In smart cities, crowding in transportation hubs, large event venues, and commercial/tourist districts can rapidly escalate from service congestion to public-safety incidents. Real-world operations are constrained by heterogeneous sensing coverage, delayed statistics, privacy requirements, and the need for accountable multi-agency decisions. Following a rigorous PRISMA protocol, we synthesized 107 primary empirical studies (2020–2026) to systematically review context-aware crowd technologies. Moving beyond isolated algorithmic benchmarks, we organized these advances into a mathematically formalized closed-loop framework (Sensing–Prediction–Intervention–Feedback). Crowd sensing has evolved toward edge-based computer vision, passive mobile signaling, and multimodal fusion to balance operational trade-offs among density applicability, environmental robustness, privacy burdens, and end-to-end latency. Prediction architectures—converging on Spatiotemporal Graph Neural Networks (ST-GNNs) and simulation-augmented digital twins—are critically evaluated against constraints in predictive horizon, computational overhead, and explainability. To bridge theory and practical deployment, we deduce a multidimensional evaluation taxonomy and a hierarchical trigger-and-escalation matrix, tailoring control philosophies (e.g., spatiotemporal capacity synchronization and dynamic demand reshaping) to the three heterogeneous scenarios. Finally, we propose four strategic directions to chart a deployment-oriented roadmap for the integrated Urban Brain: edge-based privacy-preserving fusion, cross-scenario generalization, accountable Explainable Artificial Intelligence (XAI) with human-in-the-loop synergy, and end-to-end outcome-oriented empirical validation.

According to historical crowd accidents data, pedestrian panic behaviors have often triggered and further exacerbated crowd incidents, leading to severe casualties in transit hubs. To date, most existing panic behavior recognition models still fail to detect crowd panic quickly enough to guide timely pedestrian-control measures. To address this gap, we propose the pedestrian Panic Behavior Recognition Model (PBRM), which integrates audio-semantic signals, speech-derived panic keywords, 21-keypoint kinematic patterns associated with running and falls, and multi-inflection pedestrian trajectories. These heterogeneous cues are consolidated through a lightweight fusion mechanism—efficient enough for real-time execution on edge devices—to generate a unified panic score, thereby providing operators with a rapid and reliable basis for crowd-control decisions. Evaluated on the four-hour Hongqiao-Panic dataset collected at Hongqiao Railway Station, PBRM achieves 84.2% precision, 85.7% recall, 84.9% F1, and 1.18 s average alert lead, improving the best single-modality baseline by 3.0 pp F1 while keeping the false-alarm rate (FAR) below 8%. Ablation study shows that audio-semantic channels dominate early cues, where as posture-trajectory streams reinforce decision robustness under occlusion. These results demonstrate that PBRM can be deployed on edge devices to provide operators with a critical lead time for crowd-control interventions, advancing intelligent transportation safety from post-event surveillance to proactive prevention.

Predicting human future motion holds significant importance in the domains of autonomous driving and public safety. Kinematic features, including joint coordinates and velocity, are commonly employed in skeleton-based human motion prediction. Nevertheless, most existing approaches neglect the critical role of dynamic information and tend to degrade as the prediction length increases. To address the related constraints due to single-scale and fixed-joint topological relationships, this study proposes a novel method that incorporates joint torques estimated via Lagrangian equations as dynamic features of the human body. Specifically, the human skeleton is modeled as a multi-rigid body system, with generalized joint torques calculated based on the Lagrangian formula. Furthermore, to extract both kinematic and dynamic joint information effectively for predicting long-term human motion, we propose a Multiscale Mixed-Graph Neural Network (MS-MGNN). MS-MGNN can extract kinematic and dynamic joint features across three distinct scales: joints, limbs, and body parts. The extraction of joint features at each scale is facilitated by a single-scale mixed-graph convolution module. And to effectively integrate the extracted kinematic and dynamic features, a KD-fused Graph-GRU (Kinematic and Dynamics Fused Graph Gate Recurrent Unit) predictor is designed to fuse them. Finally, the proposed method exhibits superior motion prediction capabilities across multiple motions. In motion prediction experiments on the Human3.6 dataset, it outperforms existing approaches by decreasing the average prediction error by 9.1%, 12.2%, and 10.9% at 160 ms, 320 ms, and 400 ms for short-term prediction and 7.1% at 560 ms for long-term prediction.

