Search

The continuous downward movement exhibited by the Lashagou landslide group in recent years poses a significant threat to the safety of both vehicles and pedestrians traversing the highway G310. By integrating geomorphological interpretation using multi-temporal optical images, interferometric synthetic aperture radar (InSAR) measurements, and continuous global navigation satellite system (GNSS) observations, this paper traced the formation period of the Lashagou landslide group, and explored its kinematic behavior under external drivers such as rainfall and snowmelt. The results indicate that the formation period can be specifically categorized into three periods: before, during, and after the construction of highway G310. The construction of highway G310 is the direct cause and prerequisite for the formation of the Lashagou landslide group, whereas summer precipitation and spring snowmelt are the external driving factors contributing to its continuous downward movement. Additionally, both the long-term seasonal downslope movement and transient acceleration events are strongly controlled by rainfall, and there is a time lag of approximately 1–2 days between the transient acceleration and heavy rainfall events. This study highlights the benefits of leveraging multi-source remote sensing data to investigate slow-moving landslides, which is advantageous for the implementation of effective control and engineering intervention to mitigate potential landslide disasters. [ABSTRACT FROM AUTHOR]

LiDAR-based 3D object detection and localization are crucial components of autonomous navigation systems, including autonomous vehicles and mobile robots. Most existing LiDAR-based 3D object detection and localization approaches primarily use geometric or structural feature abstractions from LiDAR point clouds. However, these approaches can be susceptible to environmental noise due to adverse weather conditions or the presence of highly scattering media. In this work, we propose an intensity-aware voxel encoder for robust 3D object detection. The proposed voxel encoder generates an intensity histogram that describes the distribution of point intensities within a voxel and is used to enhance the voxel feature set. We integrate this intensity-aware encoder into an efficient single-stage voxel-based detector for 3D object detection. Experimental results obtained using the KITTI dataset show that our method achieves comparable results with respect to the state-of-the-art method for car objects in 3D detection and from a bird's-eye view and superior results for pedestrian and cyclic objects. Furthermore, our model can achieve a detection rate of 40.7 FPS during inference time, which is higher than that of the state-of-the-art methods and incurs a lower computational cost. [ABSTRACT FROM AUTHOR]

With the continuous advancement of autonomous driving and monitoring technologies, there is increasing attention on non-intrusive target monitoring and recognition. This paper proposes an ArcFace SE-attention model-agnostic meta-learning approach (AS-MAML) by integrating attention mechanisms into residual networks for pedestrian gait recognition using frequency-modulated continuous-wave (FMCW) millimeter-wave radar through meta-learning. We enhance the feature extraction capability of the base network using channel attention mechanisms and integrate the additive angular margin loss function (ArcFace loss) into the inner loop of MAML to constrain inner loop optimization and improve radar discrimination. Then, this network is used to classify small-sample micro-Doppler images obtained from millimeter-wave radar as the data source for pose recognition. Experimental tests were conducted on pose estimation and image classification tasks. The results demonstrate significant detection and recognition performance, with an accuracy of 94.5%, accompanied by a 95% confidence interval. Additionally, on the open-source dataset DIAT-μRadHAR, which is specially processed to increase classification difficulty, the network achieves a classification accuracy of 85.9%. [ABSTRACT FROM AUTHOR]

This study investigated the interplay between exit selection models and local pedestrian movement patterns within floor field frameworks. Specifically, this investigation analysed the performance of a multinomial logit exit choice model, incorporating both expected utility theory and cumulative prospect theory frameworks when coupled with three distinct local-level pedestrian movement models (FF-Von Neumann, FF-Moore, and NSFF). The expected utility theory framework considers the deterministic component as a linear relationship, while the cumulative prospect theory framework further considers the decision-maker's risky attitudes by transforming objective terms into subjective terms using a power value function. The core objective was to comprehend how local movement dynamics, as represented by the floor field models, influence decision-making during exit selection. Comparative analyses revealed intriguing variations between the three local models, despite their shared expected utility theory-based exit choice framework. These discrepancies stemmed from the diverse pedestrian trajectory behaviours generated by each model. Consequently, these local dynamics impacted the decision-maker's assessment of critical factors, such as the number of evacuees close to the decision-maker ( N C D M ) and the number of evacuees close to an exit ( N C E ), which the exit choice model incorporates. These assessments, in turn, significantly affected higher-level decision-making. The integration of the three models with the multinomial logit exit choice model, using either cumulative prospect theory and expected utility theory frameworks, further strengthened the observed bilateral relationship. While the specific nature of this relationship varied depending on the chosen framework and its implementation details, these consistent findings demonstrate the robustness of the results. This reinforced the influence of local-level pedestrian dynamics on higher-level exit selection, highlighting the importance of accurate crowd dynamics modelling, especially when advanced exit choice models consider local movement factors. [ABSTRACT FROM AUTHOR]

Predicting human trajectories poses a significant challenge due to the complex interplay of pedestrian behavior, which is influenced by environmental layout and interpersonal dynamics. This complexity is further compounded by variations in scene density. To address this, we introduce a novel dataset from the Festival of Lights in Lyon 2022, characterized by a wide range of densities (0.2–2.2 ped/ m 2 ). Our analysis demonstrates that density-based classification of data can significantly enhance the accuracy of predictive algorithms. We propose an innovative two-stage processing approach, surpassing current state-of-the-art methods in performance. Additionally, we utilize a collision-based error metric to better account for collisions in trajectory predictions. Our findings indicate that the effectiveness of this error metric is density-dependent, offering prediction insights. This study not only advances our understanding of human trajectory prediction in dense environments, but also presents a methodological framework for integrating density considerations into predictive modeling, thereby improving algorithmic performance and collision avoidance. [ABSTRACT FROM AUTHOR]

In the pedestrian navigation system, researchers have reduced measurement errors and improved system navigation performance by fusing measurements from multiple low-cost inertial measurement unit (IMU) arrays. Unfortunately, the current data fusion methods for inertial sensor arrays ignore the system error compensation of individual IMUs and the correction of position information in the zero-velocity interval. Therefore, these methods cannot effectively reduce errors and improve accuracy. An error compensation method for pedestrian navigation systems based on a low-cost array of IMUs is proposed in this paper. The calibration method for multiple location-free IMUs is improved by using a sliding variance detector to segment the angular velocity magnitude into stationary and motion intervals, and each IMU is calibrated independently. Compensation is then applied to the velocity residuals in the zero-velocity interval after zero-velocity update (ZUPT). The experimental results show a significant improvement in the average noise performance of the calibrated IMU array, with a 3.01-fold increase in static noise performance. In the closed-loop walking experiment, the average horizontal position error of a single calibrated IMU is reduced by 27.52% compared to the uncalibrated IMU, while the calibrated IMU array shows a 2.98-fold reduction in average horizontal position error compared to a single calibrated IMU. After compensating for residual velocity, the average horizontal position error of a single IMU is reduced by 0.73 m, while that of the IMU array is reduced by 64.52%. [ABSTRACT FROM AUTHOR]

