Development of vehicle-recognition method on water surfaces using LiDAR data:SPD^(2)(spherically stratified point projection with diameter and distance)

Swarm robot systems are an important application of autonomous unmanned surface vehicles on water surfaces.For monitoring natural environments and conducting security activities within a certain range using a surface vehicle,the swarm robot system is more efficient than the operation of a single object as the former can reduce cost and save time.It is necessary to detect adjacent surface obstacles robustly to operate a cluster of unmanned surface vehicles.For this purpose,a LiDAR(light detection and ranging)sensor is used as it can simultaneously obtain 3D information for all directions,relatively robustly and accurately,irrespective of the surrounding environmental conditions.Although the GPS(global-positioning-system)error range exists,obtaining measurements of the surface-vessel position can still ensure stability during platoon maneuvering.In this study,a three-layer convolutional neural network is applied to classify types of surface vehicles.The aim of this approach is to redefine the sparse 3D point cloud data as 2D image data with a connotative meaning and subsequently utilize this transformed data for object classification purposes.Hence,we have proposed a descriptor that converts the 3D point cloud data into 2D image data.To use this descriptor effectively,it is necessary to perform a clustering operation that separates the point clouds for each object.We developed voxel-based clustering for the point cloud clustering.Furthermore,using the descriptor,3D point cloud data can be converted into a 2D feature image,and the converted 2D image is provided as an input value to the network.We intend to verify the validity of the proposed 3D point cloud feature descriptor by using experimental data in the simulator.Furthermore,we explore the feasibility of real-time object classification within this framework.

基于知识蒸馏和定位引导的Pointpillars点云检测网络

激光雷达数据由于其几何特性,被广泛应用于三维目标检测任务中。由于点云数据的稀疏性和不规则性,难以实现特征提取的质量和推理速度间的平衡。本文提出一种基于体柱特征编码的三维目标检测算法,以Pointpillars网络为基础,设计Teacher-Student模型框架对回归框尺度进行蒸馏,增加蒸馏损失,优化训练网络模型,提升特征提取的质量。为进一步提高模型检测效果,设计定位引导分类项,增加分类预测和回归预测之间的相关性,提高物体识别准确率。本网络所做改进没有引入额外的网络嵌入。算法在KITTI数据集上的实验结果表明,相比于基准网络,在三维模式下的平均精度值从60.65%提升到了64.69%,鸟瞰图模式下的平均精度值从67.74%提升到70.24%。模型推理速度为45 FPS,在提升检测精度的同时满足了实时性要求。

基于GCR-PointPillars的点云三维目标检测

针对PointPillars算法中存在识别与定位不准确的问题,提出一种GCR-PointPillars三维目标检测模型,该模型首先在Pillar特征网络中引入全局注意力机制,学习点云特征之间的相关性,增强伪图特征的全局信息交互能力;其次,基于ConvNeXt V2重新构建特征提取网络,提取更加丰富的语义信息,从而有效提升网络的学习能力;最后引入RDIoU来联合引导分类和回归任务,有效缓解分类和回归不一致的问题。文中模型在KITTI数据集中与基准网络相比,汽车类别在简单、中等、困难三种难度级别下分别提高了2.69%、4.29%、4.84%,并且推理速度达到25.8 f/s。实验结果表明,文中模型在保持实时性速度的同时,检测效果也有明显提升。

Change Point Detection for Process Data Analytics Applied to a Multiphase Flow Facility

Change point detection becomes increasingly important because it can support data analysis by providing labels to the data in an unsupervised manner.In the context of process data analytics,change points in the time series of process variables may have an important indication about the process operation.For example,in a batch process,the change points can correspond to the operations and phases defined by the batch recipe.Hence identifying change points can assist labelling the time series data.Various unsupervised algorithms have been developed for change point detection,including the optimisation approachwhich minimises a cost functionwith certain penalties to search for the change points.The Bayesian approach is another,which uses Bayesian statistics to calculate the posterior probability of a specific sample being a change point.The paper investigates how the two approaches for change point detection can be applied to process data analytics.In addition,a new type of cost function using Tikhonov regularisation is proposed for the optimisation approach to reduce irrelevant change points caused by randomness in the data.The novelty lies in using regularisation-based cost functions to handle ill-posed problems of noisy data.The results demonstrate that change point detection is useful for process data analytics because change points can produce data segments corresponding to different operating modes or varying conditions,which will be useful for other machine learning tasks.

