汽轮机TSI系统的测量与调试

介绍了TSI系统各类探头测量原理及安装、校验方法。

YOLO-MFD:Remote Sensing Image Object Detection with Multi-Scale Fusion Dynamic Head

Remote sensing imagery,due to its high altitude,presents inherent challenges characterized by multiple scales,limited target areas,and intricate backgrounds.These inherent traits often lead to increased miss and false detection rates when applying object recognition algorithms tailored for remote sensing imagery.Additionally,these complexities contribute to inaccuracies in target localization and hinder precise target categorization.This paper addresses these challenges by proposing a solution:The YOLO-MFD model(YOLO-MFD:Remote Sensing Image Object Detection withMulti-scale Fusion Dynamic Head).Before presenting our method,we delve into the prevalent issues faced in remote sensing imagery analysis.Specifically,we emphasize the struggles of existing object recognition algorithms in comprehensively capturing critical image features amidst varying scales and complex backgrounds.To resolve these issues,we introduce a novel approach.First,we propose the implementation of a lightweight multi-scale module called CEF.This module significantly improves the model’s ability to comprehensively capture important image features by merging multi-scale feature information.It effectively addresses the issues of missed detection and mistaken alarms that are common in remote sensing imagery.Second,an additional layer of small target detection heads is added,and a residual link is established with the higher-level feature extraction module in the backbone section.This allows the model to incorporate shallower information,significantly improving the accuracy of target localization in remotely sensed images.Finally,a dynamic head attentionmechanism is introduced.This allows themodel to exhibit greater flexibility and accuracy in recognizing shapes and targets of different sizes.Consequently,the precision of object detection is significantly improved.The trial results show that the YOLO-MFD model shows improvements of 6.3%,3.5%,and 2.5%over the original YOLOv8 model in Precision,map@0.5 and map@0.5:0.95,separately.These results illustrate the clear advantages of the method.

SDH-FCOS:An Efficient Neural Network for Defect Detection in Urban Underground Pipelines

Urban underground pipelines are an important infrastructure in cities,and timely investigation of problems in underground pipelines can help ensure the normal operation of cities.Owing to the growing demand for defect detection in urban underground pipelines,this study developed an improved defect detection method for urban underground pipelines based on fully convolutional one-stage object detector(FCOS),called spatial pyramid pooling-fast(SPPF)feature fusion and dual detection heads based on FCOS(SDH-FCOS)model.This study improved the feature fusion component of the model network based on FCOS,introduced an SPPF network structure behind the last output feature layer of the backbone network,fused the local and global features,added a top-down path to accelerate the circulation of shallowinformation,and enriched the semantic information acquired by shallow features.The ability of the model to detect objects with multiple morphologies was strengthened by introducing dual detection heads.The experimental results using an open dataset of underground pipes show that the proposed SDH-FCOS model can recognize underground pipe defects more accurately;the average accuracy was improved by 2.7% compared with the original FCOS model,reducing the leakage rate to a large extent and achieving real-time detection.Also,our model achieved a good trade-off between accuracy and speed compared with other mainstream methods.This proved the effectiveness of the proposed model.

Ghost-YOLO v8:An Attention-Guided Enhanced Small Target Detection Algorithm for Floating Litter on Water Surfaces

Addressing the challenges in detecting surface floating litter in artificial lakes,including complex environments,uneven illumination,and susceptibility to noise andweather,this paper proposes an efficient and lightweight Ghost-YOLO(You Only Look Once)v8 algorithm.The algorithmintegrates advanced attention mechanisms and a smalltarget detection head to significantly enhance detection performance and efficiency.Firstly,an SE(Squeeze-and-Excitation)mechanism is incorporated into the backbone network to fortify the extraction of resilient features and precise target localization.This mechanism models feature channel dependencies,enabling adaptive adjustment of channel importance,thereby improving recognition of floating litter targets.Secondly,a 160×160 small-target detection layer is designed in the feature fusion neck to mitigate semantic information loss due to varying target scales.This design enhances the fusion of deep and shallow semantic information,improving small target feature representation and enabling better capture and identification of tiny floating litter.Thirdly,to balance performance and efficiency,the GhostConv module replaces part of the conventional convolutions in the feature fusion neck.Additionally,a novel C2fGhost(CSPDarknet53 to 2-Stage Feature Pyramid Networks Ghost)module is introduced to further reduce network parameters.Lastly,to address the challenge of occlusion,a newloss function,WIoU(Wise Intersection over Union)v3 incorporating a flexible and non-monotonic concentration approach,is adopted to improve detection rates for surface floating litter.The outcomes of the experiments demonstrate that the Ghost-YOLO v8 model proposed in this paper performs well in the dataset Marine,significantly enhances precision and recall by 3.3 and 7.6 percentage points,respectively,in contrast with the base model,mAP@0.5 and mAP 0.5:0.95 improve by 5.3 and 4.4 percentage points and reduces the computational volume by 1.88MB,the FPS value hardly decreases,and the efficient real-time identification of floating debris on the water’s surface can be achieved costeffectively.