Nowadays, with the rapid development of consumer Unmanned Aerial Vehicles (UAVs), utilizing UAV platforms for visual surveillance has become very attractive, and a key part of this is remote vision-based pedestrian attribute recognition. Pedestrian Attribute Recognition (PAR) is dedicated to predicting multiple attribute labels of a single pedestrian image extracted from surveillance videos and aerial imagery, which presents significant challenges in the computer vision community due to factors such as poor imaging quality and substantial pose variations. Despite recent studies demonstrating impressive advancements in utilizing complicated architectures and exploring relations, most of them may fail to fully and systematically consider the inter-region, inter-attribute, and region-attribute mapping relations simultaneously and be stuck in the dilemma of information redundancy, leading to the degradation of recognition accuracy. To address the issues, we construct a novel Mask-Relation-Guided Transformer (MRG-T) framework that consists of three relation modeling modules to fully exploit spatial and semantic relations in the model learning process. Specifically, we first propose a Masked Region Relation Module (MRRM) to focus on precise spatial attention regions to extract more robust features with masked random patch training. To explore the semantic association of attributes, we further present a Masked Attribute Relation Module (MARM) to extract intrinsic and semantic inter-attribute relations with an attribute label masking strategy. Based on the cross-attention mechanism, we finally design a Region and Attribute Mapping Module (RAMM) to learn the cross-modal alignment between spatial regions and semantic attributes. We conduct comprehensive experiments on three public benchmarks such as PETA, PA-100K, and RAPv1, and conduct inference on a large-scale airborne person dataset named PRAI-1581. The extensive experimental results demonstrate the superior performance of our method compared to state-of-the-art approaches and validate the effectiveness of mask-relation-guided modeling in the remote vision-based PAR task. [ABSTRACT FROM AUTHOR]

Understanding pedestrian dynamics at bottlenecks and how pedestrians interact with their environment—particularly how they use and move in the space available to them—is of safety importance, since bottlenecks are a key point for pedestrian flow. We performed a series of experiments in which participants walked through a bottleneck individually for varying combinations of approaching angle, bottleneck width and walking speed, to investigate the dependence of the movement on safety-relevant influencing factors. Trajectories as well as 3D motion data were recorded for every participant. This paper shows that (1) the maximum amplitude of shoulder rotation is mainly determined by the ratio of the bottleneck width to the shoulder width of the participant, while the direction is determined by the starting angle and the foot position; (2) the 'critical point' is not invariant to the starting angle and walking speed; (3) differences between the maximum and minimum speed values arise mainly from the distribution of deceleration patterns; and (4) the position of crossing shifts by 1.75 cm/10 cm, increasing the bottleneck width in the direction of origin. [ABSTRACT FROM AUTHOR]

Enhancing the environmental perception of autonomous vehicles (AVs) in intelligent transportation systems requires computer vision technology to be effective in detecting objects and obstacles, particularly in adverse weather conditions. Adverse weather circumstances present serious difficulties for object-detecting systems, which are essential to contemporary safety procedures, infrastructure for monitoring, and intelligent transportation. AVs primarily depend on image processing algorithms that utilize a wide range of onboard visual sensors for guidance and decisionmaking. Ensuring the consistent identification of critical elements such as vehicles, pedestrians, and road lanes, even in adverse weather, is a paramount objective. This paper not only provides a comprehensive review of the literature on object detection (OD) under adverse weather conditions but also delves into the ever-evolving realm of the architecture of AVs, challenges for automated vehicles in adverse weather, the basic structure of OD, and explores the landscape of traditional and deep learning (DL) approaches for OD within the realm of AVs. These approaches are essential for advancing the capabilities of AVs in recognizing and responding to objects in their surroundings. This paper further investigates previous research that has employed both traditional and DL methodologies for the detection of vehicles, pedestrians, and road lanes, effectively linking these approaches with the evolving field of AVs. Moreover, this paper offers an in-depth analysis of the datasets commonly employed in AV research, with a specific focus on the detection of key elements in various environmental conditions, and then summarizes the evaluation matrix. We expect that this review paper will help scholars to gain a better understanding of this area of research. [ABSTRACT FROM AUTHOR]

Nighttime object detection is challenging due to dim, uneven lighting. The IIHS research conducted in 2022 shows that pedestrian anti-collision systems are less effective at night. Common solutions utilize costly sensors, such as thermal imaging and LiDAR, aiming for highly accurate detection. Conversely, this study employs a low-cost 2D image approach to address the problem by drawing inspiration from biological dark adaptation mechanisms, simulating functions like pupils and photoreceptor cells. Instead of relying on extensive machine learning with day-to-night image conversions, it focuses on image fusion and gamma correction to train deep neural networks for dark adaptation. This research also involves creating a simulated environment ranging from 0 lux to high brightness, testing the limits of object detection, and offering a high dynamic range testing method. Results indicate that the dark adaptation model developed in this study improves the mean average precision (mAP) by 1.5−6% compared to traditional models. Our model is capable of functioning in both twilight and night, showcasing academic novelty. Future developments could include using virtual light in specific image areas or integrating with smart car lighting to enhance detection accuracy, thereby improving safety for pedestrians and drivers. [ABSTRACT FROM AUTHOR]

With the development of intelligent vehicle technology, the probability of road traffic accidents occurring has been effectively reduced to a certain extent. However, there is still insufficient research on head injuries in human vehicle collisions, making it impossible to effectively predict pedestrian head injuries in accidents. To study the efficacy of a combined active and passive safety system on pedestrian head protection through the combined effect of the exterior airbag and the braking control systems of an intelligent vehicle, a "vehicle–pedestrian" interaction system is constructed in this study and is verified by real collision cases. On this basis, a combined active and passive system database is developed to analyze the cross-influence of the engine hood airbag and the vehicle braking curve parameters on pedestrian HIC (head injury criterion). Meanwhile, a hierarchy design strategy for a combined active and passive system is proposed, and a rapid prediction of HIC is achieved via the establishment of a fitting equation for each grading. The results show that the exterior airbag can effectively protect the pedestrian's head, prevent the collision between the pedestrian's head and the vehicle front structure, and reduce the HIC. The braking parameter H2 is significantly correlated with head injury, and when H2 is less than 1.8, the HIC value is less than 1000 in nearly 90% of cases. The hierarchy design strategy and HIC prediction method of the combined active and passive system proposed in this paper can provide a theoretical basis for rapid selection and parameter design. [ABSTRACT FROM AUTHOR]

Large-scale crowd phenomena are complex to model because the behaviour of pedestrians needs to be described at both strategic, tactical, and operational levels and is impacted by the density of the crowd. Microscopic models manage to mimic the dynamics at low densities, whereas mesoscopic models achieve better performances in dense situations. This paper proposes and evaluates a novel agent-based model to enable agents to dynamically change their operational model based on local density. The ability to combine microscopic and mesoscopic models for multi-scale simulation is studied through a use case of pedestrians at the Festival of Lights, Lyon, France. Pedestrian outflow data are extracted from video recordings of exiting crowds at the festival. The hybrid model is calibrated and validated using a genetic algorithm that optimises the match between simulated and observed outflow data. Additionally, a local sensitivity analysis is then conducted to identify the most sensitive parameters in the model. Finally, the performance of the hybrid model is compared to different models in terms of density map and computation time. The results demonstrate that the hybrid model has the capacity to effectively simulate pedestrians across varied density scenarios while optimising computational performance compared to other models. [ABSTRACT FROM AUTHOR]