A reasoning diagram based method for fault diagnosis of railway point system

Railway Point System(RPS)is an important infrastructure in railway industry and its faults may have significant impacts on the safety and efficiency of train operations.For the fault diagnosis of RPS,most existing methods assume that sufficient samples of each failure mode are available,which may be unrealistic,especially for those modes of low occurrence frequency but with high risk.To address this issue,this work proposes a novel fault diagnosis method that only requires the power signals generated under normal RPS operations in the training stage.Specifically,the failure modes of RPS are distinguished through constructing a reasoning diagram,whose nodes are either binary logic problems or those that can be decomposed into the problems of the binary logic.Then,an unsupervised method for the signal segmentation and a fault detection method are combined to make decisions for each binary logic problem.Based on the results of decisions,the diagnostic rules are established to identify the failure modes.Finally,the data collected from multiple real-world RPSs are used for validation and the results demonstrate that the proposed method outperforms the benchmark in identifying the faults of RPSs.

Analysis of Bridge-Bearing Capacity Detection and Evaluation Technology

A bridge project is taken as an example to analyze the application of bearing capacity detection and evaluation.This article provides a basic overview of the project,the application of bearing capacity detection technology,and the bearing capacity assessment analysis.It is hoped that this analysis can provide a scientific reference for the load-bearing capacity detection and evaluation work in bridge engineering projects,thereby achieving a scientific assessment of the overall load-bearing capacity of the bridge engineering structure.

基于改进PointPillars的点云车辆目标检测

针对自动驾驶领域中,激光雷达获取的点云数据存在稀疏性以及边缘噪点误检等问题,提出一种基于改进PointPil-lars的点云车辆目标检测方法。首先,基于SimAM注意力机制改进体素化特征输入,使得网络特征提取阶段能更加关注关键信息,提高特征学习的全局性。其次,基于卷积块注意力模块(CBAM)改进骨干网络结构,提出全新的轻量化通道注意力模块Tiny-CAM和可变形空间注意力模块Deformable-SAM,构建Multi-CBAM骨干网络,提升网络特征提取及特征融合能力。在KITTI数据集以及非公开车库点云数据集上进行验证,实验结果表明,与原网络相比,改进PointPillars方法具有更高的检测精度,平均检测精度提升2.98%,针对遮挡小于30%的点云车辆目标检测精度提升6.51%,证明了该方法的有效性。

DM Code Key Point Detection Algorithm Based on CenterNet

Data Matrix(DM)codes have been widely used in industrial production.The reading of DM code usually includes positioning and decoding.Accurate positioning is a prerequisite for successful decoding.Traditional image processing methods have poor adaptability to pollution and complex backgrounds.Although deep learning-based methods can automatically extract features,the bounding boxes cannot entirely fit the contour of the code.Further image processing methods are required for precise positioning,which will reduce efficiency.Because of the above problems,a CenterNet-based DM code key point detection network is proposed,which can directly obtain the four key points of the DM code.Compared with the existing methods,the degree of fitness is higher,which is conducive to direct decoding.To further improve the positioning accuracy,an enhanced loss function is designed,including DM code key point heatmap loss,standard DM code projection loss,and polygon Intersection-over-Union(IoU)loss,which is beneficial for the network to learn the spatial geometric characteristics of DM code.The experiment is carried out on the self-made DM code key point detection dataset,including pollution,complex background,small objects,etc.,which uses the Average Precision(AP)of the common object detection metric as the evaluation metric.AP reaches 95.80%,and Frames Per Second(FPS)gets 88.12 on the test set of the proposed dataset,which can achieve real-time performance in practical applications.

PVS-CNN:子流稀疏卷积优化的Point-Voxel CNN

针对经典的三维卷积网络在模型较大的场景上分割和检测的效率低和内存占用大的问题,提出PVS-CNN网络框架,通过更新哈希表和特征稀疏矩阵的方式实现了效率高且占用低的三维卷积,引用子流稀疏卷积改进PV-Conv。将PVS-CNN在ShapeNet和S3DIS数据集上进行评估,实验结果表明,所提出的PVS-CNN比PVCNN快3.6倍,GPU内存占用仅为PVCNN的0.55倍。在目标检测上,与F-PVCNN相比,PVS-CNN在时间效率和检测精度上全面优于F-PVCNN。

