Crowd Behavior Analysis Research Articles

Inferring the Accurate Locations of Noise Records in Mobile Phone Location Data

ABSTRACTThe positioning uncertainty of mobile phone location (MPL) data greatly influences location services and crowd behavior analysis. Although many achievements have been made in controlling its main sources (signal drift and ping‐pong effects), several problems, such as single‐oscillation patterns, insufficient position optimization, and a lack of effective evaluation, remain. In this study, a set of MPL data quality optimization methods are proposed. First, the characteristics of drift records and the oscillation patterns of ping‐pong records are discussed. The quality of the MPL data is subsequently controlled with the proposed feature‐based drift‐record detection method, complex oscillation pattern‐based ping‐pong‐record detection method, and cumulative duration weighting‐based ping‐pong‐record optimization method. These methods are applied to the MPL dataset of a major operator in Nanjing city, and the optimization effect is evaluated with GPS data collected synchronously. The results show that the proposed detection and optimization methods can effectively improve the accuracy of MPL data.

SPCANet: congested crowd counting via strip pooling combined attention network.

Crowd counting aims to estimate the number and distribution of the population in crowded places, which is an important research direction in object counting. It is widely used in public place management, crowd behavior analysis, and other scenarios, showing its robust practicality. In recent years, crowd-counting technology has been developing rapidly. However, in highly crowded and noisy scenes, the counting effect of most models is still seriously affected by the distortion of view angle, dense occlusion, and inconsistent crowd distribution. Perspective distortion causes crowds to appear in different sizes and shapes in the image, and dense occlusion and inconsistent crowd distributions result in parts of the crowd not being captured completely. This ultimately results in the imperfect capture of spatial information in the model. To solve such problems, we propose a strip pooling combined attention (SPCANet) network model based on normed-deformable convolution (NDConv). We model long-distance dependencies more efficiently by introducing strip pooling. In contrast to traditional square kernel pooling, strip pooling uses long and narrow kernels (1×N or N×1) to deal with dense crowds, mutual occlusion, and overlap. Efficient channel attention (ECA), a mechanism for learning channel attention using a local cross-channel interaction strategy, is also introduced in SPCANet. This module generates channel attention through a fast 1D convolution to reduce model complexity while improving performance as much as possible. Four mainstream datasets, Shanghai Tech Part A, Shanghai Tech Part B, UCF-QNRF, and UCF CC 50, were utilized in extensive experiments, and mean absolute error (MAE) exceeds the baseline, which is 60.9, 7.3, 90.8, and 161.1, validating the effectiveness of SPCANet. Meanwhile, mean squared error (MSE) decreases by 5.7% on average over the four datasets, and the robustness is greatly improved.

Human crowd behaviour analysis based on video segmentation and classification using expectation–maximization with deep learning architectures

Human crowd behaviour analysis based on video segmentation and classification using expectation–maximization with deep learning architectures

A Survey on Age and Gender Detection Using Deep Learning

Abstract: The age and gender information are very important for various real world applications such as social understanding, biometrics, identity verification, crowd behavior analysis etc. There are numerous works proposed for age and gender prediction in the past several years. The age and gender detector project aims to develop an advanced AI system capable of accurately determining the age and genders of individuals from images. As we can see, the model outputs are mostly special parts as well as wrinkles, which are important for age and gender prediction. This project utilizes deep learning techniques to analyze special features and patterns, enabling real time identification and classification of age and gender attributes.