In urban settings, roadside infrastructure LiDAR is a ground-based remote sensing system that collects 3D sparse point clouds for the traffic object detection of vehicles, pedestrians, and cyclists. Current anchor-free algorithms for 3D point cloud object detection based on roadside infrastructure face challenges related to inadequate feature extraction, disregard for spatial information in large 3D scenes, and inaccurate object detection. In this study, we propose AFRNet, a two-stage anchor-free detection network, to address the aforementioned challenges. We propose a 3D feature extraction backbone based on the large sparse kernel convolution (LSKC) feature set abstraction module, and incorporate the CBAM attention mechanism to enhance the large scene feature extraction capability and the representation of the point cloud features, enabling the network to prioritize the object of interest. After completing the first stage of center-based prediction, we propose a refinement method based on attentional feature fusion, where fused features incorporating raw point cloud features, voxel features, BEV features, and key point features are used for the second stage of refinement to complete the detection of 3D objects. To evaluate the performance of our detection algorithms, we conducted experiments using roadside LiDAR data from the urban traffic dataset DAIR-V2X, based on the Beijing High-Level Automated Driving Demonstration Area. The experimental results show that AFRNet has an average of 5.27 percent higher detection accuracy than CenterPoint for traffic objects. Comparative tests further confirm that our method achieves high accuracy in roadside LiDAR object detection. [ABSTRACT FROM AUTHOR]

Rapid advances in technology and shifting tastes among motorists have reworked the contemporary automobile production sector. Driving is now much safer and more convenient than ever before thanks to a plethora of new technology and apps. Millions of people are hurt every year despite the fact that automobiles are networked and have several sensors and radars for collision avoidance. Each year, many of them are injured in car accidents and need emergency care, and sadly, the fatality rate is growing. Vehicle and pedestrian collisions are still a serious problem, making it imperative to advance methods that prevent them. This paper refines our previous efficient VANET-based pedestrian safety system based on two-way communication between smart cars and the cell phones of vulnerable road users. We implemented the scheme using C and NS3 to simulate different traffic scenarios. Our objective is to measure the additional overhead to protect vulnerable road users. We prove that our proposed scheme adds just a little amount of additional overhead and successfully satisfies the stringent criteria of safety applications. [ABSTRACT FROM AUTHOR]

Pedestrian detection is a critical task for safety-critical systems, but detecting pedestrians is challenging in low-light and adverse weather conditions. Thermal images can be used to improve robustness by providing complementary information to RGB images. Previous studies have shown that multi-modal feature fusion using convolution operation can be effective, but such methods rely solely on local feature correlations, which can degrade the performance capabilities. To address this issue, we propose an attention-based novel fusion network, referred to as INSANet (INtra-INter Spectral Attention Network), that captures global intra- and inter-information. It consists of intra- and inter-spectral attention blocks that allow the model to learn mutual spectral relationships. Additionally, we identified an imbalance in the multispectral dataset caused by several factors and designed an augmentation strategy that mitigates concentrated distributions and enables the model to learn the diverse locations of pedestrians. Extensive experiments demonstrate the effectiveness of the proposed methods, which achieve state-of-the-art performance on the KAIST dataset and LLVIP dataset. Finally, we conduct a regional performance evaluation to demonstrate the effectiveness of our proposed network in various regions. [ABSTRACT FROM AUTHOR]

The zero-velocity update (ZUPT) algorithm is a pivotal advancement in pedestrian navigation accuracy, utilizing foot-mounted inertial sensors. Its key issue hinges on accurately identifying periods of zero-velocity during human movement. This paper introduces an innovative adaptive sliding window technique, leveraging the Fourier Transform to precisely isolate the pedestrian's gait frequency from spectral data. Building on this, the algorithm adaptively adjusts the zero-velocity detection threshold in accordance with the identified gait frequency. This adaptation significantly refines the accuracy in detecting zero-velocity intervals. Experimental evaluations reveal that this method outperforms traditional fixed-threshold approaches by enhancing precision and minimizing false positives. Experiments on single-step estimation show the adaptability of the algorithm to motion states such as slow, fast, and running. Additionally, the paper demonstrates pedestrian trajectory localization experiments under a variety of walking conditions. These tests confirm that the proposed method substantially improves the performance of the ZUPT algorithm, highlighting its potential for pedestrian navigation systems. [ABSTRACT FROM AUTHOR]

Pedestrian tracking in surveillance videos is crucial and challenging for precise personnel management. Due to the limited coverage of a single video, the integration of multiple surveillance videos is necessary in practical applications. In the realm of pedestrian management using multiple surveillance videos, continuous pedestrian tracking is quite important. However, prevailing cross-video pedestrian matching methods mainly rely on the appearance features of pedestrians, resulting in low matching accuracy and poor tracking robustness. To address these shortcomings, this paper presents a cross-video pedestrian tracking algorithm, which introduces spatial information. The proposed algorithm introduces the coordinate features of pedestrians in different videos and a linear weighting strategy focusing on the overlapping view of the tracking process. The experimental results show that, compared to traditional methods, the method in this paper improves the success rate of target pedestrian matching and enhances the robustness of continuous pedestrian tracking. This study provides a viable reference for pedestrian tracking and crowd management in video applications. [ABSTRACT FROM AUTHOR]

Effective collision risk reduction in autonomous vehicles relies on robust and straightforward pedestrian tracking. Challenges posed by occlusion and switching scenarios significantly impede the reliability of pedestrian tracking. In the current study, we strive to enhance the reliability and also the efficacy of pedestrian tracking in complex scenarios. Particularly, we introduce a new pedestrian tracking algorithm that leverages both the YOLOv8 (You Only Look Once) object detector technique and the StrongSORT algorithm, which is an advanced deep learning multi-object tracking (MOT) method. Our findings demonstrate that StrongSORT, an enhanced version of the DeepSORT MOT algorithm, substantially improves tracking accuracy through meticulous hyperparameter tuning. Overall, the experimental results reveal that the proposed algorithm is an effective and efficient method for pedestrian tracking, particularly in complex scenarios encountered in the MOT16 and MOT17 datasets. The combined use of Yolov8 and StrongSORT contributes to enhanced tracking results, emphasizing the synergistic relationship between detection and tracking modules. [ABSTRACT FROM AUTHOR]

Robust and accurate three-dimensional localization is essential for personal navigation, emergency rescue, and worker monitoring in indoor environments. For localization technology to be employed in various applications, it is necessary to reduce infrastructure dependence and limit the maximum error bound. This study aims to accurately estimate the location of various people using smartphones in a building with a cloud platform-based localization system. The proposed technology is modularized in a hierarchical structure to sequentially estimate the floor and location. This system comprises four localization modules: course level detection, fine level detection (FLD), fine location tracking (FLT), and level change detection (LCD). Each module operates organically according to the current user status. The position estimation range is defined as a total of three phases, and an appropriate location estimation module suitable for the corresponding phase operates to estimate the user's location gradually and precisely. When the user's floor is determined by an FLD, the two-dimensional position of the user is estimated by an FLT module that tracks the user's position by comparing the received signal strength indicator vector sequence and radio map. Also, LCD recognizes the user's floor change and converts the user's phase. To verify the proposed technology, various experiments were conducted in a six-story building, and an average accuracy of less than 2 m was obtained. [ABSTRACT FROM AUTHOR]

