Search

Train stations have increasingly become crowded, necessitating stringent requirements in the design of stations and commuter navigation through these stations. In this study, we explored the use of mobile eye tracking in combination with observation and a survey to gain knowledge on customer experience in a crowded train station. We investigated the utilization of mobile eye tracking in ascertaining customers perception of the train station environment and analyzed the effect of a signalization prototype (visual pedestrian flow cues), which was intended for regulating pedestrian flow in a crowded underground passage. Gaze behavior, estimated crowd density, and comfort levels (an individuals comfort level in a certain situation), were measured before and after the implementation of the prototype. The results revealed that the prototype was visible in conditions of low crowd density. However, in conditions of high crowd density, the prototype was less visible, and the path choice was influenced by other commuters. Hence, herd behavior appeared to have a stronger effect than the implemented signalization prototype in conditions of high crowd density. Thus, mobile eye tracking in combination with observation and the survey successfully aided in understanding customers perception of the train station environment on a qualitative level and supported the evaluation of the signalization prototype the crowded underground passage. However, the analysis process was laborious, which could be an obstacle for its practical use in gaining customer insights.

Smart Cities refer to urban areas which exploits recent technologies for improving the performance, sustainability, and livability of their infrastructure and services. Crowd Density Analysis (CDA), a vital component of Smart Cities, involves the use of sensors, cameras, and data analytics to monitor and analyze the density and movement of people in public spaces. CDA utilizing DL harnesses the control of neural networks to mechanically and exactly evaluate the density of crowds in numerous settings, mainly in smart cities. DL techniques like Recurrent Neural Network (RNN) and Convolutional Neural Network (CNN), are trained on vast datasets of crowd videos or images to learn complex designs and features. These models can forecast crowd density levels, recognize crowd anomalies, and offer real-time visions into crowd behavior. This study designs an Artificial Intelligence Driven Crowd Density Analysis for Sustainable Smart Cities (AICDA-SSC) technique. The aim of the AICDA-SSC method is to analyze the crowd density and classify it into multiple classes by the use of hyperparameter-tuned DL models. To accomplish this, the AICDA-SSC technique applies contrast enhancement using the CLAHE approach. Besides, the complex and intrinsic features can be derived by the use of the Inception v3 model and its hyperparameters can be chosen by the use of the marine predator’s algorithm (MPA). For crowd density detection and classification, the AICDA-SSC technique applies a gated recurrent unit (GRU) model. Finally, a chaotic sooty tern optimizer algorithm (CSTOA) based hyperparameter selection procedure takes place to increase the effectiveness of the GRU system. The experimental evaluation of the AICDA-SSC technique takes place on a crowd-density image dataset. The experimentation values showcase the superior performance of the AICDA-SSC method to the recently developed DL models.

Forecasting crowd congestion is a critical aspect of crowd management, particularly in dynamic and densely populated areas, such as urban centers, events, or pilgrimage sites. In this paper, we proposed the first crowd congestion forecasting framework for the pilgrimage of Umrah. We addressed the crowd congestion forecasting problem by clustering the crowd flow trajectory in Masjid Al-Haram (Great Mosque) in the city of Makkah into six zones. The framework consists of two main components: 1) Ensemble forecasting model that aims at forecasting the crowd density of Masjid Al-Haram and its six zones, and 2) decision making algorithm that aims at keeping the crowd density at an acceptable level, and recommends updating the crowd flows when the forecasted crowd density exceeds the crowd density threshold. We built the ensemble learning model in three phases. In the first phase, we selected and evaluated different learning base models, including ARIMA, Sequence to Sequence (Seq2Seq) learning, M-1D-CNN-LSTM, and DeepSTN. In the second phase, the best three models, which performed well in the first phase, are selected to build the stacked ensemble model. The latter is validated using the walk-forward technique in the third phase. To evaluate the framework, we built a crowd dataset based on two temporal properties: 1) hourly context and 2) daily context. We evaluated the three phases of the ensemble forecasting model. In the first phase, DeepSTN performs the best by achieving a Mean Absolute Error (MAE) of 0.281. The results also indicate that DeepSTN is the best fit for five zones, and one variant of Seq2Seq, named Seq2Seq2b is the best fit for one zone under Mean Square Error (MSE) and Root Mean Squared Error (RMSE). Under MAE, DeepSTN and Seq2Seq2b, each of which is the best choice for three zones. In the second phase, the stacked ensemble achieves a MAE of 0.257. In the third phase, the stacked ensemble model is validated using the walk forward technique, which allows to reduce the MAE to 0.253. Although this framework focuses on Umrah, it can be customized for other use cases that involve crowd congestion forecasting.