Enhancing Urban Spaces through Crowd Behavior Analysis A Case Study of Arafat to Muzdalifah Road During Hajj Time

Enhancing Urban Spaces through Crowd Behavior Analysis A Case Study of Arafat to Muzdalifah Road During Hajj Time

An integrated multi-level feature fusion framework for crowd behaviour prediction and analysis

<p>The uncontrolled outburst in population has led to crowd gatherings in various public places causing panic and disaster in certain unpleasant and extreme conditions. A study on the analysis of crowd accumulation has been carried out for various reasons that include management of crowd, design of a well-planned public space, the possibility for surveillance at every area and transportation systems. A lot of disasters also occurs due to uncontrollable crowd behaviour and poor crowd management. It could result in loss of property, fatalities or casualties. To avoid this, the conduct of a crowd of people has been studied and analyzed to control their movement and traffic. Hence, in this research work, integrated multi-level feature fusion (IMFF) framework is designed to predict the behaviour; further classification based on the local region is carried out to enhance the prediction. In the case of multi-level feature fusion; first level feature fusion utilizes the motion and appearance; second-level feature fusion utilizes the spatial connection and third-level utilizes the temporal connections. Further, the classification approach is integrated based on the local region is used to enhance the crowd behaviour prediction in terms of accuracy and faster. Moreover, performance evaluation is carried out considering the two distinctive datasets.</p>

Machine Learning-Based Crowd behavior Analysis and Forecasting

In many places today, the world's overcrowding causes crowded conditions. Analysis of crowd activity is a developing field of study. It is common knowledge that mob activity can forecast what might happen during an event. Crowd management could be very effective if situations like riots, mass lynchings, traffic jams, accidents, stampedes, etc. could be predicted beforehand. In this paper, we propose a new multicolumn convolutional neural network (MCNN) based technique for predicting mob behavior. The features of the incoming image are first analyzed and extracted. The approximated number of the gathering is then established, and image cropping is completed. For each area of the image, low level characteristics are retrieved. The objects in the picture are then created as density images. Using our method, the gathered characteristics and their object density maps are then linearly mapped. At last, we forecast and quantify the population using the MCNN algorithm. For the ShanghaiTech dataset, we have evaluated our method using actual data.

Scale-aware CNN for crowd density estimation and crowd behavior analysis

Visual surveillance is a highly demanded system in various real-time applications for civil and military sectors. For huge gatherings such as rallies and stadiums, crowd monitoring becomes a tedious task. Moreover, crowd density estimation also plays an important role to improve the performance of crowd monitoring system. Several techniques have been presented for crowd counting or density estimation and crowd behavior analysis. The crowd scenes contain noise, occlusion, cluttered environment which creates complexity to analyze the crowd behavior. To overcome the challenges of crowd monitoring, we present a combined solution to perform the crowd density estimation and crowd behavior analysis. The crowd density estimation is carried out by developing a new CNN based architecture which considers scale information and overcome the issues of scale variations. In order to deal with this issue of scale variation, we introduce a scale-aware attention module where multiple branches of self-attention module are concatenated to improve the scale variation realization. Further, we present the crowd behavior analysis model which uses motion map and energy level distribution based features to detect the abnormal crowd behavior. The Proposed approach achieves average accuracy of abnormal event detection as 98.95, and crowd counting accuracy as 97.60. Furthermore, the average MAE and MSE is achieved as 58.60, 98.55 for ShanghaiTech Part A dataset and 7.55, 8.50 for Part B dataset, respectively. Similarly, the MAE and MSE for UCF 50 dataset is obtained as 210.20, and 260.80, respectively which shows a significant improvement over other techniques discussed in the experimental study.

Review of Virtual Simulation of Crowd Motion for Urban Emergency Management

With increasing urbanization in China, there are more and more urban crowds, bringing new challenges to public safety management. The analysis and modeling of crowd behavior are important aspects of emergency management in smart cities. This paper reviews and summarizes existing research into crowd behavior simulation and analyzes existing simulation data collection methods. Crowd simulation technology is discussed from three aspects: crowd modeling, motion navigation, and emotion-driven crowd animation. The indicators of the simulation models are analyzed from the perspective of model evaluation. Finally, combined with the status quo, the existing research limitations are analyzed, and the direction of further research into crowd simulation behavior is discussed.