Point Cloud Processing Methods for 3D Point Cloud Detection Tasks

Light detection and ranging(LiDAR)sensors play a vital role in acquiring 3D point cloud data and extracting valuable information about objects for tasks such as autonomous driving,robotics,and virtual reality(VR).However,the sparse and disordered nature of the 3D point cloud poses significant challenges to feature extraction.Overcoming limitations is critical for 3D point cloud processing.3D point cloud object detection is a very challenging and crucial task,in which point cloud processing and feature extraction methods play a crucial role and have a significant impact on subsequent object detection performance.In this overview of outstanding work in object detection from the 3D point cloud,we specifically focus on summarizing methods employed in 3D point cloud processing.We introduce the way point clouds are processed in classical 3D object detection algorithms,and their improvements to solve the problems existing in point cloud processing.Different voxelization methods and point cloud sampling strategies will influence the extracted features,thereby impacting the final detection performance.

Point association analysis of vessel target detection with SAR, HFSWR and AIS

A space-borne synthetic aperture radar （SAR）, a high frequency surface wave radar （HFSWR）, and a ship automatic identification system （AIS） are the main remote sensors for vessel monitoring in a wide range. These three sensors have their own advantages and weaknesses, and they can complement each other in some situations. So it would improve the capability of vessel target detection to use multiple sensors including SAR, HFSWR, and A/S to identify non-cooperative vessel targets from the fusion results. During the fusion process of multiple sensors＇ detection results, point association is one of the key steps, and it can affect the accuracy of the data fusion and the efficiency of a non-cooperative target＇s recognition. This study investigated the point association analyses of vessel target detection under different conditions： space- borne SAR paired with AIS, as well as HFSWR, paired with AIS, and the characteristics of the SAR and the HFSWR and their capability of vessel target detection. Then a point association method of multiple sensors was proposed. Finally, the thresholds selection of key parameters in the points association （including range threshold, radial velocity threshold, and azimuth threshold） were investigated, and their influences on final association results were analyzed.

Automatic Feature Point Detection and Tracking of Human Actions in Time-of-flight Videos

Detecting feature points on the human body in video frames is a key step for tracking human movements. There have been methods developed that leverage models of human pose and classification of pixels of the body image. Yet, occlusion and robustness are still open challenges. In this paper, we present an automatic, model-free feature point detection and action tracking method using a time-of-flight camera. Our method automatically detects feature points for movement abstraction. To overcome errors caused by miss-detection and occlusion, a refinement method is devised that uses the trajectory of the feature points to correct the erroneous detections. Experiments were conducted using videos acquired with a Microsoft Kinect camera and a publicly available video set and comparisons were conducted with the state-of-the-art methods. The results demonstrated that our proposed method delivered improved and reliable performance with an average accuracy in the range of 90 %.The trajectorybased refinement also demonstrated satisfactory effectiveness that recovers the detection with a success rate of 93.7 %. Our method processed a frame in an average time of 71.1 ms.

A Moving IR Point Target Detection Algorithm Based on Reverse Phase Feature of Neighborhood in Difference Between Neighbor Frame Images

An algorithm for detecting moving IR point target in complex background is proposed, which is based on the Reverse Phase Feature of Neighborhood （RPFN） of target in difference between neighbor frame images that two positions of the target in the difference image are near and the gray values of them are close to in absolute value but with inverse sign. Firstly, pairs of points with RPFN are detected in the difference image between neighbor frame images, with which a virtual vector graph is made, and then the moving point target can be detected by the vectors＇ sequence cumulated in vector graphs. In addition, a theorem for the convergence of detection of target contrail by this algorithm is given and proved so as to afford a solid guarantee for practical applications of the algorithm proposed in this paper. Finally, some simulation results with 1000 frames from 10 typical images in complex background show that moving point targets with SNR not lower than 1.5 can be detected effectively.

Detection of the End Point Temperature of Thermal Denatured Protein in Fish and Chicken Meat Through SDS-PAGE Electrophoresis

Sodium dodecyl sulfate polyacrylamide gel electrophoresis (SDS-PAGE) was applied in the detection of the end point temperature (EPT) of thermal denatured protein in fish and meat in this study. It was also used in studying the thermal denatured temperature range of proteins in salmon and chicken meat. The results show that the temperature ranges of denatured proteins were from 65 ℃ to 75 ℃ , and these temperature ranges were influenced by the processing methods. Through SDS-PAGE, the features of repeated heating thermal denatured proteins under the same temperature and processing time were studied. The electrophoresis patterns of thermal denatured proteins determined through repeated heating at the same temperature did not exhibit any change. For the detection of cooked fish and meat samples, they were subjected to applying the SDS-PAGE method, which revealed an EPT ranging from 60 ℃ to 80 ℃ .