Statistical mechanics of walks defined on the spatial graphs of the city of Lubbock (10,421 nodes) and the Texas Tech University (TTU) campus pedestrian network (1466 nodes) are used for evaluating structural isolation and the integration of graph nodes, assessing their accessibility and navigability in the graph, and predicting possible graph structural modifications driving the campus evolution. We present the betweenness and closeness maps of the campus, the first passage times to the different campus areas by isotropic and anisotropic random walks, as well as the first passage times under the conditions of traffic noise. We further show the isolation and integration indices of all areas on the campus, as well as their navigability and strive scores, and energy and fugacity scores. The TTU university campus, a large pedestrian zone located close to the historical city center of Lubbock, mediates between the historical city going downhill and its runaway sprawling body. [ABSTRACT FROM AUTHOR]

Pedestrian detection has always been a difficult and hot spot in computer vision research. At the same time, pedestrian detection technology plays an important role in many applications, such as intelligent transportation and security monitoring. In complex scenes, pedestrian detection often faces some challenges, such as low detection accuracy and misdetection due to small target sizes and scale variations. To solve these problems, this paper proposes a pedestrian detection network PT-YOLO based on the YOLOv5. The pedestrian detection network PT-YOLO consists of the YOLOv5 network, the squeeze-and-excitation module (SE), the weighted bi-directional feature pyramid module (BiFPN), the coordinate convolution (coordconv) module and the wise intersection over union loss function (WIoU). The SE module in the backbone allows it to focus on the important features of pedestrians and improves accuracy. The weighted BiFPN module enhances the fusion of multi-scale pedestrian features and information transfer, which can improve fusion efficiency. The prediction head design uses the WIoU loss function to reduce the regression error. The coordconv module allows the network to better perceive the location information in the feature map. The experimental results show that the pedestrian detection network PT-YOLO is more accurate compared with other target detection methods in pedestrian detection and can effectively accomplish the task of pedestrian detection in complex scenes. [ABSTRACT FROM AUTHOR]

Analysis of pedestrians' head and lower limb injuries at the tissue level is lacking in studies of tram–pedestrian collisions. The purpose of this paper therefore to investigate the impact response process and severity of pedestrians' injuries in tram–pedestrian collisions, using the Total Human Model for Safety (THUMS) pedestrian human body model together with the tram FE model. Two full-scale tram–pedestrian dummy crash tests were performed to validate the FE model, and the total correlation and analysis (CORA) score of head acceleration yielded values of 0.840 and 0.734, confirming a strong agreement between the FE-simulated head responses and the experimental head kinematics. The effects of different tram speeds and impact angles on pedestrians' impact response injuries and the differences were further analyzed. The results indicate that direct impact of the lower limb with the tram's obstacle deflector leads to lower limb bone shaft fractures and knee tissue damage. Neck fling contributed to worsened head injury. Coup contusions were the predominant type of brain contusion, surpassing contrecoup contusions, while diffuse axonal injury was mainly concentrated in the collision-side region of the brain. Pedestrians' injuries are influenced by tram velocity and impact angle: higher tram velocities increase the risk of lower limb and head injuries. The risk of head injury for pedestrians is higher when the impact angle is negative, while lower limb injuries are more significant when the impact angle is 0°. This study provides practical guidance for enhancing tram safety and protecting pedestrians. [ABSTRACT FROM AUTHOR]

Lighting pedestrian crossings play an important role in ensuring the safety of pedestrians on the road, especially at night or in conditions of reduced visibility. Currently functioning normative and formal requirements, which are the basis for the design of lighting for pedestrian crossings, are described by criteria of lighting intensity. Each of the existing solutions operates in an urban environment, and at the stage of design and operation, the obtained values of the produced luminance contrast of the pedestrian silhouette and its background are not known. The main purpose of the article is to compare, based on luminance parameters, the three lighting solutions used at pedestrian crossings. This article presents and describes the method of determining the luminance contrast based on luminance measurements of the pedestrian silhouette and its background. Detailed results of measurements of luminance parameters at selected pedestrian crossings are presented. An analysis of the results was made with a breakdown of typical lighting solutions used in urban conditions. The differences between standard lighting were discussed, as well as supplementary and dedicated lighting. The obtained ranges of luminance contrast levels occurring in urban conditions for individual solutions were determined. The energy indicator for each solution was determined. [ABSTRACT FROM AUTHOR]

This paper proposes a novel prediction model termed the social and spatial attentive generative adversarial network (SSA-GAN). The SSA-GAN framework utilizes a generative approach, where the generator employs social attention mechanisms to accurately model social interactions among pedestrians. Unlike previous methodologies, our model utilizes comprehensive motion features as query vectors, significantly enhancing predictive performance. Additionally, spatial attention is integrated to encapsulate the interactions between pedestrians and their spatial context through semantic spatial features. Moreover, we present a novel approach for generating simulated multi-trajectory datasets using the CARLA simulator. This method circumvents the limitations inherent in existing public datasets such as UCY and ETH, particularly when evaluating multi-trajectory metrics. Our experimental findings substantiate the efficacy of the proposed SSA-GAN model in capturing the nuances of pedestrian interactions and providing accurate multimodal trajectory predictions. [ABSTRACT FROM AUTHOR]

A simple approach to the Hamiltonian theory of radiation phenomena is proposed. It is shown that the so-called "Trautman-Bondi-mass", known to a rather narrow circle of specialists in general relativity, appears naturally in any special relativistic field theory. The structure of the "radiation data phase space" for the field and its isomorphism with the "Cauchy data phase space" are thoroughly analyzed. [ABSTRACT FROM AUTHOR]

Signal control, as an integral component of traffic management, plays a pivotal role in enhancing the efficiency of traffic and reducing environmental pollution. However, the majority of signal control research based on game theory primarily focuses on vehicular perspectives, often neglecting pedestrians, who are significant participants at intersections. This paper introduces a game theory-based signal control approach designed to minimize and equalize the queued vehicles and pedestrians across the different phases. The Nash bargaining solution is employed to determine the optimal green duration for each phase within a fixed cycle length. Several simulation tests were carried out by SUMO software to assess the effectiveness of this proposed approach. We select the actuated signal control approach as the baseline to demonstrate the superiority and stability of the proposed control strategy. The simulation results reveal that the proposed approach is able to reduce pedestrian and vehicle delay, vehicle queue length, fuel consumption, and CO2 emissions under different demand levels and demand patterns. Furthermore, the proposed approach consistently achieves more equalized queue length for each lane compared to the actuated control strategy, indicating a higher degree of fairness. [ABSTRACT FROM AUTHOR]

