Recognition of occluded pedestrians from the driver's perspective for extending sight distance and ensuring driving safety at signal-free intersections

Urban intersections without traffic signals are prone to accidents involving motor vehicles and pedestrians.Utilizing computer vision technology to detect pedestrians crossing the street can effectively mitigate the occurrence of such accidents.Faced with the complex issue of pedestrian occlusion at signal-free intersections,this paper proposes a target detection model called Head feature And ENMS fusion Residual connection For CNN(HAERC).Specifically,the model includes a head feature module that detects occluded pedestrians by integrating their head features with the overall target.Additionally,to address the misselection caused by overlapping candidate boxes in two-stage target detection models,an Extended Non-Maximum Suppression classifier(ENMS)with expanded IoU thresholds is proposed.Finally,leveraging the CityPersons dataset and categorizing it into four classes based on occlusion levels(heavy,reasonable,partial,bare),the HAERC model is experimented on these classes and compared with baseline models.Experimental results demonstrate that HAERC achieves superior False Positives Per Image(FPPI)values of 46.64%,9.59%,9.43%,and 6.78%respectively for the four classes,outperforming all baseline models.The study concludes that the HAERC model effectively identifies occluded pedestrians in the complex environment of urban intersections without traffic signals,thereby enhancing safety for long-range driving at such intersections.

Pedestrian lane formation with following–overtaking model and measurement of system order

Pedestrian self-organizing movement plays a significant role in evacuation studies and architectural design.Lane formation,a typical self-organizing phenomenon,helps pedestrian system to become more orderly,the majority of following behavior model and overtaking behavior model are imprecise and unrealistic compared with pedestrian movement in the real world.In this study,a pedestrian dynamic model considering detailed modelling of the following behavior and overtaking behavior is constructed,and a method of measuring the lane formation and pedestrian system order based on information entropy is proposed.Simulation and analysis demonstrate that the following and avoidance behaviors are important factors of lane formation.A high tendency of following results in good lane formation.Both non-selective following behavior and aggressive overtaking behavior cause the system order to decrease.The most orderly following strategy for a pedestrian is to overtake the former pedestrian whose speed is lower than approximately 70%of his own.The influence of the obstacle layout on pedestrian lane and egress efficiency is also studied with this model.The presence of a small obstacle does not obstruct the walking of pedestrians;in contrast,it may help to improve the egress efficiency by guiding the pedestrian flow and mitigating the reduction of pedestrian system orderliness.

Measuring Pedestrian Stress Response (MPSR) Using Wearable Technologies

Walkability is an essential aspect of urban transportation systems. Properly designed walking paths can enhance transportation safety, encourage pedestrian activity, and improve community quality of life. This, in turn, can help achieve sustainable development goals in urban areas. This pilot study uses wearable technology data to present a new method for measuring pedestrian stress in urban environments and the results were presented as an interactive geographic information system map to support risk-informed decision-making. The approach involves analyzing data from wearable devices using heart rate variability (RMSSD and slope analysis) to identify high-stress locations. This data-driven approach can help urban planners and safety experts identify and address pedestrian stressors, ultimately creating safer, more walkable cities. The study addresses a significant challenge in pedestrian safety by providing insights into factors and locations that trigger stress in pedestrians. During the pilot study, high-stress pedestrian experiences were identified due to issues like pedestrian-scooter interaction on pedestrian paths, pedestrian behavior around high foot traffic areas, and poor visibility at pedestrian crossings due to inadequate lighting.

Hybrid pedestrian positioning system using wearable inertial sensors and ultrasonic ranging

Pedestrian positioning system(PPS)using wearable inertial sensors has wide applications towards various emerging fields such as smart healthcare,emergency rescue,soldier positioning,etc.The performance of traditional PPS is limited by the cumulative error of inertial sensors,complex motion modes of pedestrians,and the low robustness of the multi-sensor collaboration structure.This paper presents a hybrid pedestrian positioning system using the combination of wearable inertial sensors and ultrasonic ranging(H-PPS).A robust two nodes integration structure is developed to adaptively combine the motion data acquired from the single waist-mounted and foot-mounted node,and enhanced by a novel ellipsoid constraint model.In addition,a deep-learning-based walking speed estimator is proposed by considering all the motion features provided by different nodes,which effectively reduces the cumulative error originating from inertial sensors.Finally,a comprehensive data and model dual-driven model is presented to effectively combine the motion data provided by different sensor nodes and walking speed estimator,and multi-level constraints are extracted to further improve the performance of the overall system.Experimental results indicate that the proposed H-PPS significantly improves the performance of the single PPS and outperforms existing algorithms in accuracy index under complex indoor scenarios.