Previous research has determined that home field advantage (HFA) is positively related to crowd density. Isolating this effect is a substantial empirical challenge as crowd density is endogenous with home win-likelihood via fan interest. We consider a natural-experimental setting that introduces exogenous crowd-density variation into National Football League (NFL) games. COVID-19 safety protocols allow us to disentangle crowd-presence, crowd-density, and built-environment effects upon HFA. We find strong evidence that crowd presence is a significant, substantial source of HFA, but crowd density is not. No-crowd games in 2020 featured no measurable HFA conditional upon team strengths, whereas partially fan-restricted games featured no significant decline in HFA relative to games without crowd restrictions (20162019 and 2021). Results suggest HFA is fully attributable to crowd presence, with no evidence of stadium familiarity or travel distance effects. Betting markets efficiently predicted the partial-crowd effect from season's outset but adjusted incrementally (behaviorally) to incorporate the true no-crowd effect only by season's end. [ABSTRACT FROM AUTHOR]

A casino is a recreation center, one of our society's leisure amenities. Therefore, a casino is a public location where guests can play various games of chance and gambling to entertain themselves. From previous reviews as shown in the study, casinos ought to have various crowd control strategies available to avert the risks associated with overcrowding. However, it depends on how effective the designers and other building professionals are willing to implement these strategies to make the building more conducive. The study examined crowd control strategies in recreational facilities in Lagos state, Nigeria, with a view to understanding why these facilities were created for maximum profit returns, over the safety of the users. To achieve this, a structured questionnaire was used for data collection, and a descriptive approach was used to analyze the data. The findings revealed that the grand mean value of 4.57 was more significant than the cut-off mean value of 3.5, indicating that measures implemented for crowd control in the casino were ineffective. The findings imply that the crowd control strategies implemented have less effect on casino users. Thus, inadequate provision of crowd control strategies puts users at potential risk in the casinos. Casinos should provide safety measures by design from the onset or as a precaution after establishment. [ABSTRACT FROM AUTHOR]

A mathematical model for the evacuation of people from a road tunnel is created, taking into account various factors such as the speed at which people move, the density of the flow of people, and the outcome of the fire. This model allows for the precise calculation of the evacuation time and the optimization of the evacuation route in a fire scenario. The constructed mathematical model was used to determine how long it would take for people to evacuate this road tunnel, and the findings of the Pathfinder simulation were compared. The findings demonstrate a relationship between the model's evacuation time and the human flow density, movement velocity, and fire product characteristics. The evacuation time is closer to the outcome of the actual fire scene when the impact of the fire environment on the speed of evacuation is quantified. The mathematical model of human evacuation's calculation of the evacuation time is essentially accurate when compared to the Pathfinder simulation's calculation, with an error of only 0.77 %. The model provides recommendations for optimizing the evacuation of people from a road tunnel in the case of a fire by not only predicting where the crowding would occur but also by calculating the duration of the crowding.