Pedestrian detection based on deep learning methods have reached great success in the past few years with several possible real-world applications including autonomous driving, robotic navigation, and video surveillance. In this work, a new neural network two-stage pedestrian detector with a new custom classification head, adding the triplet loss function to the standard bounding box regression and classification losses, is presented. This aims to improve the domain generalization capabilities of existing pedestrian detectors, by explicitly maximizing inter-class distance and minimizing intra-class distance. Triplet loss is applied to the features generated by the region proposal network, aimed at clustering together pedestrian samples in the features space. We used Faster R-CNN and Cascade R-CNN with the HRNet backbone pre-trained on ImageNet, changing the standard classification head for Faster R-CNN, and changing one of the three heads for Cascade R-CNN. The best results were obtained using a progressive training pipeline, starting from a dataset that is further away from the target domain, and progressively fine-tuning on datasets closer to the target domain. We obtained state-of-the-art results, M R − 2 of 9.9, 11.0, and 36.2 for the reasonable, small, and heavy subsets on the CityPersons benchmark with outstanding performance on the heavy subset, the most difficult one. [ABSTRACT FROM AUTHOR]

As micro-electro-mechanical systems (MEMS) technology continues its rapid ascent, a growing array of smart devices are integrating lightweight, compact, and cost-efficient magnetometers and inertial sensors, paving the way for advanced human motion analysis. However, sensors housed within smartphones frequently grapple with the detrimental effects of magnetic interference on heading estimation, resulting in diminished accuracy. To counteract this challenge, this study introduces a method that synergistically employs convolutional neural networks (CNNs) and support vector machines (SVMs) for adept interference detection. Utilizing a CNN, we automatically extract profound features from single-step pedestrian motion data that are then channeled into an SVM for interference detection. Based on these insights, we formulate heading estimation strategies aptly suited for scenarios both devoid of and subjected to magnetic interference. Empirical assessments underscore our method's prowess, boasting an impressive interference detection accuracy of 99.38%. In indoor environments influenced by such magnetic disturbances, evaluations conducted along square and equilateral triangle trajectories revealed single-step heading absolute error averages of 2.1891° and 1.5805°, with positioning errors averaging 0.7565 m and 0.3856 m, respectively. These results lucidly attest to the robustness of our proposed approach in enhancing indoor pedestrian positioning accuracy in the face of magnetic interferences. [ABSTRACT FROM AUTHOR]

Multi-camera video surveillance has been widely applied in crowd statistics and analysis in smart city scenarios. Most existing studies rely on appearance or motion features for cross-camera trajectory tracking, due to the changing asymmetric perspectives of multiple cameras and occlusions in crowded scenes, resulting in low accuracy and poor tracking performance. This paper proposes a tracking method that fuses appearance and motion features. An implicit social model is used to obtain motion features containing spatio-temporal information and social relations for trajectory prediction. The TransReID model is used to obtain appearance features for re-identification. Fused features are derived by integrating appearance features, spatio-temporal information and social relations. Based on the fused features, multi-round clustering is adopted to associate cross-camera objects. Exclusively employing robust pedestrian reidentification and trajectory prediction models, coupled with the real-time detector YOLOX, without any reliance on supplementary information, an IDF1 score of 70.64% is attained on typical datasets derived from AiCity2023. [ABSTRACT FROM AUTHOR]

Three-dimensional (3D) indoor models are a crucial component to simulate pedestrian evacuations realistically in indoor environments. However, existing 3D indoor models cannot fully represent realistic indoor environments to enable the simulation of 3D pedestrian motions in evacuations because spaces above/below some physical components (e.g., desks, chairs) have been largely overlooked. Thus, this paper introduces a conceptual space model to advance a space identification and classification scheme that can fully capture 3D pedestrian motions. This paper first proposes the definition and parameterisation of different 3D pedestrian motions. Then, the definition and specifications of three categories of space components are elaborated on based on the motions. Finally, a voxel-based approach is introduced to identify and classify the space components, which are demonstrated by an illustrative example. This work contributes to advancing 3D indoor modelling to enable a more realistic simulation of 3D pedestrian motions. [ABSTRACT FROM AUTHOR]

Occluded pedestrian detection faces huge challenges. False positives and false negatives in crowd occlusion scenes will reduce the accuracy of occluded pedestrian detection. To overcome this problem, we proposed an improved you-only-look-once version 3 (YOLOv3) based on squeeze-and-excitation networks (SENet) and optimized generalized intersection over union (GIoU) loss for occluded pedestrian detection, namely YOLOv3-Occlusion (YOLOv3-Occ). The proposed network model considered incorporating squeeze-and-excitation networks (SENet) into YOLOv3, which assigned greater weights to the features of unobstructed parts of pedestrians to solve the problem of feature extraction against unsheltered parts. For the loss function, a new generalized intersection over unionintersection over groundtruth (GIoUIoG) loss was developed to ensure the areas of predicted frames of pedestrian invariant based on the GIoU loss, which tackled the problem of inaccurate positioning of pedestrians. The proposed method, YOLOv3-Occ, was validated on the CityPersons and COCO2014 datasets. Experimental results show the proposed method could obtain 1.2% MR−2 gains on the CityPersons dataset and 0.7% mAP@50 improvements on the COCO2014 dataset. [ABSTRACT FROM AUTHOR]

Object detection in pedestrian walkways is a crucial area of research that is widely used to improve the safety of pedestrians. It is not only challenging but also a tedious process to manually examine the labeling of abnormal actions, owing to its broad applications in video surveillance systems and the larger number of videos captured. Thus, an automatic surveillance system that identifies the anomalies has become indispensable for computer vision (CV) researcher workers. The recent advancements in deep learning (DL) algorithms have attracted wide attention for CV processes such as object detection and object classification based on supervised learning that requires labels. The current research study designs the bioinspired Garra rufa optimization-assisted deep learning model for object classification (BGRODL-OC) technique on pedestrian walkways. The objective of the BGRODL-OC technique is to recognize the presence of pedestrians and objects in the surveillance video. To achieve this goal, the BGRODL-OC technique primarily applies the GhostNet feature extractors to produce a set of feature vectors. In addition to this, the BGRODL-OC technique makes use of the GRO algorithm for hyperparameter tuning process. Finally, the object classification is performed via the attention-based long short-term memory (ALSTM) network. A wide range of experimental analysis was conducted to validate the superior performance of the BGRODL-OC technique. The experimental values established the superior performance of the BGRODL-OC algorithm over other existing approaches. [ABSTRACT FROM AUTHOR]

As was shown in the previous part of the study, windshields are an important part of the passive safety means of modern low-floor trams with an extraordinary effect on pedestrian safety in a pedestrian–tram collisions. Therefore, maximum attention must be paid to the definition of tram windshield characteristics. This article describes a windshield crash test, from which data are obtained to verify the feasibility of the applied computational approaches. A developed analytical model is utilised for a simple description of the energy balance during collision with an illustrative definition of the important parameters of laminated glass as well as their clear physical interpretations. The finite element analysis (FEA) performed in Ansys software using two versions of material definition, namely a simpler (*MAT_ELASTIC with nonlocal failure criterion) and a more complex (*MAT_GLASS with brittle stress-state-dependent failure) material model, which are presented as suitable for obtaining a detailed description of the shattering process of laminated glass, which can also be used effectively in windshield engineering. [ABSTRACT FROM AUTHOR]