In public transportation hubs, the combined motion (CM) between a passenger and his luggage is a primary movement form. The state of CM always influences the stability of the movement of passenger crowds. While there is still a lack of systematic studies on the passenger-luggage combined motion, even most state-of-the-art literatures focus only on the impact of luggage on the overall efficiency of crowd evacuation. To fill this academic lag, this study investigated the motion relationship between passengers and luggage and then proposed a passenger-luggage combined motion model (PLCMM), which helps determine the relevance between passengers and luggage. Furthermore, a novel energy-based criterion for the stability of PLCMM and an abnormal state recognition model were established. Finally, the proposed model and criteria were validated in the waiting hall of Shanghai Hongqiao High-speed Railway Station, as a typical large public transportation scenario. The luggage abnormality recognition model can identify three abnormal states, i.e., luggage falling off, tail dumping, and sudden acceleration. A performance comparison between the proposed PLCMM and five other representative models was conducted from the aspects of scenarios, algorithm complexity, and research focus. The detection accuracy of the PLCCM was 96.154% and the algorithm complexity was considerably lower than the complexity exhibited by the purely computer vision-based approaches. The results demonstrated that PLCMM aligned closely with the ground truth, and outperformed other state-of-the-art models. The stability criterion can be employed to assess the impact of lateral perturbation forces on the stability of the passenger-luggage combined motion, to support the daily passenger flow control and management in more public traffic areas.

Panic behaviors in a pedestrian flow often lead to a state of chaos or disorder among the pedestrian crowd, resulting in a crowd accident with high possibility. To investigate the panic pedestrian dynamics and further prevent serious crowd accidents, simulation based on dynamics modeling and accident video data is a popular solution to date. Thereby, it is challenging but significant to improve the crowd dynamics model more consistent with the ground truth of real pedestrian movement scenarios, with consideration of both physical contact force and panic emotional propagation in a crowd. Therefore, this study proposed an extended social force model (ESFM) by applying the physical contact-force estimation during pedestrian collision based on non-smooth contact dynamics. Subsequently, the ESFM was integrated with an improved panic propagation model (IPPM) considering obstacle and promotion factors. Finally, taking the crowd panic accident happened in Nepal in 2015 as an experiment case, the simulation of panic crowd dynamics was conducted within Anylogic software. Four cases of SFM, ESFM, SFM $+$ IPPM, and ESFM $+$ IPPM were compared quantitatively and graphically. The experimental results showed that the pedestrian distribution obtained from the proposed ESFM $+$ IPPM was the closest to the ground truth during the panic response period, with 28.8% lower of Hausdorff distance than the original SFM, and 21.6% lower the well-known BHSFM, respectively. This approach can help improve the panic crowd modeling and pedestrian distribution prediction in real scenarios.

Pedestrian panic behavior is a primary cause of overcrowding and stampede accidents in public micro-road network areas with high pedestrian density. However, reliably detecting such behaviors remains challenging due to their inherent complexity, variability, and stochastic nature. Current detection models often rely on single-modality features, which limits their effectiveness in complex and dynamic crowd scenarios. To overcome these limitations, this study proposes a contour-driven multimodal framework that first employs a CNN (CDNet) to estimate density maps and, by analyzing steep contour gradients, automatically delineates a candidate panic zone. Within these potential panic zones, pedestrian trajectories are analyzed through LSTM networks to capture irregular movements, such as counterflow and nonlinear wandering behaviors. Concurrently, semantic recognition based on Transformer models is utilized to identify verbal distress cues extracted through Baidu AI’s real-time speech-to-text conversion. The three embeddings are fused through a lightweight attention-enhanced MLP, enabling end-to-end inference at 40 FPS on a single GPU. To evaluate branch robustness under streaming conditions, the UCF Crowd dataset (150 videos without panic labels) is processed frame-by-frame at 25 FPS solely for density assessment, whereas full panic detection is validated on 30 real Itaewon-Stampede videos and 160 SUMO/Unity simulated emergencies that include explicit panic annotations. The proposed system achieves 91.7% accuracy and 88.2% F1 on the Itaewon set, outperforming all single- or dual-modality baselines and offering a deployable solution for proactive crowd safety monitoring in transport hubs, festivals, and other high-risk venues.

This article reviewed state-of-the-art achievements in pedestrian contacting force measurement as a hotspot survey closer to ground truth supporting pedestrian dynamics in mass-gathering environments. It analyzed different forces acting on pedestrian bodies, including normal external forces, self-driven forces, abnormal external forces, and pedestrian motion constraint forces from other obstacles, besides the crowding posture on the force distribution. This review covered main methodologies: sophisticated pressure sensors, modern technology for pedestrian motion-capturing systems, and advanced numerical simulations. Further, this paper summarized key findings from recent studies related to pedestrian contacting or crowding forces. It was found that despite significant advances, study achievements are mainly limited to different crowding postures, such as experiments regarding controlled environments in flat areas, indoor corridors, staircases, and competitive evacuation drills. Lack of sufficient sensor-based body measurements and contact force measurements on slop roads was analyzed. Finally, future research outlook was outlined, including planned experiments in highly crowded environments.

