为了解决中小尺度公路洒落物检测中的漏检、误检以及难以定位等问题,本文提出了一种图像引导和点云空间约束的公路洒落物检测定位方法。该方法使用改进的YOLOv7-OD网络处理图像数据获取二维目标预测框信息,将目标预测框投影到激光雷达坐标系下得到锥形感兴趣区域(region of interest,ROI)。在ROI区域内的点云空间约束下,联合点云聚类和点云生成算法获得不同尺度的洒落物在三维空间中的检测定位结果。实验表明:改进的YOLOv7-OD网络在中尺度目标上的召回率和平均精度分别为85.4%和82.0%,相比YOLOv7网络分别提升6.6和8.0个百分点;在小尺度目标上的召回率和平均精度分别为66.8%和57.3%,均提升5.3个百分点;洒落物定位方面,对于距离检测车辆30~40 m处的目标,深度定位误差为0.19 m,角度定位误差为0.082°,实现了多尺度公路洒落物的检测和定位。

CNN-Transformer特征融合多目标跟踪算法

在卷积神经网络(CNN)中,卷积运算能高效地提取目标的局部特征,却难以捕获全局表示;而在视觉Transformer中,注意力机制可以捕获长距离的特征依赖,但会忽略局部特征细节。针对以上问题,提出一种基于CNN-Transformer双分支主干网络进行特征提取和融合的多目标跟踪算法CTMOT(CNN-transformer multi-object tracking)。使用基于CNN和Transformer双分支并行的主干网络分别提取图像的局部和全局特征。使用双向桥接模块(two-way braidge module,TBM)对两种特征进行充分融合。将融合后的特征输入两组并行的解码器进行处理。将解码器输出的检测框和跟踪框进行匹配,完成多目标跟踪任务。在多目标跟踪数据集MOT17、MOT20、KITTI以及UADETRAC上进行评估,CTMOT算法的MOTP和IDs指标在四个数据集上均达到了SOTA效果,MOTA指标分别达到了76.4%、66.3%、92.36%和88.57%,在MOT数据集上与SOTA方法效果相当,在KITTI数据集上达到SOTA效果。由于同时完成目标检测和关联,能够端到端进行目标跟踪,跟踪速度可达35 FPS,表明CTMOT算法在跟踪的实时性和准确性上达到了较好的平衡,具有较大潜力。

“天问二号”任务科学目标和有效载荷配置

回顾了近30年国际上小行星探测任务的科学目标和载荷配置。在总结小行星探测主要科学问题的基础上,对中国行星探测工程“天问二号”探测任务的对象选择、科学目标和有效载荷配置进行了论述。围绕实现科学目标探测,并提出了相应的科学研究内容和有效载荷技术指标。

基于改进YOLOX与多级数据关联的行人多目标跟踪算法研究

目标跟踪是计算机视觉领域的基本问题,行人多目标跟踪在智能监控、智慧交通等多个领域有着广泛的应用前景。然而实际跟踪场景中存在频繁遮挡、尺度变化等情况,给多目标跟踪算法带来了极大的挑战。为了进一步提升跟踪精度,在DeepSORT的基础上,提出一种基于改进YOLOX与多级数据关联的行人多目标跟踪算法。对于检测器,为了增强网络的特征表达能力,提高检测精度,在YOLOX骨架网络与颈部网络分别引入ECA通道注意力模块与ASFF自适应特征融合模块。对于身份识别特征,为了减少数据关联步骤的错误匹配数量,提高跟踪效率,使用轻量的OSNet重识别网络与NSA卡尔曼滤波获取目标特征。对于数据关联,为了减少身份切换次数,避免目标丢失,将检测与跟踪都进行分类处理,使用不同的相似性计算方法,实现基于检测置信度与轨迹状态的多级数据关联。实验结果表明:与改进前YOLOX与DeepSORT简单结合的算法相比,在YOLOX中引入ECA模块与ASFF模块使误检数量大幅降低,使用YOLOX-s模型时降幅可达17%;结合OSNet模型与NSA卡尔曼滤波的特征提取方法能提高跟踪稳定性,IDF1指标提高0.77%,IDSW减少947;基于检测置信度与轨迹状态的多级数据关联算法可以明显改善跟踪性能,MOTA指标提升3.36%。算法最终在MOT17与MOT20测试集上的MOTA达80.4%与77.7%,IDF1达78.4%与76.7%。提出的行人多目标跟踪方法相较于其他先进算法在跟踪精度与跟踪速度上达到更好的平衡,可为工业上在线行人多目标跟踪应用提供参考。

狭长空间内重载调姿装配机器人的设计与研究

针对舱体类狭长空间内部待安装设备种类多、批量大、载荷重、空间余量微小、装配路径复杂、装配风险高等问题,设计了一种重载调姿装配机器人。在机器人运动学研究的基础上,建立了误差模型,并以最小包围球半径为约束条件,通过遗传算法将误差参数的辨识结果补偿到机器人控制系统。以机柜装配为例,针对空间约束条件规划工作路径,基于动力学约束能耗函数模型,以时间、冲击和能耗为优化目标,得到多目标最优轨迹。样机实验验证了误差参数辨识的有效性,减小了机器人的绝对定位误差,且多目标最优轨迹的关节总冲击小、运动平稳,实现了机柜类设备高效、平稳、可靠的安装。