This article represents the first paper in a two-part series dealing with safety during tram–pedestrian collisions. This research is dedicated to the safety of trams for pedestrians during collisions and is motivated by the increased number of lethal cases. The first part of this paper includes an overview of tram face development from the earliest designs to the current ones in use and, at the same time, provides a synopsis and explanation of the technical context, including a link to current and forthcoming legislation. The historical design development can be characterised by three steps, from an almost vertical front face, to leaned and pointed shapes, to the current inclined low-edged windshield without a protruding coupler. However, since most major manufacturers now export their products worldwide and customisation is only of a technically insignificant nature, our conclusions are generalisable (supported by the example of Berlin). The most advantageous shape of the tram's front, minimising the effects on pedestrians in all collision phases, has evolved rather spontaneously and was unprompted, and it is now being built into the European Commission regulations. The goal of the second part of this paper is to conduct a series of tram–pedestrian collisions with a focus on the frontal and side impacts using a crash test dummy (anthropomorphic test device—ATD). Four tram types approaching the collision at four different impact speeds (5 km/h, 10 km/h, 15 km/h, and 20 km/h) were used. The primary outcome variable was the resultant head acceleration. The risk and severity of possible head injuries were assessed using the head injury criterion (HIC15) and its linkage to the injury level on the Abbreviated Injury Scale (AIS). The results showed increasing head impacts with an increasing speed for all tram types and collision scenarios. Higher values of head acceleration were reached during the frontal impact (17–124 g) compared to the side one (2–84 g). The HIC15 values did not exceed the value of 300 for any experimental setting, and the probability of AIS4+ injuries did not exceed 10%. The outcomes of tram–pedestrian collisions can be influenced by the ATD's position and orientation, the impact speed and front-end design of trams, and the site of initial contact. [ABSTRACT FROM AUTHOR]

This paper proposes a multimodal fusion 3D target detection algorithm based on the attention mechanism to improve the performance of 3D target detection. The algorithm utilizes point cloud data and information from the camera. For image feature extraction, the ResNet50 + FPN architecture extracts features at four levels. Point cloud feature extraction employs the voxel method and FCN to extract point and voxel features. The fusion of image and point cloud features is achieved through regional point fusion and voxel fusion methods. After information fusion, the Coordinate and SimAM attention mechanisms extract fusion features at a deep level. The algorithm's performance is evaluated using the DAIR-V2X dataset. The results show that compared to the Part-A2 algorithm; the proposed algorithm improves the mAP value by 7.9% in the BEV view and 7.8% in the 3D view at IOU = 0.5 (cars) and IOU = 0.25 (pedestrians and cyclists). At IOU = 0.7 (cars) and IOU = 0.5 (pedestrians and cyclists), the mAP value of the SECOND algorithm is improved by 5.4% in the BEV view and 4.3% in the 3D view, compared to other comparison algorithms. [ABSTRACT FROM AUTHOR]

In the field of autonomous driving, object detection under point clouds is indispensable for environmental perception. In order to achieve the goal of reducing blind spots in perception, many autonomous driving schemes have added low-cost blind-filling LiDAR on the side of the vehicle. Unlike point cloud target detection based on high-performance LiDAR, the blind-filling LiDARs have low vertical angular resolution and are mounted on the side of the vehicle, resulting in easily mixed point clouds of pedestrian targets in close proximity to each other. These characteristics are harmful for target detection. Currently, many research works focus on target detection under high-density LiDAR. These methods cannot effectively deal with the high sparsity of the point clouds, and the recall and detection accuracy of crowded pedestrian targets tend to be low. To overcome these problems, we propose a real-time detection model for crowded pedestrian targets, namely RTCP. To improve computational efficiency, we utilize an attention-based point sampling method to reduce the redundancy of the point clouds, then we obtain new feature tensors by the quantization of the point cloud space and neighborhood fusion in polar coordinates. In order to make it easier for the model to focus on the center position of the target, we propose an object alignment attention module (OAA) for position alignment, and we utilize an additional branch of the targets' location occupied heatmap to guide the training of the OAA module. These methods improve the model's robustness against the occlusion of crowded pedestrian targets. Finally, we evaluate the detector on KITTI, JRDB, and our own blind-filling LiDAR dataset, and our algorithm achieved the best trade-off of detection accuracy against runtime efficiency. [ABSTRACT FROM AUTHOR]

The comprehension of the fire evacuation process is crucial for developing effective evacuation management strategies to enhance pedestrian safety. In this study, we construct a classroom with internal obstacles forming intersecting pathways in Minecraft, and conduct a series of virtual evacuation experiments involving multiple pedestrians to investigate the pedestrian behaviors. Case studies in a single-exit classroom demonstrated that normal obstacles and fire in the main evacuation path prompt pedestrians to detour, and pedestrians exhibit fire-avoidance behavior in advance during fire emergency. In the two-exit classroom experiments, normal obstacles have a limited effect on the exit choices of pedestrians, as they primarily choose the nearest exit. Pedestrians positioned in the center of classroom are influenced by their initial orientations, and some pedestrians opt for exits in their initial facing directions. The presence of fire has a greater influence on pedestrians' exit choices, with most opting for exits away from the fire. Furthermore, during fire emergencies, some pedestrians engage in risk-taking behavior by choosing higher-risk paths in pursuit of a faster evacuation. These adventurous pedestrians proactively plan routes that maximize their distance from the fire and exhibit orderly queuing behavior. These findings are helpful to reveal pedestrian behaviors during fire emergencies. [ABSTRACT FROM AUTHOR]

This article presents a comprehensive review of the existing literature on the topic of data assimilation for agent-based models, with a specific emphasis on pedestrians and passengers within the context of transportation systems. This work highlights a plethora of advanced techniques that may have not been previously employed for online pedestrian simulation, and may therefore offer significant value to readers in this domain. Notably, these methods often necessitate a sophisticated understanding of mathematical principles such as linear algebra, probability theory, singular value decomposition, optimization, machine learning, and compressed sensing. Despite this complexity, this article strives to provide a nuanced explanation of these mathematical underpinnings. It is important to acknowledge that the subject matter under study is still in its nascent stages, and as such, it is highly probable that new techniques will emerge in the coming years. One potential avenue for future exploration involves the integration of machine learning with Agent-based Data Assimilation (ABDA, i.e., data assimilation methods used for agent-based models) methods. [ABSTRACT FROM AUTHOR]

Multi-object pedestrian tracking plays a crucial role in autonomous driving systems, enabling accurate perception of the surrounding environment. In this paper, we propose a comprehensive approach for pedestrian tracking, combining the improved YOLOv8 object detection algorithm with the OC-SORT tracking algorithm. First, we train the improved YOLOv8 model on the Crowdhuman dataset for accurate pedestrian detection. The integration of advanced techniques such as softNMS, GhostConv, and C3Ghost Modules results in a remarkable precision increase of 3.38% and an mAP@0.5:0.95 increase of 3.07%. Furthermore, we achieve a significant reduction of 39.98% in parameters, leading to a 37.1% reduction in model size. These improvements contribute to more efficient and lightweight pedestrian detection. Next, we apply our enhanced YOLOv8 model for pedestrian tracking on the MOT17 and MOT20 datasets. On the MOT17 dataset, we achieve outstanding results with the highest HOTA score reaching 49.92% and the highest MOTA score reaching 56.55%. Similarly, on the MOT20 dataset, our approach demonstrates exceptional performance, achieving a peak HOTA score of 48.326% and a peak MOTA score of 61.077%. These results validate the effectiveness of our approach in challenging real-world tracking scenarios. [ABSTRACT FROM AUTHOR]

