ST-LaneNet: Lane Line Detection Method Based on Swin Transformer and LaneNet

The advancement of autonomous driving heavily relies on the ability to accurate lane lines detection.As deep learning and computer vision technologies evolve,a variety of deep learning-based methods for lane line detection have been proposed by researchers in the field.However,owing to the simple appearance of lane lines and the lack of distinctive features,it is easy for other objects with similar local appearances to interfere with the process of detecting lane lines.The precision of lane line detection is limited by the unpredictable quantity and diversity of lane lines.To address the aforementioned challenges,we propose a novel deep learning approach for lane line detection.This method leverages the Swin Transformer in conjunction with LaneNet(called ST-LaneNet).The experience results showed that the true positive detection rate can reach 97.53%for easy lanes and 96.83%for difficult lanes(such as scenes with severe occlusion and extreme lighting conditions),which can better accomplish the objective of detecting lane lines.In 1000 detection samples,the average detection accuracy can reach 97.83%,the average inference time per image can reach 17.8 ms,and the average number of frames per second can reach 64.8 Hz.The programming scripts and associated models for this project can be accessed openly at the following GitHub repository:https://github.com/Duane 711/Lane-line-detec tion-ST-LaneNet.

Research on Transmission Line Tower Tilting and Foundation State Monitoring Technology Based onMulti-Sensor Cooperative Detection and Correction

The transmission line tower will be affected by bad weather and artificial subsidence caused by the foundation and other factors in the power transmission.The tower’s tilt and severe deformation will cause the building to collapse.Many small changes caused the tower’s collapse,but the early staff often could not intuitively notice the changes in the tower’s state.In the current tower online monitoring system,terminal equipment often needs to replace batteries frequently due to premature exhaustion of power.According to the need for real-time measurement of power line tower,this research designed a real-time monitoring device monitoring the transmission tower attitude tilting and foundation state based on the inertial sensor,the acceleration of 3 axis inertial sensor and angular velocity raw data to pole average filtering pre-processing,and then through the complementary filtering algorithm for comprehensive calculation of tilt angle,the system meets the demand for inclined online monitoring of power line poles and towers regarding measurement accuracy,with low cost and power consumption.The optimization multi-sensor cooperative detection and correction measured tilt angle result relative accuracy can reach 1.03%,which has specific promotion and application value since the system has the advantages of unattended and efficient calculation.

Analysis of the joint detection capability of the SMILE satellite and EISCAT-3D radar

The Solar wind Magnetosphere Ionosphere Link Explorer(SMILE)satellite is a small magnetosphere–ionosphere link explorer developed cooperatively between China and Europe.It pioneers the use of X-ray imaging technology to perform large-scale imaging of the Earth’s magnetosheath and polar cusp regions.It uses a high-precision ultraviolet imager to image the overall configuration of the aurora and monitor changes in the source of solar wind in real time,using in situ detection instruments to improve human understanding of the relationship between solar activity and changes in the Earth’s magnetic field.The SMILE satellite is scheduled to launch in 2025.The European Incoherent Scatter Sciences Association(EISCAT)-3D radar is a new generation of European incoherent scatter radar constructed by EISCAT and is the most advanced ground-based ionospheric experimental device in the high-latitude polar region.It has multibeam and multidirectional quasi-real-time three-dimensional(3D)imaging capabilities,continuous monitoring and operation capabilities,and multiple-baseline interferometry capabilities.Joint detection by the SMILE satellite and the EISCAT-3D radar is of great significance for revealing the coupling process of the solar wind–magnetosphere–ionosphere.Therefore,we performed an analysis of the joint detection capability of the SMILE satellite and EISCAT-3D,analyzed the period during which the two can perform joint detection,and defined the key scientific problems that can be solved by joint detection.In addition,we developed Web-based software to search for and visualize the joint detection period of the SMILE satellite and EISCAT-3D radar,which lays the foundation for subsequent joint detection experiments and scientific research.

A self-organization formation configuration based assignment probability and collision detection

The formation control of multiple unmanned aerial vehicles(multi-UAVs)has always been a research hotspot.Based on the straight line trajectory,a multi-UAVs target point assignment algorithm based on the assignment probability is proposed to achieve the shortest overall formation path of multi-UAVs with low complexity and reduce the energy consumption.In order to avoid the collision between UAVs in the formation process,the concept of safety ball is introduced,and the collision detection based on continuous motion of two time slots and the lane occupation detection after motion is proposed to avoid collision between UAVs.Based on the idea of game theory,a method of UAV motion form setting based on the maximization of interests is proposed,including the maximization of self-interest and the maximization of formation interest is proposed,so that multi-UAVs can complete the formation task quickly and reasonably with the linear trajectory assigned in advance.Finally,through simulation verification,the multi-UAVs target assignment algorithm based on the assignment probability proposed in this paper can effectively reduce the total path length,and the UAV motion selection method based on the maximization interests can effectively complete the task formation.