基于红外相机和毫米波雷达融合的烟雾遮挡无人驾驶车辆目标检测与跟踪

战场环境下无人驾驶车辆的感知系统易受烟雾、扬尘等天气的影响,对关键目标的检测与跟踪能力大大下降,造成目标漏检、目标误检、目标丢失等严重后果。针对该问题,开发毫米波雷达和红外相机融合系统,采用目标级融合方式建立简洁有效的融合规则,提炼和组合各传感器的优势信息,最终输出稳定的目标感知结果。对毫米波雷达的目标进行有效性检验和提取,并提出改进的基于密度的含噪声空间聚类应用算法,以减少毫米波雷达噪音干扰。以YOLOv4网络为基础,引入MobileNetv2主干网络,在网络训练过程中运用迁移学习方法,同时对红外数据样本进行扩充,解决了红外图像训练样本少的问题。试验结果表明,相较于仅基于红外相机的算法,融合检测算法在烟雾环境下的精度显著提升,且算法实时性高,实现了烟雾环境下毫米波雷达与红外相机融合的目标检测与跟踪,提高了无人驾驶车辆目标检测与跟踪系统的抗烟雾干扰能力。

改进YOLOv5模型在自然环境下柑橘识别的应用

在复杂的自然环境中绿色柑橘生长形态各异,颜色与背景色相近,为有效识别绿色柑橘,提出一种基于混合注意力机制并改进YOLOv5模型的柑橘识别方法。首先,改进YOLOv5的网络结构,在主干网络中添加混合注意力机制,即在主干网络中的第2层嵌入SE(squeeze and excitation)注意力,第11层嵌入CA(coordinate attention)注意力;其次,改进网络模型特征融合结构,将YOLOv5模型Concat特征融合操作的下层分支放在模型C3模块之前,再与另一条上层分支进行特征融合;最后,改进模型分类损失函数,将YOLOv5模型的分类损失函数改成Varifocal Loss函数,加强绿色柑橘特征信息的提取,提高绿色柑橘检测精度。根据自然环境和柑橘自身的特点,对自建数据集进行分类,设计3组不同分类场景下柑橘的对比试验以验证其有效性。试验结果表明,改进后的YOLOv5-SC模型准确率为91.74%,平均精度为95.09%,F1为89.56%,在自然环境下对绿色柑橘的识别具有更高的准确率和更好的鲁棒性,为绿色水果智能采摘提供技术支持。

面向自动驾驶道路场景中异常案例的多模态数据挖掘算法

基于深度学习的视觉感知技术的发展有利于自动驾驶系统中环境感知技术的进步。然而,对于自动驾驶场景中的异常案例,目前的感知模型还存在一些问题。这是因为基于深度学习的感知模型的能力取决于训练数据集的分布。尤其是驾驶场景中的类别从未出现在训练集中,感知系统也往往很脆弱。因此识别未知类别和极端场景仍然是自动驾驶感知技术安全性的挑战。本文从处理数据集的角度出发,提出了一种新颖的多模态异常案例自动挖掘流程(corner case mining pipeline, CCMP)。为验证CCMP的有效性,在Waymo开放数据集的基础上构建了异常案例子集“Waymo-Anomaly”,该子集共有3 200个图像,每个图像都将包含文本中定义的异常案例场景。并且基于私有数据集Waymo-Anomaly,证明了CCMP针对异常案例场景挖掘的召回率可以达到91.7%。此外,还通过实验验证了目标检测器在包含异常案例的数据集中针对长尾分布的有效性。最终,希望从处理数据集的角度来提高自动驾驶感知模型在现实世界中的真实性。

技术与社会转型互构下的“人工智能+”:新质生产力发展引擎

“人工智能+”叠加了更多学科领域的力量,是发展新质生产力的重要影响因素,这一影响不仅是由于技术本身具备高科技含量,而且和技术与社会转型之间的快速互构有关。参照法国哲学家吉尔伯特·西蒙东提出的“技术物”这一概念,“人工智能+”为现代社会带来了“智能物”。“智能物”比传统意义上的“技术物”更具有能动性,能够快速吸收处理海量数据信息并针对某一领域进行社会化模拟,影响人类的生产活动,人类也因此产生了对更高效、更便捷、更智能的生活和工作方式的追求,这一互构反馈机制对新质生产力的发展形成了必要环境。而随着“人工智能+”覆盖面的增大,智能物对生产效能、产业增长、产业竞争、生产关系等方面也产生了相应的影响。

基于改进NSGA-Ⅱ算法的梯级水库多目标优化调度

针对在时间步长较小、计算时段数目较多时,传统智能优化算法在求解梯级水库联合优化调度问题上效率低甚至无可行解的问题,提出了一种改进NSGA-Ⅱ算法。该算法基于NSGA-Ⅱ算法框架,引入参考目标值、潜力目标值、偏移度以及变异引导算子来优化种群进化过程,强化迭代中的种群质量,使获得的解集更加接近真实的Pareto前沿。福建省金溪流域梯级水库多目标优化调度实例验证结果表明,改进NSGA-Ⅱ算法相对其他算法运算效率更高,优化结果更好,具有较好的实用性。