The present study investigated the cooling effect of extensive green roofs and green façades, at the pedestrian level, of a Mediterranean densely populated neighborhood. The ENVI-met environmental model was employed to simulate the microclimatic environment on a typical summer day. Thermal conditions of the study area were evaluated based on air temperature and the Mediterranean thermal stress scale of UTCI (Universal Thermal Climate Index). Three mitigation strategies were developed to ameliorate the thermal conditions in the examined area focusing on the efficacy of green façades, green roofs, and the synergetic effect of the green façade and green roof. The mitigation strategies' performance was evaluated in characteristic design layouts of the study area, namely the following: a typical Mediterranean square, a church with a churchyard, an avenue, NS and EW street orientations, and courtyards. Results showed that compared to the existing configuration, the synergetic effect of the green façade and green roof achieved the greatest amelioration of the thermal conditions during the hottest hours of the day (12:00–18:00) since it produced an average Tair reduction of up to 0.7 °C and a UTCI reduction of 1.6 °C (both in the courtyards design layout). Among the examined design layouts, the courtyards produced the greatest reductions in air temperature and UTCI, whereas the EW streets were the lowest. [ABSTRACT FROM AUTHOR]

Intelligent video surveillance plays a pivotal role in enhancing the infrastructure of smart urban environments. The seamless integration of multi-angled cameras, functioning as perceptive sensors, significantly enhances pedestrian detection and augments security measures in smart cities. Nevertheless, current pedestrian-focused target detection encounters challenges such as slow detection speeds and increased costs. To address these challenges, we introduce the YOLOv5-MS model, an YOLOv5-based solution for target detection. Initially, we optimize the multi-threaded acquisition of video streams within YOLOv5 to ensure image stability and real-time performance. Subsequently, leveraging reparameterization, we replace the original BackBone convolution with RepvggBlock, streamlining the model by reducing convolutional layer channels, thereby enhancing the inference speed. Additionally, the incorporation of a bioinspired "squeeze and excitation" module in the convolutional neural network significantly enhances the detection accuracy. This module improves target focusing and diminishes the influence of irrelevant elements. Furthermore, the integration of the K-means algorithm and bioinspired Retinex image augmentation during training effectively enhances the model's detection efficacy. Finally, loss computation adopts the Focal-EIOU approach. The empirical findings from our internally developed smart city dataset unveil YOLOv5-MS's impressive 96.5% mAP value, indicating a significant 2.0% advancement over YOLOv5s. Moreover, the average inference speed demonstrates a notable 21.3% increase. These data decisively substantiate the model's superiority, showcasing its capacity to effectively perform pedestrian detection within an Intranet of over 50 video surveillance cameras, in harmony with our stringent requisites. [ABSTRACT FROM AUTHOR]

Local feature extractions have been verified to be effective for person re-identification (re-ID) in recent literature. However, existing methods usually rely on extracting local features from single part of a pedestrian while neglecting the relationship of local features among different pedestrian images. As a result, local features contain limited information from one pedestrian image, and cannot benefit from other pedestrian images. In this paper, we propose a novel approach named Local Relation-Aware Graph Convolutional Network (LRGCN) to learn the relationship of local features among different pedestrian images. In order to completely describe the relationship of local features among different pedestrian images, we propose overlap graph and similarity graph. The overlap graph formulates the edge weight as the overlap node number in the node's neighborhoods so as to learn robust local features, and the similarity graph defines the edge weight as the similarity between the nodes to learn discriminative local features. To propagate the information for different kinds of nodes effectively, we propose the Structural Graph Convolution (SGConv) operation. Different from traditional graph convolution operations where all nodes share the same parameter matrix, SGConv learns different parameter matrices for the node itself and its neighbor nodes to improve the expressive power. We conduct comprehensive experiments to verify our method on four large-scale person re-ID databases, and the overall results show LRGCN exceeds the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Identifying early special traffic events is crucial for efficient traffic control management. If there are a sufficient number of vehicles equipped with automatic event detection and report gadgets, this enables a more rapid response to special events, including road debris, unexpected pedestrians, accidents, and malfunctioning vehicles. To address the needs of such a system and service, we propose a framework for an in-vehicle module-based special traffic event and emergency detection and safe driving monitoring service, which utilizes the modified ResNet classification algorithm to improve the efficiency of traffic management on highways. Due to the fact that this type of classification problem has scarcely been proposed, we have adapted various classification algorithms and corresponding datasets specifically designed for detecting special traffic events. By utilizing datasets containing data on road debris and malfunctioning or crashed vehicles obtained from Korean highways, we demonstrate the feasibility of our algorithms. Our main contributions encompass a thorough adaptation of various deep-learning algorithms and class definitions aimed at detecting actual emergencies on highways. We have also developed a dataset and detection algorithm specifically tailored for this task. Furthermore, our final end-to-end algorithm showcases a notable 9.2% improvement in performance compared to the object accident detection-based algorithm. [ABSTRACT FROM AUTHOR]

The electromagnetic wave transmitted by the millimeter-wave radar can penetrate flames, smoke, and the high-temperature field, and is the main sensor for detecting disaster victims in closed spaces. However, a moving target in the closed space will produce a considerable number of false detections in the point cloud data collected by the radar due to multipath scattering. The false detections lead to false trajectories generated by multi-target tracking filters, such as the labeled multi-Bernoulli (LMB) filter, which, therefore, leads to inaccurate estimation of the number of pedestrians. Addressing this problem, in this paper, a three-class combination of the clutter point clouds model is proposed: static clutter, non-continuous dynamic clutter (NCDC), and continuous dynamic clutter (CDC). The model is based on the spatial and temporal distribution characteristics of the CDC sequence captured by a two-dimensional (2D) millimeter-wave (MMW) radar. However, in open space, CDC appears infrequently in radar tracking applications, and thus has not been considered in multi-target tracking filters such as the LMB filter. This leads to confusion between the CDC point cloud collected by the high-resolution radar in closed spaces and the real-target point cloud. To solve this problem, the impact mechanism of the LMB filter on prediction, update, and state estimation is modeled in this paper in different stages based on the temporal and spatial distribution characteristics of CDC. Finally, a hybrid clutter model-based LMB filter (HCM-LMB) is proposed, which focuses on scenes where NCDC and CDC are mixed. The filter introduces the temporal and spatial distribution characteristics of NCDC based on the original LMB filter, and improves the prediction, update, and state estimation of the original filter by combining the impact mechanism model and the new CDC prediction, CDC estimation, and false trajectory label management algorithm. Experiments were conducted on pedestrians in building corridors using 2D MMW radar perception. The experimental results show that under the influence of CDC, the total number of pedestrians estimated by the HCM-LMB filter was reduced by 22.5% compared with that estimated by the LMB filter. [ABSTRACT FROM AUTHOR]