Improved YOLOv5-Based Inland River Floating Garbage Detection Model

Detection of floating garbage in inland rivers is crucial for water environmental protection,as it effectively reduces ecological damage and ensures the safety of water resources.To address the inefficiency of traditional cleanup methods and the challenges in detecting small targets,an improved YOLOv5 object detection model was proposed in this study.In order to enhance the model’s sensitivity to small targets and mitigate the impact of redundant information on detection performance,a bi-level routing attention mechanism was introduced and embedded into the backbone network.Additionally,a multi-scale detection head was incorporated into the model,allowing for more comprehensive coverage of floating garbage of various sizes through multi-scale feature extraction and detection.The Focal-EIoU loss function was also employed to optimize the model parameters,improving localization accuracy.Experimental results on the publicly available FloW_Img dataset demonstrated that the improved YOLOv5 model outperforms the original YOLOv5 model in terms of precision and recall,achieving a mAP(mean average precision)of 86.12%,with significant improvements and faster convergence.

Head Motion Detection in Gaze Based Aiming

Unmanned weapons have great potential to be widely used in future wars.The gaze-based aiming technology can be applied to control pan-tilt weapon systems remotely with high precision and efficiency.Gaze direction is related to head motion,which is a combination of head and eye movements.In this paper,a head motion detection method is proposed,which is based on the fusion of inertial and vision information.The inertial sensors can measure rotation in high-frequency with good performance,while vision sensors are able to eliminate drifts.By combining the characteristics of both sensors,the proposed approach achieves the effect of highfrequency,real-time,and drift-free head motion detection.The experiments show that our method can smooth the outputs,constrain drifts of inertial measurements,and achieve high detection accuracy.

基于改进Double-Head RCNN的无人机航拍图像小目标检测算法

为解决无人机航拍图像中小目标特征信息少且容易被噪声干扰导致现有算法漏检率和误检率高的问题,提出一种改进Double-Head Region-卷积神经网络(RCNN)的无人机航拍图像小目标检测算法。在骨干网络ResNet-50上引入Transformer和可变形卷积(DCN)模块,更有效提取小目标特征信息和语义信息;提出一种基于内容感知特征重组(CARAFE)的特征金字塔网络(FPN)结构模块,解决特征融合过程中小目标被背景噪声干扰而丢失特征信息的问题;在区域建议网络中针对小目标尺度分布特点重新设置Anchor生成尺度,进一步提升小目标检测性能。在VisDrone-DET2021数据集上的实验结果表明:所提算法能提取更具有表征能力的小目标特征信息和语义信息,对比Double-Head RCNN算法,所提算法的参数量增加了9.73×10^(6),FPS损失了0.6,但是AP、AP50和AP75分别提升了2.6%、6.2%和2.1%,APs提升了3.1%。

The Practice of a Method of Self-Study Students Counting in Classrooms Based on Head Detection in Colleges and Universities

In order to solve the problem that it is difficult for students to find self-study classrooms because of the limited classroom resources, combined with the current situation of informatization in colleges and universities, a feasible method of students counting in classrooms based on head detection is proposed. This method first collects the scene images in the classroom at regular intervals based on the existing examination monitoring system, and then uses the offline trained AdaBoost cascade detector to detect the head candidate region in the images. Then, the trained CNN-SVM model is used to further identify the head, and finally the identification results are processed and the number of students in the classrooms is counted. The test and practice show that the query system for the idle situation of self-study classrooms constructed by coordinating the classroom seat capacity, classroom scheduling data and the students counting in the classroom based on the above method can easily query the current crowded degree of the students in the classrooms, which plays a good guiding role for students to find self-study classrooms. The method has strong reference and promotion significance for solving similar problems in other universities.