IR-YOLO: Real-Time Infrared Vehicle and Pedestrian Detection

Road traffic safety can decrease when drivers drive in a low-visibility environment.The application of visual perception technology to detect vehicles and pedestrians in infrared images proves to be an effective means of reducing the risk of accidents.To tackle the challenges posed by the low recognition accuracy and the substan-tial computational burden associated with current infrared pedestrian-vehicle detection methods,an infrared pedestrian-vehicle detection method A proposal is presented,based on an enhanced version of You Only Look Once version 5(YOLOv5).First,A head specifically designed for detecting small targets has been integrated into the model to make full use of shallow feature information to enhance the accuracy in detecting small targets.Second,the Focal Generalized Intersection over Union(GIoU)is employed as an alternative to the original loss function to address issues related to target overlap and category imbalance.Third,the distribution shift convolution optimization feature extraction operator is used to alleviate the computational burden of the model without significantly compromising detection accuracy.The test results of the improved algorithm show that its average accuracy(mAP)reaches 90.1%.Specifically,the Giga Floating Point Operations Per second(GFLOPs)of the improved algorithm is only 9.1.In contrast,the improved algorithms outperformed the other algorithms on similar GFLOPs,such as YOLOv6n(11.9),YOLOv8n(8.7),YOLOv7t(13.2)and YOLOv5s(16.0).The mAPs that are 4.4%,3%,3.5%,and 1.7%greater than those of these algorithms show that the improved algorithm achieves higher accuracy in target detection tasks under similar computational resource overhead.On the other hand,compared with other algorithms such as YOLOv8l(91.1%),YOLOv6l(89.5%),YOLOv7(90.8%),and YOLOv3(90.1%),the improved algorithm needs only 5.5%,2.3%,8.6%,and 2.3%,respectively,of the GFLOPs.The improved algorithm has shown significant advancements in balancing accuracy and computational efficiency,making it promising for practical use in resource-limited scenarios.

Method of improving pedestrian navigation performance based on chest card

With the development of positioning technology,loca-tion services are constantly in demand by people.As a primary location service pedestrian navigation has two main approaches based on radio and inertial navigation.The pedestrian naviga-tion based on radio is subject to environmental occlusion lead-ing to the degradation of positioning accuracy.The pedestrian navigation based on micro-electro-mechanical system inertial measurement unit(MIMU)is less susceptible to environmental interference,but its errors dissipate over time.In this paper,a chest card pedestrian navigation improvement method based on complementary correction is proposed in order to suppress the error divergence of inertial navigation methods.To suppress atti-tude errors,optimal feedback coefficients are established by pedestrian motion characteristics.To extend navigation time and improve positioning accuracy,the step length in subsequent movements is compensated by the first step length.The experi-mental results show that the positioning accuracy of the pro-posed method is improved by more than 47%and 44%com-pared with the pure inertia-based method combined with step compensation and the traditional complementary filtering com-bined method with step compensation.The proposed method can effectively suppress the error dispersion and improve the positioning accuracy.

Lightweight Cross-Modal Multispectral Pedestrian Detection Based on Spatial Reweighted Attention Mechanism

Multispectral pedestrian detection technology leverages infrared images to provide reliable information for visible light images, demonstrating significant advantages in low-light conditions and background occlusion scenarios. However, while continuously improving cross-modal feature extraction and fusion, ensuring the model’s detection speed is also a challenging issue. We have devised a deep learning network model for cross-modal pedestrian detection based on Resnet50, aiming to focus on more reliable features and enhance the model’s detection efficiency. This model employs a spatial attention mechanism to reweight the input visible light and infrared image data, enhancing the model’s focus on different spatial positions and sharing the weighted feature data across different modalities, thereby reducing the interference of multi-modal features. Subsequently, lightweight modules with depthwise separable convolution are incorporated to reduce the model’s parameter count and computational load through channel-wise and point-wise convolutions. The network model algorithm proposed in this paper was experimentally validated on the publicly available KAIST dataset and compared with other existing methods. The experimental results demonstrate that our approach achieves favorable performance in various complex environments, affirming the effectiveness of the multispectral pedestrian detection technology proposed in this paper.