Copyright of Guangdong Architecture Civil Engineering is the property of Guangdong Architecture Civil Engineering Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Counting and detecting occluded faces in a crowd is a challenging task in computer vision. In this paper, we propose a new approach to face detection-based crowd estimation under significant occlusion and head posture variations. Most state-of-the-art face detectors cannot detect excessively occluded faces. To address the problem, an improved approach to training various detectors is described. To obtain a reasonable evaluation of our solution, we trained and tested the model on our substantially occluded data set. The dataset contains images with up to 90 degrees out-of-plane rotation and faces with 25%, 50%, and 75% occlusion levels. In this study, we trained the proposed model on 48,000 images obtained from our dataset consisting of 19 crowd scenes. To evaluate the model, we used 109 images with face counts ranging from 21 to 905 and with an average of 145 individuals per image. Detecting faces in crowded scenes with the underlying challenges cannot be addressed using a single face detection method. Therefore, a robust method for counting visible faces in a crowd is proposed by combining different traditional machine learning and convolutional neural network algorithms. Utilizing a network based on the VGGNet architecture, the proposed algorithm outperforms various state-of-the-art algorithms in detecting faces ‘in-the-wild’. In addition, the performance of the proposed approach is evaluated on publicly available datasets containing in-plane/out-of-plane rotation images as well as images with various lighting changes. The proposed approach achieved similar or higher accuracy.

Sports spectators are one of the factors that affect home advantage. The outbreak of the COVID-19 pandemic created unique conditions under which most of the leagues in the world played matches without crowds for over six months. This situation facilitated an analytical comparison of two different periods: before and during the coronavirus pandemic. The current study sought to examine home advantage in the Israeli sport domain in general, and specifically the impact of the absence of a crowd. The study consisted of 4,030 matches played in Israel’s top football and basketball leagues, of which 3,589 took place with crowds from August 2015 to March 2020, while the others were held without spectators from May 2020 to February 2021. Descriptive and analyses of variance procedures indicated a home advantage independent of crowd size, density, geographic region, league level, and type of sport. However, higher-quality teams demonstrated a higher home advantage ratio for the goals conceded. The findings of the study indicate that in the Israeli context, the crowd plays less of a role in home advantage than other potential factors.

Aiming at the problem that the existing crowd counting methods cannot achieve accurate crowd counting and map visualization in a large scene, a crowd density estimation and mapping method based on surveillance video and GIS (CDEM-M) is proposed. Firstly, a crowd semantic segmentation model (CSSM) and a crowd denoising model (CDM) suitable for high-altitude scenarios are constructed by transfer learning. Then, based on the homography matrix between the video and remote sensing image, the crowd areas in the video are projected to the map space. Finally, according to the distance from the crowd target to the camera, the camera inclination, and the area of the crowd polygon in the geographic space, a BP neural network for the crowd density estimation is constructed. The results show the following: (1) The test accuracy of the CSSM was 96.70%, and the classification accuracy of the CDM was 86.29%, which can achieve a high-precision crowd extraction in large scenes. (2) The BP neural network for the crowd density estimation was constructed, with an average error of 1.2 and a mean square error of 4.5. Compared to the density map method, the MAE and RMSE of the CDEM-M are reduced by 89.9 and 85.1, respectively, which is more suitable for a high-altitude camera. (3) The crowd polygons were filled with the corresponding number of points, and the symbol was a human icon. The crowd mapping and visual expression were realized. The CDEM-M can be used for crowd supervision in stations, shopping malls, and sports venues. [ABSTRACT FROM AUTHOR]

Train stations have increasingly become crowded, necessitating stringent requirements in the design of stations and commuter navigation through these stations. In this study, we explored the use of mobile eye tracking in combination with observation and a survey to gain knowledge on customer experience in a crowded train station. We investigated the utilization of mobile eye tracking in ascertaining customers' perception of the train station environment and analyzed the effect of a signalization prototype (visual pedestrian flow cues), which was intended for regulating pedestrian flow in a crowded underground passage. Gaze behavior, estimated crowd density, and comfort levels (an individual's comfort level in a certain situation), were measured before and after the implementation of the prototype. The results revealed that the prototype was visible in conditions of low crowd density. However, in conditions of high crowd density, the prototype was less visible, and the path choice was influenced by other commuters. Hence, herd behavior appeared to have a stronger effect than the implemented signalization prototype in conditions of high crowd density. Thus, mobile eye tracking in combination with observation and the survey successfully aided in understanding customers' perception of the train station environment on a qualitative level and supported the evaluation of the signalization prototype the crowded underground passage. However, the analysis process was laborious, which could be an obstacle for its practical use in gaining customer insights. [ABSTRACT FROM AUTHOR]