An Implementation of Multiscale Line Detection and Mathematical Morphology for Efficient and Precise Blood Vessel Segmentation in Fundus Images

Diagnosing various diseases such as glaucoma,age-related macular degeneration,cardiovascular conditions,and diabetic retinopathy involves segmenting retinal blood vessels.The task is particularly challenging when dealing with color fundus images due to issues like non-uniformillumination,low contrast,and variations in vessel appearance,especially in the presence of different pathologies.Furthermore,the speed of the retinal vessel segmentation system is of utmost importance.With the surge of now available big data,the speed of the algorithm becomes increasingly important,carrying almost equivalent weightage to the accuracy of the algorithm.To address these challenges,we present a novel approach for retinal vessel segmentation,leveraging efficient and robust techniques based on multiscale line detection and mathematical morphology.Our algorithm’s performance is evaluated on two publicly available datasets,namely the Digital Retinal Images for Vessel Extraction dataset(DRIVE)and the Structure Analysis of Retina(STARE)dataset.The experimental results demonstrate the effectiveness of our method,withmean accuracy values of 0.9467 forDRIVE and 0.9535 for STARE datasets,aswell as sensitivity values of 0.6952 forDRIVE and 0.6809 for STARE datasets.Notably,our algorithmexhibits competitive performance with state-of-the-art methods.Importantly,it operates at an average speed of 3.73 s per image for DRIVE and 3.75 s for STARE datasets.It is worth noting that these results were achieved using Matlab scripts containing multiple loops.This suggests that the processing time can be further reduced by replacing loops with vectorization.Thus the proposed algorithm can be deployed in real time applications.In summary,our proposed system strikes a fine balance between swift computation and accuracy that is on par with the best available methods in the field.

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.

Multi-Equipment Detection Method for Distribution Lines Based on Improved YOLOx-s

The YOLOx-s network does not sufficiently meet the accuracy demand of equipment detection in the autonomous inspection of distribution lines by Unmanned Aerial Vehicle(UAV)due to the complex background of distribution lines,variable morphology of equipment,and large differences in equipment sizes.Therefore,aiming at the difficult detection of power equipment in UAV inspection images,we propose a multi-equipment detection method for inspection of distribution lines based on the YOLOx-s.Based on the YOLOx-s network,we make the following improvements:1)The Receptive Field Block(RFB)module is added after the shallow feature layer of the backbone network to expand the receptive field of the network.2)The Coordinate Attention(CA)module is added to obtain the spatial direction information of the targets and improve the accuracy of target localization.3)After the first fusion of features in the Path Aggregation Network(PANet),the Adaptively Spatial Feature Fusion(ASFF)module is added to achieve efficient re-fusion of multi-scale deep and shallow feature maps by assigning adaptive weight parameters to features at different scales.4)The loss function Binary Cross Entropy(BCE)Loss in YOLOx-s is replaced by Focal Loss to alleviate the difficulty of network convergence caused by the imbalance between positive and negative samples of small-sized targets.The experiments take a private dataset consisting of four types of power equipment:Transformers,Isolators,Drop Fuses,and Lightning Arrestors.On average,the mean Average Precision(mAP)of the proposed method can reach 93.64%,an increase of 3.27%.The experimental results show that the proposed method can better identify multiple types of power equipment of different scales at the same time,which helps to improve the intelligence of UAV autonomous inspection in distribution lines.

Detecting land subsidence near metro lines in the Baoshan district of Shanghai with multi-temporal interferometric synthetic aperture radar

Land subsidence is a major factor that affects metro line （ML） stability. In this study, an improved multi- temporal interferometric synthetic aperture radar （InSAR） （MTI） method to detect land subsidence near MLs is presented. In particular, our multi-temporal InSAR method provides surface subsidence measurements with high observation density. The MTI method tracks both point-like targets and distributed targets with temporal radar back- scattering steadiness. First, subsidence rates at the point targets with low-amplitude dispersion index （ADI） values are extracted by applying a least-squared estimator on an optimized freely connected network. Second, to reduce error propagation, the pixels with high-ADI values are classified into several groups according to ADI intervals and processed using a Pearson correlation coefficient and hierarchical analysis strategy to obtain the distributed targets. Then, nonlinear subsidence components at all point-like and distributed targets are estimated using phase unwrapping and spatiotemporal filtering on the phase residuals. The proposed MTI method was applied to detect land subsidence near MLs of No. 1 and 3 in the Baoshan district of Shanghai using 18 TerraSAR-X images acquired between April 21, 2008 and October 30, 2010. The results show that the mean subsidence rates of the stations distributed along the two MLs are -12.9 and -14.0 ram/year. Furthermore, three subsidence funnels near the MLs are discovered through the hierarchical analysis. The testing results demonstrate the satisfactory capacity of the proposed MTI method in providing detailed subsidence information near MLs.