In current transportation hubs, passengers travelling with wheeled luggage or suitcases is a common phenomenon. Due to the fact that most luggage occupies a certain space in dense passenger crowds with high mass inertia, its abnormal motion, such as drifting, can frequently trigger unavoidable local disturbances and turbulence in the surrounding pedestrian flows, further increasing congestion risk. Meanwhile, there still is a lack of quantitative disturbance propagation analysis, since most state-of-the-art achievements rely on either scenario-based experiments or the spatial characteristics of crowd distribution assessed qualitatively. Therefore, this study considers the luggage-laden passenger as a deformable particle. The resulting disturbance on surrounding non-luggage-carrying passengers is analyzed and quantified into a nonlinear pressure term. Subsequently, the disturbance propagation model of passenger-owned luggage is developed by adapting the classical Aw–Rascle traffic flow model with a pressure term. Simulation experiments of disturbances caused by luggage drifting and retrograding were conducted in Pathfinder 2022 Software. Experimental results showed that the disturbing force of a left-sided crowd can reach a peak of 238 N with a passenger density of 3.0 p/m2, and the maximum force difference between the left- and right-sided disturbing force can reach 153 N, as confirmed by a case study in an L-shaped corridor of a transportation hub. Furthermore, it is recommended that the proposed model can be applied in crowd flow analysis and intelligent decision-making for passenger management in transportation hubs.

Crowd accident surveys have shown that regardless of the initial triggering factors, pedestrian fall behavior is the most critical factor causing and aggravating crowd accidents in public traffic areas (PTAs). The application of pedestrian fall behavior detection methods in PTAs is significant. Once deployed, they would prevent many pedestrians from losing life in crowded traffic area accidents. However, most existing methods are still focused on medical assistance for the elderly. Therefore, this paper conducted bibliometric and content analyses, combining fall detection-related keywords from internationally recognized literature databases and benchmark pedestrian behavior datasets. Based on the analysis of the state-of-the-art (SOTA) achievements in fall detection methods, the fall detection methods were classified into different categories according to the research approach. This study undertakes a comprehensive analysis of five predominant methods, namely, computer vision, Internet of Things, smartphone, kinematic, and wearable device-based methods. Furthermore, the benchmark datasets, including fall scenarios, were introduced and compared. Finally, this study provides a detailed discussion of existing fall detection methods, and possible future directions are identified considering the application requirements in PTAs. This overview may help researchers understand the SOTA fall detection methods and devise new methodologies by improving and synthesizing the highlighted issues in PTAs.

Abnormal crowd behavior recognition is one of the research hotspots in computer vision. Its goal is to use computer vision technology and abnormal behavior detection models to accurately perceive, predict, and intervene in potential abnormal behaviors of the crowd and monitor the status of the crowd system in public places in real time, to effectively prevent and deal with public security risks and ensure public life safety and social order. To this end, focusing on the abnormal crowd behavior recognition technology in the computer vision system, a systematic review study of its theory and cutting-edge technology is conducted. First, the crowd level and abnormal behaviors in public places are defined, and the challenges faced by abnormal crowd behavior recognition are expounded. Then, from the dimensions based on traditional methods and based on deep learning, the mainstream technologies of abnormal behavior recognition are discussed, and the design ideas, advantages, and limitations of various methods are analyzed. Next, the mainstream software tools are introduced to provide a comprehensive reference for the technical framework. Secondly, typical abnormal behavior datasets at home and abroad are sorted out, and the characteristics of these datasets are compared in detail from multiple perspectives such as scale, characteristics, and uses, and the performance indicators of different algorithms on the datasets are compared and analyzed. Finally, the full text is summarized and the future development direction of abnormal crowd behavior recognition technology is prospected.

In order to achieve a balance between power efficiency and spectrum utilization, Hybrid Asymmetrically clipped optical OFDM (HACO-OFDM) uses odd carriers for asymmetrically clipped optical OFDM (ACO-OFDM) modulation and even carriers for Pulse Amplitude Modulation-Discrete Multitone (PAM-DMT) modulation. However, ACO-OFDM and PAM-DMT interfere with each other in the time domain, which has a great impact on system performance. To address this problem, this paper proposes a Pre-distortion HACO-OFD modulation method, which eliminates the interference caused by ACO-OFDM to PAM-DMT from the perspective of the transmitter frequency domain. The simulation results show that under the same conditions, compared with existing methods, the signal-to-noise ratio of the proposed method is improved by 4 dB, and it has better fairness.