Highly sensitive ECL-PCR method for detection of K-ras point mutation

A highly sensitive electrochemiluminescence-polymerase chain reaction (ECL-PCR) method for K-ras point mutation detection is developed. Briefly, K-ras oncogene was amplified by a Ru(bpy)3(2+) (TBR)-labeled forward and a biotin-labeled reverse primer, and followed by digestion with MvaI restriction enzyme, which only cut the wild-type amplicon containing its cutting site. The digested product was then adsorbed to the streptavidin-coated microbead through the biotin label and detected by ECL assay. The experiment results showed that the different genotypes can be clearly discriminated by ECL-PCR method. It is useful in point mutation detection, due to its sensitivity, safety, and simplicity.

Detection of Multiscale Center Point Objects Based on Parallel Network

Anchor-based detectors are widely used in object detection.To improve the accuracy of object detection,multiple anchor boxes are intensively placed on the input image,yet.Most of which are invalid.Although the anchor-free method can reduce the number of useless anchor boxes,the invalid ones still occupy a high proportion.On this basis,this paper proposes a multiscale center point object detection method based on parallel network to further reduce the number of useless anchor boxes.This study adopts the parallel network architecture of hourglass-104 and darknet-53 of which the first one outputs heatmaps to generate the center point for object feature location on the output attribute feature map of darknet-53.Combining feature pyramid and CIoU loss function,this algorithm is trained and tested on MSCOCO dataset,increasing the detection rate of target location and the accuracy rate of small object detection.Though resembling the state-of-the-art two-stage detectors in overall object detection accuracy,this algorithm is superior in speed.

Loop Closure Detection of Visual SLAM Based on Point and Line Features

For traditional loop closure detection algorithm,only using the vectorization of point features to build visual dictionary is likely to cause perceptual ambiguity.In addition,when scene lacks texture information,the number of point features extracted from it will be small and cannot describe the image effectively.Therefore,this paper proposes a loop closure detection algorithm which combines point and line features.To better recognize scenes with hybrid features,the building process of traditional dictionary tree is improved in the paper.The features with different flag bits were clustered separately to construct a mixed dictionary tree and word vectors that can represent the hybrid features,which can better describe structure and texture information of scene.To ensure that the similarity score between images is more reasonable,different similarity coefficients were set in different scenes,and the candidate frame with the highest similarity score was selected as the candidate closed loop.Experiments show that the point line comprehensive feature was superior to the single feature in the structured scene and the strong texture scene,the recall rate of the proposed algorithm was higher than the state of the art methods when the accuracy is 100%,and the algorithm can be applied to more diverse environments.

New Approach in Processing of the Infrared Image Sequence for Moving Dim Point Targets Detection

The development of an efficient moving target detection algorithm in IR-image sequence is considered one of the most critical research fields in modern IRST (Infrared Search and Track) systems, especially when dealing with moving dim point targets. In this paper we propose a new approach in processing of the Infrared image sequence for moving dim point targets detection built on the transformation of the IR-image sequence into 4-vectors for each frame in the sequence. The results of testing the proposed approach on a set of frames having a simple single pixel target performing a different motion patterns show the validity of the approach for detecting the motion, with simplicity in calculation and low time consumption.

基于特征融合的改进型PointPillar点云目标检测

针对PointPillar在自动驾驶道路场景下对点云稀疏小目标检测效果差的问题,通过引入一种多尺度特征融合策略和注意力机制,提出一种点云目标检测网络Pillar-FFNet。针对网络中的特征提取问题,设计了一种基于残差结构的主干网络;针对馈入检测头的特征图没有充分利用高层特征的语义信息和低层特征的空间信息的问题,设计了一种简单有效的多尺度特征融合策略;针对主干网络提取的特征图中信息冗余的问题,提出了一种卷积注意力机制。为验证所提算法的性能,在KITTI和DAIR-V2X-I数据集上进行实验。实验结果表明,所提出的算法在KITTI数据集上与PointPillar相比,汽车、行人和骑行者的平均精度最大提高分别为0.84%,2.13%和4.02%;在DAIR-V2X-I数据集上与PointPillar相比,汽车、行人和骑行者的平均精度最大提高分别为0.33%,2.09%和4.71%,由此证明了所提方法对点云稀疏小目标检测的有效性。