Counting and detecting occluded faces in a crowd is a challenging task in computer vision. In this paper, we propose a new approach to face detection-based crowd estimation under significant occlusion and head posture variations. Most state-of-the-art face detectors cannot detect excessively occluded faces. To address the problem, an improved approach to training various detectors is described. To obtain a reasonable evaluation of our solution, we trained and tested the model on our substantially occluded data set. The dataset contains images with up to 90 degrees out-of-plane rotation and faces with 25%, 50%, and 75% occlusion levels. In this study, we trained the proposed model on 48,000 images obtained from our dataset consisting of 19 crowd scenes. To evaluate the model, we used 109 images with face counts ranging from 21 to 905 and with an average of 145 individuals per image. Detecting faces in crowded scenes with the underlying challenges cannot be addressed using a single face detection method. Therefore, a robust method for counting visible faces in a crowd is proposed by combining different traditional machine learning and convolutional neural network algorithms. Utilizing a network based on the VGGNet architecture, the proposed algorithm outperforms various state-of-the-art algorithms in detecting faces ‘in-the-wild’. In addition, the performance of the proposed approach is evaluated on publicly available datasets containing in-plane/out-of-plane rotation images as well as images with various lighting changes. The proposed approach achieved similar or higher accuracy. [ABSTRACT FROM AUTHOR]

This study aims to determine predictors of crowd effect in five major football leagues in Europe. Literature review shows that crowd effect can be determined as size, proximity or density for the analysis. In this study, density was selected among them. Therefore, stadium occupancy rates were used as the crowd effect indicator. As the predictors of crowd effect; total transfer expenditure, total market value, average goals scored per match, UEFA coefficients of each league were utilized as variables of the research. In addition, gross domestic product of each country were included in the analysis as the predictor. Because supporters’ economic conditions are also important to afford ticket prices. In this context, data regarding the variables includes from the season of 2005-2006 to 2019-2020 for English Premier League, French Ligue 1, German Bundesliga, Italian Serie A, Spanish La Liga. In this study, panel data analysis was used among quantitative research methods. Stationary of data was determined at the level of I(1). It was indicated through cointegration test that there was a cointegration relationship in the panel. Hence, stadium occupancy rate would move together with other variables in the long term except total market value. According to panel causality analysis results; total transfer expenditure, average goals scored per match, and UEFA coefficients, and gross domestic product are predictors of stadium occupancy rate.

Train stations have increasingly become crowded, necessitating stringent requirements in the design of stations and commuter navigation through these stations. In this study, we explored the use of mobile eye tracking in combination with observation and a survey to gain knowledge on customer experience in a crowded train station. We investigated the utilization of mobile eye tracking in ascertaining customers’ perception of the train station environment and analyzed the effect of a signalization prototype (visual pedestrian flow cues), which was intended for regulating pedestrian flow in a crowded underground passage. Gaze behavior, estimated crowd density, and comfort levels (an individual’s comfort level in a certain situation), were measured before and after the implementation of the prototype. The results revealed that the prototype was visible in conditions of low crowd density. However, in conditions of high crowd density, the prototype was less visible, and the path choice was influenced by other commuters. Hence, herd behavior appeared to have a stronger effect than the implemented signalization prototype in conditions of high crowd density. Thus, mobile eye tracking in combination with observation and the survey successfully aided in understanding customers’ perception of the train station environment on a qualitative level and supported the evaluation of the signalization prototype the crowded underground passage. However, the analysis process was laborious, which could be an obstacle for its practical use in gaining customer insights.