Automatic Fetal Segmentation Designed on Computer-Aided Detection with Ultrasound Images

In the present research,we describe a computer-aided detection(CAD)method aimed at automatic fetal head circumference(HC)measurement in 2D ultrasonography pictures during all trimesters of pregnancy.The HC might be utilized toward determining gestational age and tracking fetal development.This automated approach is particularly valuable in low-resource settings where access to trained sonographers is limited.The CAD system is divided into two steps:to begin,Haar-like characteristics were extracted from ultrasound pictures in order to train a classifier using random forests to find the fetal skull.We identified the HC using dynamic programming,an elliptical fit,and a Hough transform.The computer-aided detection(CAD)program was well-trained on 999 pictures(HC18 challenge data source),and then verified on 335 photos from all trimesters in an independent test set.A skilled sonographer and an expert in medicine personally marked the test set.We used the crown-rump length(CRL)measurement to calculate the reference gestational age(GA).In the first,second,and third trimesters,the median difference between the standard GA and the GA calculated by the skilled sonographer stayed at 0.7±2.7,0.0±4.5,and 2.0±12.0 days,respectively.The regular duration variance between the baseline GA and the health investigator’s GA remained 1.5±3.0,1.9±5.0,and 4.0±14 a couple of days.The mean variance between the standard GA and the CAD system’s GA remained between 0.5 and 5.0,with an additional variation of 2.9 to 12.5 days.The outcomes reveal that the computer-aided detection(CAD)program outperforms an expert sonographer.When paired with the classifications reported in the literature,the provided system achieves results that are comparable or even better.We have assessed and scheduled this computerized approach for HC evaluation,which includes information from all trimesters of gestation.

Design of Heading Fault-Tolerant System for Underwater Vehicles Based on Double-Criterion Fault Detection Method

This paper proposes a heading fault tolerance scheme for operation-level underwater robots subject to external interference.The scheme is based on a double-criterion fault detection method using a redundant structure of a dual electronic compass.First,two subexpansion Kalman filters are set up to fuse data with an inertial attitude measurement system.Then,fault detection can effectively identify the fault sensor and fault source.Finally,a fault-tolerant algorithm is used to isolate and alarm the faulty sensor.The program can effectively detect the constant magnetic field interference,change the magnetic field interference and small transient magnetic field interference,and conduct fault tolerance control in time to ensure the heading accuracy of the system.Test verification shows that the system is practical and effective.

基于Involution Prediction Head的小目标检测算法

针对通用目标检测算法在检测小目标时存在错检和漏检等问题,提出了一种小目标检测算法IPH(Involution Prediction Head),将其运用在YOLOv4和YOLOv5的检测头部分,在VOC2007数据集上的实验结果表明,运用IPH后的YOLOv4小目标检测精度APs(AP for small objects)相比原始算法提升了1.1%,在YOLOv5上的APs更是提升了5.9%。经智能交通检测数据集进一步检验,IPH算法和去下采样能有效提升小目标检测精度,减少错检和漏检的情况。

Development of a Liquid Chip Technique to Simultaneously Detect Taura Syndrome Virus( TSV) and Yellow Head Disease Virus( YHDV)

The aim is to develop a liquid chip technique to detect Taura syndrome virus( TSV) and yellow head disease virus( YHDV) on Penaeus orientalis simultaneously. The CP2 gene of TSV and N gene of YHDV in Gen Bank was analysed by using the software DNAStar 7. 0 to design the TSV-and YHDV-specific primers. The primers were labeled with biotin and subjected to amination modification. They were then coupled with fluorescence-coded microspheres and then used for hybridization with RT- PCR products of TSV and YHDV. The liquid chip detection technique for detection of TSV and YHDV was established by using BD FACSArray to detect fluorescence signal in the reaction system. This assay system had a high sensitivity to TSV and YHDV,with the detection of limit of 100 pg. Moreover,the assay was specific for the detection of TSV,YHDV and was not susceptible to cross with other viruses,including white spot syndrome virus( WSSV),spring viremia of carp virus( SVCV),infectious haematopoietic necrosis virus( IHNV). In conclusion,the liquid chip assay technique established in this study is highly sensitive and specific to TSV and YHDV detection. Moreover,it provides a novel,convenient and rapid approach for the detection of TSV and YHDV.