In the context of predicting pedestrian trajectories for indoor mobile robots, it is crucial to accurately measure the distance between indoor pedestrians and robots. This study aims to address this requirement by extracting pedestrians as regions of interest and mitigating issues related to inaccurate depth camera distance measurements and illumination conditions. To tackle these challenges, we focus on an improved version of the H-GrabCut image segmentation algorithm, which involves four steps for segmenting indoor pedestrians. Firstly, we leverage the YOLO-V5 object recognition algorithm to construct detection nodes. Next, we propose an enhanced BIL-MSRCR algorithm to enhance the edge details of pedestrians. Finally, we optimize the clustering features of the GrabCut algorithm by incorporating two-dimensional entropy, UV component distance, and LBP texture feature values. The experimental results demonstrate that our algorithm achieves a segmentation accuracy of 97.13% in both the INRIA dataset and real-world tests, outperforming alternative methods in terms of sensitivity, missegmentation rate, and intersection-over-union metrics. These experiments confirm the feasibility and practicality of our approach. The aforementioned findings will be utilized in the preliminary processing of indoor mobile robot pedestrian trajectory prediction and enable path planning based on the predicted results. [ABSTRACT FROM AUTHOR]

Indoor positioning using smartphones has garnered significant research attention. Geomagnetic and sensor data offer convenient methods for achieving this goal. However, conventional geomagnetic indoor positioning encounters several limitations, including low spatial resolution, poor accuracy, and stability issues. To address these challenges, we propose a fusion positioning approach. This approach integrates geomagnetic data, light intensity measurements, and inertial navigation data, utilizing a hierarchical optimization strategy. We employ a Tent-ASO-BP model that enhances the traditional Back Propagation (BP) algorithm through the integration of chaos mapping and Atom Search Optimization (ASO). In the offline phase, we construct a dual-resolution fingerprint database using Radial Basis Function (RBF) interpolation. This database amalgamates geomagnetic and light intensity data. The fused positioning results are obtained via the first layer of the Tent-ASO-BP model. We add a second Tent-ASO-BP layer and use an improved Pedestrian Dead Reckoning (PDR) method to derive the walking trajectory from smartphone sensors. In PDR, we apply the Biased Kalman Filter–Wavelet Transform (BKF-WT) for optimal heading estimation and set a time threshold to mitigate the effects of false peaks and valleys. The second-layer model combines geomagnetic and light intensity fusion coordinates with PDR coordinates. The experimental results demonstrate that our proposed positioning method not only effectively reduces positioning errors but also improves robustness across different application scenarios. [ABSTRACT FROM AUTHOR]

Due to the characteristics of multibody (MB) and finite element (FE) digital human body models (HBMs), the reconstruction of running pedestrians (RPs) remains a major challenge in traffic accidents (TAs) and new innovative methods are needed. This study presents a novel approach for reconstructing moving pedestrian TAs based on a humanoid robot method to improve the accuracy of analyzing dynamic vehicle–pedestrian collision accidents. Firstly, we applied the theory of humanoid robots to the corresponding joints and centroids of the TNO HBM and implemented the pedestrian running process. Secondly, we used rigid–flexible coupling HBMs to build pedestrians, which can not only simulate running but also analyze human injuries. Then, we validated the feasibility of the RP reconstruction method by comparing the simulated dynamics with the pedestrian in the accident. Next, we extracted the velocity and posture of the pedestrian at the moment of collision and further validated the modeling method through a comparison of human injuries and forensic autopsy results. Finally, by comparing two other cases, we can conclude that there are relative errors in both the pedestrian injury results and the rest position. This comparative analysis is helpful for understanding the differences in injury characteristics between the running pedestrian and the other two cases in TAs. [ABSTRACT FROM AUTHOR]

Trajectory prediction aims to predict the movement intention of traffic participants in the future based on the historical observation trajectories. For traffic scenarios, pedestrians, vehicles and other traffic participants have social interaction of surrounding traffic participants in both time and spatial dimensions. Most previous studies only use pooling methods to simulate the interaction process between participants and cannot fully capture the spatio-temporal dependence, possibly accumulating errors with the increase in prediction time. To overcome these problems, we propose the Spatial–Temporal Interaction Attention-based Trajectory Prediction Network (STIA-TPNet), which can effectively model the spatial–temporal interaction information. Based on trajectory feature extraction, the novel Spatial–Temporal Interaction Attention Module (STIA Module) is proposed to extract the interaction relationships between traffic participants, including temporal interaction attention, spatial interaction attention, and spatio-temporal attention fusion. By adaptive allocation of attention weights, temporal interaction attention is a temporal attention mechanism used to capture the movement pattern of each traffic participant in the scene, which can learn the importance of historical trajectories at different moments to future behaviors. Since the participants number in recent traffic scenes dynamically changes, the spatial interaction attention is designed to abstract the traffic participants in the scene into graph nodes, and abstract the social interaction between participants into graph edges. Coupling the temporal and spatial interaction attentions can adaptively model the temporal–spatial information and achieve accurate trajectory prediction. By performing experiments on the INTERACTION dataset and the UTP (Unmanned Aerial Vehicle-based Trajectory Prediction) dataset, the experimental results show that the proposed method significantly improves the accuracy of trajectory prediction and outperforms the representative methods in comparison. [ABSTRACT FROM AUTHOR]

A macro network loading model for multi-flow lines, time varying, and pedestrian congestion is proposed. The station hub is abstracted as a network of different types of nodes, and the flow of passengers at each node is calculated in real time for the purpose of simulating the hub's collection and distribution process. For correct transmission of passenger flow on heterogeneous networks, three types of indexes are proposed to distinguish the nodes, and the corresponding fundamental diagrams are then matched. This paper divides the update process of the dynamic network loading model into multiple processes by flow lines, and improves the computational speed of the DNL model. The proposed model is applied to the simulation of passenger flow collection and distribution in an actual hub station with multi-flow lines. The analysis results illustrate that the model can accurately reflect the realistic congestion facilities and explain the formation process of high-density areas. A rolling passenger flow control model based on optimal control theory is proposed. The effectiveness of the control model is verified based on simulation data. [ABSTRACT FROM AUTHOR]

In recent years, the application of artificial intelligence (AI) in the automotive industry has led to the development of intelligent systems focused on road safety, aiming to improve protection for drivers and pedestrians worldwide to reduce the number of accidents yearly. One of the most critical functions of these systems is pedestrian detection, as it is crucial for the safety of everyone involved in road traffic. However, pedestrian detection goes beyond the front of the vehicle; it is also essential to consider the vehicle's rear since pedestrian collisions occur when the car is in reverse drive. To contribute to the solution of this problem, this research proposes a model based on convolutional neural networks (CNN) using a proposed one-dimensional architecture and the Inception V3 architecture to fuse the information from the backup camera and the distance measured by the ultrasonic sensors, to detect pedestrians when the vehicle is reversing. In addition, specific data collection was performed to build a database for the research. The proposed model showed outstanding results with 99.85% accuracy and 99.86% correct classification performance, demonstrating that it is possible to achieve the goal of pedestrian detection using CNN by fusing two types of data. [ABSTRACT FROM AUTHOR]