DroneAttention: Sparse weighted temporal attention for drone-camera based activity recognition

Human activity recognition (HAR) using drone-mounted cameras has attracted considerable interest from the computer vision research community in recent years. A robust and efficient HAR system has a pivotal role in fields like video surveillance, crowd behavior analysis, sports analysis, and human–computer interaction. What makes it challenging are the complex poses, understanding different viewpoints, and the environmental scenarios where the action is taking place. To address such complexities, in this paper, we propose a novel Sparse Weighted Temporal Attention (SWTA) module to utilize sparsely sampled video frames for obtaining global weighted temporal attention. The proposed SWTA is comprised of two parts. First, temporal segment network that sparsely samples a given set of frames. Second, weighted temporal attention, which incorporates a fusion of attention maps derived from optical flow, with raw RGB images. This is followed by a basenet network, which comprises a convolutional neural network (CNN) module along with fully connected layers that provide us with activity recognition. The SWTA network can be used as a plug-in module to the existing deep CNN architectures, for optimizing them to learn temporal information by eliminating the need for a separate temporal stream. It has been evaluated on three publicly available benchmark datasets, namely Okutama, MOD20, and Drone-Action. The proposed model has received an accuracy of 72.76%, 92.56%, and 78.86% on the respective datasets thereby surpassing the previous state-of-the-art performances by a margin of 25.26%, 18.56%, and 2.94%, respectively.

A Research Perceptive on Deep Learning Framework for Pedestrian Detection in a Crowd

In populated cities, we often find crowded events like political meetings, religious festivals, music concerts, and events in shopping malls, which have more safety issues. Smart surveillance systems are used in big cities to keep crowds safe and make crowd security less complicated and more accurate. However, the surveillance systems proposed for a crowd are monitored by human agents, which are inefficient, error-prone, and overwhelming. Even with deep learning-based feature engineering in crowds, many variants of crowd analysis still lack attention and are technically unaddressed. Considering this scenario, the smart system requires the most advanced techniques to monitor the security of the crowd. Crowd analysis is commonly divided into crowd statics and behavior analysis. This paper explores more about crowd behaviour analysis, pedestrian and group detection which describes the movements that are noticed in the crowd image. Subsequently, the issues of the current methodology of pedestrian detection, datasets, and evaluation criteria are analyzed. Keyword : Crowd Analysis, Pedestrian and group detection, deep learning, Crowd IoT analysis, Human Activity Recognition.

A new approach for social group detection based on spatio-temporal interpersonal distance measurement

Visual-based social group detection aims to cluster pedestrians in crowd scenes according to social interactions and spatio-temporal position relations by using surveillance video data. It is a basic technique for crowd behaviour analysis and group-based activity understanding. According to the theory of proxemics study, the interpersonal relationship between individuals determines the scope of their self-space, while the spatial distance can reflect the closeness degree of their interpersonal relationship. In this paper, we proposed a new unsupervised approach to address the issues of interaction recognition and social group detection in public spaces, which remits the need to intensely label time-consuming training data. First, based on pedestrians' spatio-temporal trajectories, the interpersonal distances among individuals were measured from static and dynamic perspectives. Combined with proxemics' theory, a social interaction recognition scheme was designed to judge whether there is a social interaction between pedestrians. On this basis, the pedestrians are clustered to identify if they form a social group. Extensive experiments on our pedestrian dataset “SCU-VSD-Social” annotated with multi-group labels demonstrated that the proposed method has outstanding performance in both accuracy and complexity.

A new approach to dominant motion pattern recognition at the macroscopic crowd level

Automatic analysis and the recognition and prediction of the behaviour of large-scale crowds in video-surveillance data is a research field of paramount importance for the security of modern societies. It serves to predict and help prevent disasters in public places where crowds of people gather. The paper proposes a novel method for generating meta-tracklets and recognition of dominant motion patterns as a basis for automatic crowd behaviour analysis at the macroscopic level, where a crowd is treated as an entity. The basic characteristic of macroscopic crowd scenes is that it is impossible to detect and track individuals in the scene. The idea of the method proposed in this paper is to recognize dominant crowd motion patterns, by avoiding time-consuming and error-sensitive crowd segmentation, crowd tracking and detection of regions of interest. Thus, the process of determining dominant motion patterns and recognizing crowd behaviour is accelerated. The method is inspired by a quantum mechanical approach. It combines a set of particles, which are considered as particles in quantum mechanics, tracklets of particles’ advection in a video clip, and the interaction of wave functions spread out from particle positions. A wave function is expressed in the form of an asymmetric potential function. Peaks of the wave field define the most probable particle flow, which defines a meta-tracklet. Dominant motion patterns are recognized by applying the functions of fuzzy predicates, which represent a combination of common-sense and human expert knowledge about crowd motions, to the meta-tracklets. The experimental results of the proposed method are presented for a subset of UCF dataset and AGORASET crowd simulation videos and have shown promising results in dominant motion pattern recognition.