Differential influences of road physical design attributes on pedestrian versus driver traffic accident frequencies

Traffic accidents involving pedestrians and drivers pose significant public health and safety concerns.Understanding the differential influences of road physical design attributes on crash frequencies for these two groups is critical for developing targeted safety interventions.Considering that the zero-truncated characteristic of the data is uncertain,the results of the zero-truncated negative binomial models and traditional negative binomial models are calculated to seek the better model.The result revealed that the road surface conditions and vertical and horizontal curvature have greater influence on both pedestrian and driver compared to number of lanes and speed limit.And speed limits were more pronounced for pedestrian crash frequency than driver group.Conversely,the effect of different types of intersections was stronger for driver crash frequency.The differential influences of road physical design attributes on traffic crash frequencies for pedestrians versus drivers highlight the importance of adopting a user-centric approach to transportation safety planning and infrastructure design.Tailoring interventions to address the unique needs and vulnerabilities of different road user groups can lead to more effective safety improvements and better overall traffic safety outcomes.

An Application of RGBD-Based Skeleton Reconstruction for Pedestrian Detection and Occlusion Handling

This study explores the challenges posed by pedestrian detection and occlusion in AR applications, employing a novel approach that utilizes RGB-D-based skeleton reconstruction to reduce the overhead of classical pedestrian detection algorithms during training. Furthermore, it is dedicated to addressing occlusion issues in pedestrian detection by using Azure Kinect for body tracking and integrating a robust occlusion management algorithm, significantly enhancing detection efficiency. In experiments, an average latency of 204 milliseconds was measured, and the detection accuracy reached an outstanding level of 97%. Additionally, this approach has been successfully applied in creating a simple yet captivating augmented reality game, demonstrating the practical application of the algorithm.

A Workable Solution for Reducing the Large Number of Vehicle and Pedestrian Accidents Occurring on a Yellow Light

Traffic intersections are incredibly dangerous for drivers and pedestrians. Statistics from both Canada and the U.S. show a high number of fatalities and serious injuries related to crashes at intersections. In Canada, during 2019, the National Collision Database shows that 28% of traffic fatalities and 42% of serious injuries occurred at intersections. Likewise, the U.S. National Highway Traffic Administration (NHTSA) found that about 40% of the estimated 5,811,000 accidents in the U.S. during the year studied were intersection-related crashes. In fact, a major survey by the car insurance industry found that nearly 85% of drivers could not identify the correct action to take when approaching a yellow traffic light at an intersection. One major reason for these accidents is the “yellow light dilemma,” the ambiguous situation where a driver should stop or proceed forward when unexpectedly faced with a yellow light. This situation is even further exacerbated by the tendency of aggressive drivers to inappropriately speed up on the yellow just to get through the traffic light. A survey of Canadian drivers conducted by the Traffic Injury Research Foundation found that 9% of drivers admitted to speeding up to get through a traffic light. Another reason for these accidents is the increased danger of making a left-hand turn on yellow. According to the National Highway Traffic Safety Association (NHTSA), left turns occur in approximately 22.2% of collisions—as opposed to just 1.2% for right turns. Moreover, a study by CNN found left turns are three times as likely to kill pedestrians than right turns. The reason left turns are so much more likely to cause an accident is because they take a driver against traffic and in the path of oncoming cars. Additionally, most of these left turns occur at the driver’s discretion—as opposed to the distressingly brief left-hand arrow at busy intersections. Drive Safe Now proposes a workable solution for reducing the number of accidents occurring during a yellow light at intersections. We believe this fairly simple solution will save lives, prevent injuries, reduce damage to public and private property, and decrease insurance costs.