Video surveillance in smart cities provides efficient city operations, safer communities, and improved municipal services. Object detection is a computer vision-based technology, which is utilized for detecting instances of semantic objects of a specific class in digital videos and images. Crowd density analysis is a widely used application of object detection, while crowd density classification techniques face complications such as inter-scene deviations, non-uniform density, intra-scene deviations and occlusion. The convolution neural network (CNN) model is advantageous. This study presents Aquila Optimization with Transfer Learning based Crowd Density Analysis for Sustainable Smart Cities (AOTL-CDA3S). The presented AOTL-CDA3S technique aims to identify different kinds of crowd densities in the smart cities. For accomplishing this, the proposed AOTL-CDA3S model initially applies a weighted average filter (WAF) technique for improving the quality of the input frames. Next, the AOTL-CDA3S technique employs an AO algorithm with the SqueezeNet model for feature extraction. Finally, to classify crowd densities, an extreme gradient boosting (XGBoost) classification model is used. The experimental validation of the AOTL-CDA3S approach is tested by means of benchmark crowd datasets and the results are examined under distinct metrics. This study reports the improvements of the AOTL-CDA3S model over recent state of the art methods. [ABSTRACT FROM AUTHOR]

Regular shelves configuration forms unique characteristics of internal obstacles in a supermarket. It is crucial to study the crowd evacuation affected by obstacles during accidents or disasters in supermarkets as assembly occupancies. Based on the Tri-14 model, this paper studied the influence of safety exit designs and shelves' configuration on the crowd evacuation efficiency with different densities in a supermarket through parameters and images. The results mainly indicate that: (1) The evacuation distance of farthest grid (Dfg) is the key factor to determine the total evacuation time of a low-density crowd. (2) For a high-density crowd, the closer the proportion ratio of the number of evacuees choosing each exit is to that of designed strand numbers of crowd flow at each exit, the higher the evacuation efficiency and average utilization efficiency of exits get; the scattered arrangement of exits will not necessarily lead to improving evacuation efficiency. Shelves' configuration could lead to the extension of Dfg, but the change may reduce evacuation time instead, especially when forming effective advanced-gathering zones. (3) Under appropriate conditions, the impact of shelves' configuration on evacuation efficiency can be negligible. This study has certain guiding significance for obstacle configuration and architectural design in large public gathering places. [ABSTRACT FROM AUTHOR]

Crowd stability analysis is an important yet challenging task, as it is difficult to obtain the quantitative information regarding a crowd in motion, for instance, the crowd count and crowd density in a pedestrian merging area. This paper proposes a novel model that can be used to accurately analyze the crowd stability based on images obtained from a real-time video surveillance system (VSS) in dense crowd scenarios. To enhance the accuracy of the human head recognition for the crowd counting and crowd density estimation, we improve the conventional convolution-neural-network (CNN) model with more columns and merged features, obtaining a four-column convolutional neural network (4C-CNN). Using more columns with receptive fields of deferent sizes, more merged features can be learned, to be adaptive to variations in pedestrian head size due to image resolution. Furthermore, the crowd density of different areas is calculated with image rectification against the perspective distortion. By utilizing the stability criterion based on crowd density, we propose a crowd stability analysis model (CSAM) with the capability of quantitative computation dynamically. The results of extensive experiments performed on public datasets indicate that this improved CNN model exhibits a better performance for crowd counting than the typical multi-column CNN models. In addition, the experiment results pertaining to Shanghai Hongqiao Railway Station demonstrate the effectiveness of the crowd stability analysis model. Thus, this integrated approach can simultaneously conduct the processes of crowd counting, image rectification, density map calculation and crowd stability analysis by using dense crowd images from a VSS. [ABSTRACT FROM AUTHOR]