基于改进YOLOv5-LITE轻量级的配电组件缺陷识别

为对配电组件缺陷进行精确快速的定位和识别,提出一种基于改进YOLOv5-LITE轻量级的配电组件缺陷识别方法。为使模型便于部署至移动设备终端,该方法使用ShuffleNetV2作为骨干网提取特征构建YOLOv5-LITE轻量级神经网络模型,并摘除ShuffleNetV2的1024卷积和5×5池化,采用全局平均池化操作替代,降低网络参数量,提升模型检测速度;通过引入有利于细粒度目标检测的152×152特征层,实现了对大、中、小尺度的缺陷检测;在PANet架构中采用深度可分离卷积代替下采样使得网络更加轻量化。实验结果表明:该方法能够识别电缆脱离垫片、电缆与绝缘子脱落、无环绝缘子3种缺陷,其检测精度分别达到92%、95%、95%,网络参数量约为YOLOv5的1/4,检测速度达到2 ms/张。所提出的方法具有实时性、准确率高、轻量化等特点。

基于先验知识辅助聚类的粗-精输电线路多金具检测

为了解决输电线路多金具检测任务中存在的小目标和密集遮挡问题并充分利用金具高分辨率航拍图像的信息优势,提出基于先验知识辅助聚类的粗-精输电线路多金具检测方法。首先,通过粗检测模块实现对输电线路高分辨率航拍图像的初步感知。接着,通过先验知识指导结构场景子区域选取模块中聚类算法半径的确定,以自适应聚类出合适的子区域。最后,设计精检测模块充分利用高分辨率航拍图像中的关键信息,进行金具的精确感知,并融合粗检测结果以实现由粗到精的金具识别。经实验证明,基于先验知识辅助聚类的粗-精输电线路多金具检测模型比之基线模型准确率提高了11.3%,对其中小目标金具和密集遮挡金具检测准确率的提高尤为明显。

基于改进HT-LCNN线段检测模型的隧洞施工活动时间信息智能提取方法

施工活动时间信息的有效提取是隧洞施工进度分析与决策的重要前提,目前常采用的一种隧洞施工活动时间记录方式是绘制横道图线段。针对传统依赖于人工统计的方式存在效率低、易出错等问题,提出基于改进深度霍夫线条先验网络(Hough Transform-Line Convolutional Neural Network,HT-LCNN)线段检测模型的隧洞施工活动时间信息智能提取方法。首先,采用单应性变换手段进行施工日志图像预处理,解决原始图像存在的倾斜、旋转、扭曲等问题;其次,利用全局上下文注意力模块(Global Context Network,GCNet)改进HT-LCNN模型的残差模块,通过建立和共享全局注意力图,获得目标线段在特征图和通道间的长距离依赖关系,提高模型对目标手绘线段的注意力,克服原有HT-LCNN方法容易受到表格线段和文字干扰的不足,实现手绘线段的高精度智能检测;进一步地,建立施工时刻-活动坐标系,根据所检测的手绘横道图线段的端点坐标位置特征,将其自动转化为施工活动时间信息。将该方法应用于某长距离引水隧洞TBM施工日志活动时间提取,本文提出的改进HT-LCNN模型的检测精度AP_(5)、AP_(10)、AP_(15)值分别为94.7%、95.0%、95.1%,均高于HT-LCNN和LCNN;基于本文方法自动提取的施工活动时间与人工提取结果相比,平均绝对误差仅为1.82 min。本研究为隧洞施工活动时间信息准确高效提取提供了新思路。