Crowd Counting via Segmentation Guided Attention Networks and Curriculum Loss

Automatic crowd behaviour analysis is an important task for intelligent transportation systems to enable effective flow control and dynamic route planning for varying road participants. Crowd counting is one of the keys to automatic crowd behaviour analysis. Crowd counting using deep convolutional neural networks (CNN) has achieved encouraging progress in recent years. Researchers have devoted much effort to the design of variant CNN architectures and most of them are based on the pre-trained VGG16 model. Due to the insufficient expressive capacity, the backbone network of VGG16 is usually followed by another cumbersome network specially designed for good counting performance. Although VGG models have been outperformed by Inception models in image classification tasks, the existing crowd counting networks built with Inception modules still only have a small number of layers with basic types of Inception modules. To fill in this gap, in this paper, we firstly benchmark the baseline Inception-v3 model on commonly used crowd counting datasets and achieve surprisingly good performance comparable with or better than most existing crowd counting models. Subsequently, we push the boundary of this disruptive work further by proposing a Segmentation Guided Attention Network (SGANet) with Inception-v3 as the backbone and a novel curriculum loss for crowd counting. We conduct thorough experiments to compare the performance of our SGANet with prior arts and the proposed model can achieve state-of-the-art performance with MAE of 57.6, 6.3 and 87.6 on ShanghaiTechA, ShanghaiTechB and UCF_QNRF, respectively.

Statistical analysis of crowd behaviour in catastrophic situation

Machine learning (ML) is one of the emerging domains in classification and prediction. It is important to understand the responses of individuals in crowd during an earthquake emergency for making appropriate earthquake emergency management plan. Our research is focused on predicting the behaviour of individuals in a crowd during Catastrophic Situation. For this purpose, intended and actual behavioural response of crowd is collected by conducting a series of surveys. The attributes that are selected for result prediction are gender, age, affiliation, health status, training level, nearby exit, earthquake intensity, earthquake location, environmental status, and individual’s response. The dataset thus collected is divided into two crowds, Crowd 1 shows the intended behaviour whereas Crowd 2 shows actual. The decision tree, k-nearest neighbour, Naïve Bayes and neural network machine learning algorithms are used for predicting results. The results are analysed by using Rapid Miner as data mining tool. The dataset is split into two partitions. By applying randomization techniques like simple random sampling, shuffle random sampling, etc. we have trained and tested the machine learning algorithms. The results of this research will be a source of help in understanding critical details about crowd behaviour in earthquake emergency.

A Review of Deep Learning Techniques for Crowd Behavior Analysis

A Review of Deep Learning Techniques for Crowd Behavior Analysis

Crowd Abnormality Detection Using Optical Flow and GLCM-Based Texture Features

Detection of abnormal crowd behavior is one of the important tasks in real-time video surveillance systems for public safety in public places such as subway, shopping malls, sport complexes and various other public gatherings. Due to high density crowded scenes, the detection of crowd behavior becomes a tedious task. Hence, crowd behavior analysis becomes a hot topic of research and requires an approach with higher rate of detection. In this work, the focus is on the crowd management and present an end-to-end model for crowd behavior analysis. A feature extraction-based model using contrast, entropy, homogeneity, and uniformity features to determine the threshold on normal and abnormal activity has been proposed in this paper. The crowd behavior analysis is measured in terms of receiver operating characteristic curve (ROC) & area under curve (AUC) for UMN dataset for the proposed model and compared with other crowd analysis methods in literature to prove its worthiness. YouTube video sequences also used for anomaly detection.