改进的YOLOv8n轻量化景区行人检测方法研究

针对景区人流量大、人员密集,而现有目标检测算法对于遮挡目标和小目标检测效率低且模型参数量大等问题,提出基于YOLOv8n的轻量化景区行人检测算法SSC-YOLOv8n。提出空间和通道重建注意力卷积SCC2fEMA模块,以显著减少模型参数量,从而提升模型的检测速度。采用精细的slim-neck范式,通过GSConv和V0V-GSCSP模块,在有效降低模型参数量的同时,提升模型的学习能力。提出坐标注意力动态解耦头,以显著增强模型对位置信息的感知度和敏感度。为了对样本进行更为精确的平衡处理,引入Focal Loss损失函数,进一步提高模型的检测精度与鲁棒性。实验结果表明,在景区行人数据集上,改进后的模型相较于原始模型,模型参数量减小了52%,mAP@0.5提升了2.1个百分点,mAP@0.5:0.95提升了1.4个百分点。在VisDrone2019数据集上,mAP@0.5提高了3.9个百分点。改进后的算法具有更强的泛化性能,能够更好地适用于景区行人检测任务。

信号交叉口行人专用相位设置条件

为高效利用交叉口有限时空资源,研究信号交叉口行人专用相位的设置条件,以提升交叉口通行效率和安全性。首先,分析适宜增设行人专用相位交叉口宏观特征,结合实地调查,确定交叉口尺寸等微观条件;其次,从安全和效率2个维度,分别建立两相位交叉口和增设行人专用相位交叉口总成本评估模型;最后,以交叉口总成本最小为目标,利用数值分析建立交叉口总成本随机动车流量负荷水平、行人流量和转弯率组合变化关系,以确定适宜设置行人专用相位的交通流条件。结果表明:机动车流量低负荷时,通常不考虑增设行人专用相位;机动车流量为中负荷和高负荷时,行人流量需分别超过750 ped/h和900 ped/h且转弯率超过0.4,才考虑增设行人专用相位。

Plant Landscape Design for Commercial Pedestrian Streets

In view of the deficiencies in landscaping of commercial pedestrian streets,this study elaborated the functions of plant landscapes,such as improving the street environment,beautifying the street,creating spaces of diversified uses,and attracting more pedestrians.On the basis of this,plant landscape design principles and techniques for commercial pedestrian streets were put forward,by combining with successful cases,relevant design suggestions were given for particular streets or environments,so as to provide references for the landscaping of commercial pedestrian streets.

Method for pedestrian signal timing at signalized intersections

The pedestrian timing at signalized intersections is studied aiming at the problems of the inconsistency of the vehicular and pedestrian timing requirements and the insufficiency of pedestrian clearance. Based on the formulae of WALK and flashing DON＇T WALK （FDW） in the highway capacity manual （HCM）, the relationship between pedestrian signal indications and vehicular signal indications is discussed using the theory of traffic flow. Then, methods of pedestrian timing for different cases are established, particularly the methods of the pedestrian green adjustment. Ways of pedestrian crossing are analyzed for roadways with different forms and widths of the median island. The sampling values of calculation parameters are studied, and the recommended formulae of pedestrian timing for different conditions are presented.

基于像素差异度注意力机制的轻量化YOLOv5行人检测算法

针对实时行人检测场景存在遮挡、形态姿势不同的行人目标,YOLOv5模型对于这些目标检测有明显的漏检问题,提出一种像素差异度注意力机制(pixel difference attention,PDA),不同于传统的通道注意力机制用全局均值池化(global average pooling,GAP)、全局最大值池化(global max pooling,GMP)来概括整张特征图的信息,全局池化将空间压缩成一个值来表征整个通道,造成了空间信息的流失,PDA将空间信息沿高和宽分别压缩,并将其分别与通道信息联系起来做注意力加权操作,同时提出一种新的通道描述指标表征通道信息,增强空间信息与通道信息的交互,使模型更容易关注到综合了空间和通道维度上的特征图的重要信息,在主干网络末端插入PDA后使模型平均精度(mean average precision,mAP)0.5提升了2.4个百分点,mAP0.5:0.95提升了4.4个百分点;针对实时检测场景的部署和检测速度要求模型拥有较少的参数量和计算量,因此提出了新的轻量化特征提取模块AC3代替原YOLOv5模型中的C3模块,该模块使插入PDA后的改进模型在精度仅仅损失0.2个百分点的情况下,参数量(parameters,Param.)减少了20%左右,浮点运算量(giga floating-point operations,GFLOPs)减少了30%左右。实验结果表明,最终的改进模型比YOLOv5s原模型在VOC行人数据集上mAP0.5提升了2.2个百分点,mAP0.5:0.95提升了3.1个百分点,且参数量减少了20%左右,浮点运算量减少了30%左右,在GTX1050上的检测速度(frames per second,FPS)提升了4。