基于时-频注意力机制网络的水声目标线谱增强

为提高被动声纳对水下低噪声安静型目标的检测,研究者开始关注基于深度学习的线谱增强方法,其中,基于LSTM的线谱增强网络由于同时具有时域和频域的非线性处理能力,具有很强的灵活性,然而其性能还需要进一步提升。为此,该文提出了基于时-频注意力机制的网络模型(TFA-Net),通过在LSTM模型的基础上同时增加时域注意力机制和频域注意力机制,充分利用了目标信号在时域和频域的双重重要特征,提升了对LOFAR谱的线谱增强效果。TFA-Net中的时域注意力机制利用LSTM隐藏状态之间的关联性,增加了模型在时域的注意力,频率注意力机制通过将深度残差收缩网络中收缩子网络的全链接层设计为1维卷积层,增加了模型在频域的注意力。相比于LSTM,TFA-Net具有更高的系统信噪比增益:在输入信噪比为–3 dB的情况下,将系统信噪比增益由2.17 dB提升到12.56 dB;在输入信噪比为–11 dB的情况下,将系统信噪比增益由0.71 dB提升到10.6 dB。仿真和实测数据的实验结果表明,TFA-Net可以有效提升LOFAR谱的线谱增强效果,解决低信噪比下水下目标的检测问题。

Upper oesophageal images and Z-line detection with 2 different small-bowel capsule systems

Transmission of oesophageal images may vary between different small-bowel capsule endoscopy models. A retrospective review of 100 examinations performed with 2 different Small-bowel capsule endoscopy （SBCE） sys- tems （PillCam and MiroCam） was performed. The oral cavity/aero-digestive tract （i.e., tongue, uvula and/or epiglottis） was captured/identified in almost all （99%） of PillCam videos but in none of MiroCam cases, P 〈 0.0001. Furthermore, oesophageal images （i.e., from the upper oesophageal sphincter to the Z-line were cap- tured in 99% of PillCam videos （mean =1= SD, 60.5 ± 334.1 frames, range： 0-3329 frames） and in 66% of Mi- roCam cases （mean ± SD, 11.1 ± 46.5 frames, range： 0-382 frames）, P 〈 0.0001. The Z-line was identified in 42% of PilICam videos and 17% of MiroCam, P = 0.0002. This information might be useful when perform- ing SBCE in patients with high risks for aspiration.

Transfer and Detection of barstar Gene to Maize Inbred Line 18-599 (White) by Particle Bombardment

In China, the purity of maize hybrid strain is discomforting to the development of seed industrialization. Finding a new method for reproduction of maize hybrid strain is necessary. In this study, using particle bombardment, barstar gene was transferred into maize inbred line 18-599 （White）, which is an antiviral and high quality maize inbred line. By molecular detection of the anther of transgenic maize, two plants transferred with barstar gene were gained in this study, which are two restorer lines. The two plants showed normal male spike, and lively microspores. But the capacity of the two restorer lines should be studied in the future. The aim of this study is to find a new method of reproduction of maize hybrid strain using engineering restorer lines and engineering sterility lines by gene engineering technology.

基于PHAM-YOLO网络的卷烟纸燃烧线检测方法

为实现卷烟纸燃烧时燃烧线的准确识别,构建了常见应用场景下的卷烟纸燃烧线数据集。针对检测背景复杂、多目标、燃烧线尺度不一且形状各异的难题,将并行混合注意机制嵌入了YOLO v5主干网络,构建了PHAM-YOLO网络模型用于卷烟纸燃烧线的检测。采用特征金字塔快速池化、边界盒回归等方法提升了卷烟纸燃烧线的定位准确性。结果表明,对于卷烟纸燃烧线数据集,PHAM-YOLO网络检测平均精度均值、精度和召回率分别为99.0%、99.8%和99.0%,其中平均精度均值比原始模型提高了5.0%,高于其他类型的目标检测方法。

Lane Line Detection Based on Improved PINet

Accurate perception of lane line information is one of the basic requirements of unmanned driving technology, which is related to the localization of the vehicle and the determination of the forward direction. In this paper, multi-level constraints are added to the lane line detection model PINet, which is used to improve the perception of lane lines. Predicted lane lines in the network are predicted to have real and imaginary attributes, which are used to enhance the perception of features around the lane lines, with pixel-level constraints on the lane lines;images are converted to bird’s-eye views, where the parallelism between lane lines is reconstructed, with lane line-level constraints on the predicted lane lines;and vanishing points are used to focus on the image hierarchy, with image-level constraints on the lane lines. The model proposed in this paper meets both accuracy (96.44%) and real-time (30 + FPS) requirements, has been tested on the highway on the ground, and has performed stably.