Heading constraint algorithm for foot-mounted PNS using low-cost IMU

Foot-mounted pedestrian navigation system(PNS)is a common solution to pedestrian navigation using micro-electro mechanical system(MEMS)inertial sensors.The inherent problems of inertial navigation system(INS)by the traditional algorithm,such as the accumulated errors and the lack of observation of heading and altitude information,have become obstacles to the application and development of the PNS.In this paper,we introduce a heuristic heading constraint method.First of all,according to the movement characteristics of human gait,we use the generalized likelihood ratio test(GLRT)detector and introduce a time threshold to classify the human gait,so that we can effectively identify the stationary state of the foot.In addition,based on zero velocity update(ZUPT)and zero angular rate update(ZARU),the cumulative error of the inertial measurement unit(IMU)is limited and corrected,and then a heuristic heading estimation is used to constrain and correct the heading of the pedestrian.After simulation and experiments with low-cost IMU,the method is proved to reduce the localization error of end-point to less than 1%of the total distance,and it has great value in application.

DTHN: Dual-Transformer Head End-to-End Person Search Network

Person search mainly consists of two submissions,namely Person Detection and Person Re-identification(reID).Existing approaches are primarily based on Faster R-CNN and Convolutional Neural Network(CNN)(e.g.,ResNet).While these structures may detect high-quality bounding boxes,they seem to degrade the performance of re-ID.To address this issue,this paper proposes a Dual-Transformer Head Network(DTHN)for end-to-end person search,which contains two independent Transformer heads,a box head for detecting the bounding box and extracting efficient bounding box feature,and a re-ID head for capturing high-quality re-ID features for the re-ID task.Specifically,after the image goes through the ResNet backbone network to extract features,the Region Proposal Network(RPN)proposes possible bounding boxes.The box head then extracts more efficient features within these bounding boxes for detection.Following this,the re-ID head computes the occluded attention of the features in these bounding boxes and distinguishes them from other persons or backgrounds.Extensive experiments on two widely used benchmark datasets,CUHK-SYSU and PRW,achieve state-of-the-art performance levels,94.9 mAP and 95.3 top-1 scores on the CUHK-SYSU dataset,and 51.6 mAP and 87.6 top-1 scores on the PRW dataset,which demonstrates the advantages of this paper’s approach.The efficiency comparison also shows our method is highly efficient in both time and space.

Tracking Human Poses with Head Orientation Estimation

Lots of progress has been made recently on 2 D human pose tracking with tracking-by-detection approaches. However,several challenges still remain in this area which is due to self-occlusions and the confusion between the left and right limbs during tracking. In this work,a head orientation detection step is introduced into the tracking framework to serve as a complementary tool to assist human pose estimation. With the face orientation determined,the system can decide whether the left or right side of the human body is exactly visible and infer the state of the symmetric counterpart. By granting a higher priority for the completely visible side,the system can avoid double counting to a great extent when inferring body poses. The proposed framework is evaluated on the HumanEva dataset. The results show that it largely reduces the occurrence of double counting and distinguishes the left and right sides consistently.

Updated overview of current biomarkers in head and neck carcinoma

Squamous cell cancer is the most common type of malignancy arising from the epithelial cells of the head and neck region. Head and neck squamous cell carcinoma(HNSCC) is one of the predominant causes of cancer related casualties worldwide. Overall prognosis in this disease has improved to some extent with the advancements in therapeutic modalities but detection of primary tumor at its initial stage and prevention of relapse are the major targets to be achieved for further improvement in terms of survival rate of patients. Latest achievements in basic research regarding molecular characterization of the disease has helped in better perception of the molecular mechanisms involved in HNSCC progression and also in recognizing and tar-geting various molecular biomarkers associated with HNSCC. In the present article, we review the infor-mation regarding latest and potential biomarkers for the early detection of HNSCC. A detailed molecular characterization, ultimately, is likely to improve the development of new therapeutic strategies, potentially relevant to diagnosis and prognosis of head and neck cancers. The need for more accurate and timely disease prediction has generated enormous research interests in this field.