A REAL-TIME IMPROVED PEDESTRIAN DEAD RECKONING TRAJECTORY TRACKING ALGORITHM

Abstract. Accurate location of pedestrians plays a crucial role in emergency relief, traffic control, crowd behavior analysis and other aspects. Especially in the context of the COVID-19 pandemic in recent years, pedestrian location technology can help relevant departments to complete target screening more quickly.However, the Pedestrian Dead Reckoning algorithm can only calculate the target trajectory through the sensor return value, but can not carry out real-time trajectory correction and location.With the rapid development of deep learning, object detection and tracking technology based on computer vision has been applied to pedestrian location, but there are two challenges in the application process.Firstly, in the pedestrian gathering scene, the target number base is large, so the accuracy of the current detection algorithm needs to be improved and the model drift index of the tracking algorithm needs to be reduced. Secondly, there is a certain distortion between the real three-dimensional coordinate space of pedestrians and the two-dimensional image captured by the camera, and the transformation of the spatial coordinate of the target point is a technical difficulty.In this regard, first of all, to improve the accuracy of pedestrian target detection in crowded scenes, this paper adopts the method of improving the generalization of network to pedestrian target, and uses k-means algorithm to find the best prior frame of pedestrian, and sets the width to height ratio suitable for the target.Secondly, to solve the problem of model drift in the above tracking process, this paper proposes a binary classification model based on target appearance difference, which introduces target context information as a new target distinguishing feature when two or more targets are similar.Finally, in order to obtain more accurate coordinate position information, this paper combines the inverse perspective algorithm to calculate the target coordinates into the coordinates in the world coordinate system, and calculates the exact position of the target in the aerial view, as well as the distance between the targets or the current flow of people.In order to evaluate the effectiveness of the proposed algorithm, experiments on target detection, tracking and precise positioning were carried out in different intensity scenarios to verify the feasibility of the proposed method.

Motion-compensated online object tracking for activity detection and crowd behavior analysis.

It is a nontrivial task to manage crowds in public places and recognize unacceptable behavior (such as violating social distancing norms during the COVID-19 pandemic). In such situations, people should avoid loitering (unnecessary moving out in public places without apparent purpose) and maintain a sufficient physical distance. In this study, a multi-object tracking algorithm has been introduced to improve short-term object occlusion, detection errors, and identity switches. The objects are tracked through bounding box detection and with linear velocity estimation of the object using the Kalman filter frame by frame. The predicted tracks are kept alive for some time, handling the missing detections and short-term object occlusion. ID switches (mainly due to crossing trajectories) are managed by explicitly considering the motion direction of the objects in real time. Furthermore, a novel approach to detect unusual behavior of loitering with a severity level is proposed based on the tracking information. An adaptive algorithm is also proposed to detect physical distance violation based on the object dimensions for the entire length of the track. At last, a mathematical approach to calculate actual physical distance is proposed by using the height of a human as a reference object which adheres more specific distancing norms. The proposed approach is evaluated in traffic and pedestrian movement scenarios. The experimental results demonstrate a significant improvement in the results.

Passenger Flow Prediction of Scenic Spot Using a GCN–RNN Model

The prediction and control of passenger flow in scenic spots is very important to the traffic management and safety of scenic spots. This study aims to predict the passenger flow of a scenic spot based on the passenger flow of the bus and subway stations around the scenic spots. We propose a passenger flow prediction model based on graph convolutional network–recurrent neural network (GCN–RNN). First, a “graph” is constructed according to the geographical relationship between the scenic spot and the surrounding bus and subway stations. Then, characteristics of surrounding areas of bus and subway stations are constructed based on the crowd behavior analysis, and these are then used as the node-information of the “graph”. Last, the GCN–RNN model is used to extract the temporal and spatial characteristics of the passenger flow data of the scenic spot to realize the prediction. The experimental results show that the proposed model is effective in passenger flow prediction in scenic spots.