基于THz-TDR的芯片金属微带线缺陷检测

针对体积小、走线密集、集成度高的封装芯片缺陷检测,目前的主要检测手段存在精度低、周期长等缺点。为弥补传统检测方法的不足,作者结合太赫兹技术与时域反射技术,探究对芯片上金属导线缺陷检测的可行性。首先在不同宽度的金属微带线上加工了不同比例的凸起、凹槽缺陷,模拟集成芯片中金属导线的不完全开/短路等阻抗不匹配情况,利用太赫兹时域反射计采集其时域反射信号。然后根据时域反射脉冲对应的时间分别对不同缺陷程度、不同缺陷类型进行定性分析,并精确计算出了芯片上金属微带线的缺陷位置。最后利用有限元分析法对硅基底上存在缺陷的金属微带线进行仿真分析,与实验结果具有良好的一致性。该研究表明,太赫兹技术与时域反射技术结合能够实现对芯片上金属导线缺陷的诊断检测,为集成芯片的缺陷检测提供了经验参考。

基于ER-YOLO算法的跨环境输电线路缺陷识别方法

为提高输电线路缺陷智能检测算法在不同环境条件下的鲁棒性,克服现有智能检测算法在不同环境下识别性能下降的问题,该文提出了跨环境鲁棒YOLO(ER-YOLO)算法。首先,基于广义注意力理论在YOLOv8的骨干网络中引入Transformer注意力机制;其次,使用大卷积核和通道注意力模块优化特征提取;最后,应用多重注意力机制检测头网络强化算法多尺度、空间位置和多任务感知能力。为获得测试数据,该文探索生成了模拟暗光、雾霾、模糊环境的虚拟数据集。经消融实验和对比分析,跨环境鲁棒YOLO算法在跨环境测试中展现了更高的缺陷识别精度和鲁棒性,各测试数据集下mAP平均值为0.726,相对改进前提升0.069,同时在实际环境下进行了验证,证明了该算法的有效性。该文提出的跨拍摄环境的输电线路缺陷识别方法,在跨环境识别中表现出卓越的性能。跨环境图像生成方法可为后续虚拟数据集生成技术提供借鉴。

基于YOLO-2MCS的输电线路走廊隐患目标检测方法

输电线路在跨越高速铁路、高速公路和重要输电通道场景下易受到外力破坏,可能严重影响输电线路安全可靠运行。针对此问题,该文通过构建输电线路走廊隐患目标数据集,提出新模型YOLO-2MCS用于输电线路走廊隐患目标检测。使用混合数据增强策略对数据集进行有效扩充,以提高模型在复杂场景下的泛化性和鲁棒性;在EfficientRep骨干网络引入卷积注意力机制模块,有效提升模型对多尺度目标的检测能力;构建使用softplus激活函数的双向特征金字塔结构加强模型特征学习能力;在检测头使用SIoU损失函数进一步提升模型检测精度。实验结果表明,相较于原YOLOv6网络,该模型在0.5:0.95的严苛阈值下平均精度均值提升4.4%;将该模型与主流的检测模型FasterR-CNN、YOLOX、YOLOv5和YOLOv7分别进行对比评估,该模型的检测精度、检测速度、模型复杂度均获得最优性能,其平均检测速度高达约300帧/s,且内存仅为40.7 MB,同时满足在边缘计算设备上部署的要求。

基于YOLOP-L的多特征融合道路全景驾驶检测

目前,驾驶员视角下的交通图像检测技术成为交通领域的重要研究方向,同时提取车辆、道路、交通标志等多种特征已经成为驾驶员理解道路信息多样性的亟需任务。以往研究已在单类目标检测的特征提取方面取得了长足进步,然而,这些研究不能很好地联合应用于其他区别较大的特征检测任务中,且融合训练过程中会损失个别特征检测的精度。针对驾驶员视野范围内道路信息多样且复杂的特点,本文提出了一种基于多特征融合训练的检测模型YOLOP-L,它能够同时对多种不同特征交通目标进行融合训练,同时保证单项检测任务的精度。首先,为了解决特征融合中语义信息表达不完整的问题,设计的SP-LNet模块通过FPN与双向特征网络结合实现网络更深层次的融合,使得提取的信息更完整,从而提升道路小目标的检测性能;其次,设计新的分割头深度可分离卷积,将语义信息与局部特征融合促使多特征融合的训练准确度与速度得到进一步提升;再次,体系中设计的GDL-Focal多类混合损失函数更专注于困难样本,可用于解决样本特征不平衡的问题。最后,对比实验表明:YOLOP-L相比原YOLOP网络运行的速度更快;在车辆目标检测任务下召回率提升了2.2%;在车道线检测任务下准确率提升2.8%,车道线IoU的值较HybridNets网络下降2.45%,但较YOLOP-L网络提升1.95%;在可行驶区域分割任务下其整体检测性能提升1.1%。结果表明,在具有挑战性的BDD100K数据集上,YOLOP-L可以在复杂场景下有效解决检测精度不足和分割缺失的问题,提高了车辆识别、车道线检测以及道路行驶区域联合训练的准确性和鲁棒性。