A fall is an abnormal behavior that rarely occurs, however, once it occurs in a crowded scenario, it is prone to cause local disturbance, density-velocity fluctuations, and crowd instability even leading to a stampede accident. Currently, research on fall behavior mainly depends on single-point detection approach but lacks investigation on disturbing mechanism in a crowd flow. To address this issue, this paper first proposed a pressure dynamics model based on limb-level contact to analyze pedestrian behavioral characteristics. Then, based on the random Brownian motion, the disturbance distribution of fall behavior was determined theoretically. Using two parameters (a pressure coefficient and disturbance intensity), the pressure term of the fluid dynamics Aw-Rascle model was improved, and the internal disturbance propagation model (DPM) of fall behavior was established, as a primary contribution of this study. Further, to eliminate the disturbance propagation in a crowd, damping motion theory was employed. The disturbance elimination mechanism of abnormal behavior was discussed to suppress disturbance propagation caused by a pedestrian fall behavior. To validate the proposed model, both field experiment and numerical simulation were conducted respectively. The stability performance of the proposed DPM was evaluated with standard deviation (less than 0.1631) based on 50 repetitive experiments. Results showed that this study could help discover the disturbance propagation dynamics and elimination mechanisms of pedestrian fall behavior in a crowded scenario.

Accurate identification of panic among individuals is a challenging but valuable application in the rapidly growing field of emotion recognition, particularly in the public security and healthcare industries. To recognize the panic emotion in a pedestrian crowd, this study introduces a facial expression recognition network (FER-net) as an advanced deep-learning network aimed at recognizing panic states. Then a panic recognition model based on face alignment (FA) and convolutional neural network (CNN) is proposed. This model can obtain greater accuracy in detecting minor emotions indicating panic by maintaining the ideal alignment of facial features. To validate this proposed model, experiments were designed. The experiment results showed a significant increase in panic detection rates compared with conventional models, and the possibility of the FER-net as a reliable tool for use in reality. Finally, this study emphasizes the positive effects of using face alignment with CNNs and can be taken as a new emotion detection technique that concentrate on unpleasant feelings like panic emotion.

With the increasing number of video surveillance cameras in public buildings, it has become challenging, yet significant to detect abnormal pedestrian behaviors in crowd management, to prevent crowd accidents. Although current advancements in human action recognition based on computer vision can help detect abnormal behaviors after their incidence, majority of them lack the ability to detect potential characteristics prior to the occurrence of real abnormal behaviors. Hence, in this study, we addressed this issue by proposing a novel dynamic centroid model (DCM) of a human body, and rebuilding pedestrian joint sub-segments from human skeleton key nodes obtained in camera images. We built a weighted centroid-combined force model based on Newton's second law, considering acceleration, mass inertial of human body sub-segments, and internal constraints. Thereafter, pedestrian kinematic and dynamic parameters were analyzed, such as speed, trajectory, force. Furthermore, abnormal behavior detection criteria were constructed for typical abnormal-behavior cases: U-turn and fall-down. Comparative experiments between the proposed DCM and the state-of-the-art methods were conducted. The experimental results showed that the model was capable of detecting abnormal behaviors, with mean values of lead time of 277 ms in U-turn behavior, and 562 ms in fall-down behavior, prior to the captured occurrence of these two abnormal behaviors. Finally, a de-occlusion algorithm was designed and jointly used with DCM, validated by a fall-down detecting experiment including partial occlusion. Therefore, this study holds significant value for the prevention of abnormal pedestrian behaviors in public places.

Understanding the effects of panic on crowd dynamics in emergency situations has long been considered necessary for pedestrian evacuation control. In the case of disasters, stampedes caused by panic behaviors occur with high possibility, and pedestrians are crushed or trampled, leading to enormous casualties. To eliminate the computational errors accumulated in the traditional macromodel, a macro-microconversion model based on the SF (social force) model and the AR (Aw-Rascle) model is proposed in this paper. The purpose is to use the crowd parameters of the microscopic model as the input part of the macroscopic model and to combine the advantages of the two models to ensure accuracy and improve calculation performance. The concept of the "pressure term" is defined to measure the panic level of the crowd. In addition, a flowchart of the numerical simulation is designed based on the road network conditions at the trampling site. To validate the conversion model, a numerical simulation is conducted in a case study of the Mecca Hajj stampede in 2015. The simulation results display the whole process of crowd marching and meeting with the dynamic variations of the "pressure term." The simulation results are compared with the traditional simulation results based on a Gaussian distribution, which verifies that the simulation results obtained by the proposed method are closer to the real situation. Moreover, in this study, a new micromacro transformation method for crowd evaluation dynamics, which can enhance computing speed and execution efficiency, is provided.