城市步行安全及其环境影响要素研究综述与展望

【目的】步行空间作为城市公共空间的重要组成部分,其安全品质是构建宜步行城市的重要基础,直接影响居民出行意愿和步行体验。【方法】以Web of Science和CNKI数据库1975—2022年步行安全相关文献为研究对象,通过计量分析与人工检阅相结合的方式,分析当前与步行安全及其环境影响要素研究相关文献的分布特征,梳理研究脉络,分析研究热点。【结果】1)步行环境安全性与行人安全感知主导步行安全研究发展方向,建成环境对行人安全事故以及行人安全感知的影响成为研究者关注的重点,新数据和新技术为分析步行安全环境核心影响要素提供支持。2)在城市建成环境中,街区、街道和交叉口等不同层级的环境要素,从活动安全、交通安全和防卫安全3个维度,对行人步行安全产生重要影响。3)研究对象从客观的建成环境拓展到主观的心理感知,研究内容从个案的安全事故分析拓展到综合的城市环境建设,研究方法方面多维度集成研究逐步替代单专业技术分析。【结论】揭示了步行安全与环境影响要素研究的发展方向、主要脉络以及关注重点,凸显多层级建成环境要素对步行安全事故和行人安全感知的重要影响,为开展步行安全环境实证研究提供理论支持。未来研究中,需对步行安全性和行人安全感知进行协同思考,推进相关研究技术的适用性,关注新兴交通技术发展对步行环境安全品质的影响。

洛阳轨道交通站点步行接驳的影响因素研究

通过分析洛阳轨道交通站点的步行接驳影响因素,旨在为提高公共交通吸引力、优化轨道交通系统和促进可持续交通发展提供参考。研究基于GIS分析、实地调研和调查问卷,重点考察了不同类型站点特征、站点设计与布局、客流特征与出行需求及公共交通政策与管理等因素。结果显示,站点周边的功能混合度、人口密度、公共设施和服务质量等因素,以及站点的出入口位置、数量、通达性对步行接驳质量有显著影响。此外,乘客的出行目的、时间分布和交通换乘需求也对步行接驳服务质量产生影响。基于调研结果,建议采取提升步行网络密度、提升步行网络的整体性等措施,以改善洛阳市轨道交通站点的步行接驳状况。

基于YOLOv7-tiny的轻量级密集人群场景行人检测算法

针对现有的高精度行人检测模型因资源要求高而导致的难以应用于边缘计算场景的问题,提出了一种适用于边缘GPU设备的轻量级实时密集行人检测算法。该算法通过在检测头中融合全维度动态卷积,降低了冗余信息对于检测效果的影响,并通过优化损失函数增强了算法区分待检测目标和背景的能力。实验结果表明,在密集人群场景下的行人检测任务中,该算法在精确度方面较本文基线算法YOLOv7-tiny提升了4.1百分点,这证明该算法能够在边缘计算场景下实现准确的密集人群检测。

基于YOLOv8的林区行人目标检测研究

为解决目标检测算法在林区行人检测中容易出现漏检及检测精度不足的问题,提出一种基于改进YOLOv8的林区行人目标检测算法。采用C2f_DWRSeg模块替换C2f模块,扩展初始卷积通道数,使网络能更高效地进行多尺度特征提取;提出一种重构的检测头,训练时增加卷积层的复杂性,推理时使用单分支结构,从而丰富网络的特征表示能力,并保持高效的推理速度;在特征融合前增加了卷积注意力机制模块CGA,减少计算量;使用Focaler-ShapeIoU损失函数代替CIoU损失函数,弥补边界框回归方法的不足,进一步提高检测能力。试验结果表明,与基准模型相比,改进后的算法mAP50提高了2%,mAP50-95提高了2.4%,模型的处理速度(FPS)提高了4.33%,证明改进后的算法能够更好地应用在林区行人检测的任务中。

超大跨预制混凝土双T板振动舒适度足尺试验研究

对跨度为30m的超大跨预制预应力混凝土双T板开展了足尺动力测试,并进行了人致振动舒适度分析,讨论了现有评估方法的适用性。试验结果表明,双T板的竖向基频满足PCI规范的限值要求,但其在三人屈伸工况下的加速度响应略不满足AISC DG 11规范的限值要求。考虑到振动舒适度问题,不建议将超大跨双T板应用于办公、住宅等限制严格的环境中。实际结构中双T板翼缘连接成整体后其动力学性能会得到加强,提供了较大的舒适度储备。