A Method for Head-shoulder Segmentation and Human Facial Feature Positioning

ＡＭｅｔｈｏｄｆｏｒＨｅａｄｓｈｏｕｌｄｅｒＳｅｇｍｅｎｔａｔｉｏｎａｎｄＨｕｍａｎＦａｃｉａｌＦｅａｔｕｒｅＰｏｓｉｔｉｏｎｉｎｇＨｕＴｉａｎｊｉａｎＣａｉＤｅｊｕｎＤｅｐａｒｔｍｅｎｔｏｆＥｌｅｃｔｒｉｃａｌａｎｄＩｎｆｏｒｍａｔｉｏｎＥｎｇｉ...

Combining Multiple Cues for Pedestrian Detection in Crowded Situations

This paper proposes a vision-based pedestrian detection in crowded situations based on a single camera. The main idea behind our work is to fuse multiple cues so that the major challenges, such as occlusion and complex background facing in the topic of crowd detection can be successfully overcome. Based on the assumption that human heads are visible, circle Hough transform (CHT) is applied to detect all circular regions and each of which is considered as the head candidate of a pedestrian. After that, the false candidates resulting from complex background are firstly removed by using template matching algorithm. Two proposed cues called head foreground contrast (HFC) and block color relation (BCR) are incorporated for further verification. The rectangular region of every detected human is determined by the geometric relationships as well as foreground mask extracted through background subtraction process. Three videos are used to validate the proposed approach and the experimental results show that the proposed method effectively lowers the false positives at the expense of little detection rate.

基于MCB-FAH-YOLOv8的钢材表面缺陷检测算法

针对现有基于深度学习的钢材表面缺陷检测算法存在误检、漏检和检测精度低等问题,提出一种基于改进CBAM(modified CBAM,MCB)和可替换四头ASFF预测头(four-head ASFF prediction head,FAH)的YOLOv8钢材表面缺陷检测算法,简记为MCB-FAH-YOLOv8。通过加入改进后的卷积注意力机制模块(CBAM)对密集目标更好的确定;通过将FPN结构改为BiFPN更加高效的提取上下文信息;通过增加自适应特征融合(ASFF)自动找出最适合的融合特征;通过将SPPF模块替换为精度更高的SimCSPSPPF模块。同时,针对微小物体检测,提出了四头ASFF预测头,可根据数据集特点进行替换。实验结果表明,MCB-FAH-YOLOv8算法在VOC2007数据集上检测精度(mAP)达到了88.8%,在NEU-DET钢铁缺陷检测数据集上检测精度(mAP)达到了81.8%,较基准模型分别提高了5.1%和3.4%,该算法在牺牲较少检测速度的情况下取得较高的检测精度,很好的平衡了算法的精度和速度。

基于改进YOLOv5s的无人机图像识别

无人机在军事情报、航拍检测等领域能够提供目标相关的图像信息,为处理任务提供目标信息。针对无人机图像背景复杂、检测目标小、可提取特征少等问题,提出基于YOLOv5s的改进无人机图像识别算法。首先,结合CotNet模块对网络结构进行优化,提升模型自学习能力并增强识别精度;其次,对颈部网络进行改进,通过跨层链接和提高特征图分辨率更好地利用浅层特征图中包含的丰富信息来定位目标,并且在检测头部分采用解耦检测头,减少预测过程中定位与分类任务对于特征信息的冲突;最后,为了提高收敛速度和模型精度,在CIoU和EIoU损失函数的基础上对损失函数的宽高纵横比进行优化。在公开数据集VisDrone测试集上进行测试,所提算法相比原始YOLOv5s算法的mAP_(50)与mAP_(50∶95)分别提升了6.1与2.9个百分点,实验结果表明,所提模型能够有效提升无人机图像识别的准确率。