The urban open public spaces are the areas where people tend to gather together, which may lead to great crowd-gathering risk. This paper proposes a new method to assess the rank and spatial distribution of crowd-gathering risk in open public spaces in a large urban area. Firstly, a crowd density estimation method based on Tencent user density (TUD) data is built for different times in open public spaces. Then, a reasonable crowd density threshold is delimited to detect critical crowd situations in open public spaces and find out the key open public spaces that need to have intensive crowd-gathering prevention. For estimating the crowd-gathering risk in key open public spaces, the quantified risk assessment approach is conducted based on the classical risk theory that simultaneously considers the probability of an accident occurring, the severity of the accident consequence, and the risk aversion factor. A case study of the area within the Outer-ring Road of Shanghai was conducted to determine the feasibility of the new method. The thematic maps that describe the ranks and spatial distribution of crowd-gathering risk were generated. According to the risk maps, the government can determine the crowd control measures in different areas to reduce the crowd-gathering risk and prevent dangerous events. [ABSTRACT FROM AUTHOR]

Cruise ships are large and complex, and it is difficult to manually make a plan to evacuate people to safe areas in a short time. Evacuation time and personnel safety are both important for emergency evacuation. This paper proposes an evacuation strategy that considers the path capacity and risk level to guide evacuees in fire; it not only ensures the safety of people on dangerous paths but also reduces road congestion to shorten evacuation time. High crowd density means slow moving speed, an exponential function including straight path and stairs speed characteristics is proposed to illustrate the relationship between crowd density and moving speed. Path capacity constraints are used to avoid the congestion caused by the evacuees in a panic. In order to evacuate the evacuees in the risk areas as soon as possible, this paper divides the path into three risk levels according to carbon monoxide concentration, visibility, and temperature along the paths. The people on the higher-risk paths are given higher priority to enter evacuation paths than those on lower risk. The priority strategy evacuates the people on risk paths to safe areas in less time. This paper models the evacuation network topology of a cruise ship and simulates the evacuation process of some situations that have different numbers of evacuees and path capacity constraints. The evacuation strategies and simulation results are guidelines for the crews to guide the people to evacuate to safe areas when there is a fire accident on the cruise ship. [ABSTRACT FROM AUTHOR]

In this paper we present an IoT based solution that can reduce the complexity of crowd estimation. About the human crowd estimation many technique are in existence but now a day’s more work are going on in the field of IoT, because this is era of IoT and most of the every organization is shifted towards IoT based system. So we are also proposed this system in this field and we are using the Respberry Pi-3 which are having quad core processor that can very useful and gives better result and gives accurate number even in the humans are very close to each others. This IoT based model can easily implements in the crowded areas and monitor the same in this area. The camera module in this model also helps to differentiate between human and other bodies. As this is a mobile model it can easily fix on the walls of street light and in the time of dark or in night the camera capture clear image for process in the presence of street light. So that this model gives better result almost 70% better result in compare to exiting approaches.

Aiming at the problem that the existing crowd counting methods cannot achieve accurate crowd counting and map visualization in a large scene, a crowd density estimation and mapping method based on surveillance video and GIS (CDEM-M) is proposed. Firstly, a crowd semantic segmentation model (CSSM) and a crowd denoising model (CDM) suitable for high-altitude scenarios are constructed by transfer learning. Then, based on the homography matrix between the video and remote sensing image, the crowd areas in the video are projected to the map space. Finally, according to the distance from the crowd target to the camera, the camera inclination, and the area of the crowd polygon in the geographic space, a BP neural network for the crowd density estimation is constructed. The results show the following: (1) The test accuracy of the CSSM was 96.70%, and the classification accuracy of the CDM was 86.29%, which can achieve a high-precision crowd extraction in large scenes. (2) The BP neural network for the crowd density estimation was constructed, with an average error of 1.2 and a mean square error of 4.5. Compared to the density map method, the MAE and RMSE of the CDEM-M are reduced by 89.9 and 85.1, respectively, which is more suitable for a high-altitude camera. (3) The crowd polygons were filled with the corresponding number of points, and the symbol was a human icon. The crowd mapping and visual expression were realized. The CDEM-M can be used for crowd supervision in stations, shopping malls, and sports venues.

Karbala city is known to host one of the largest annual human gatherings in the world, where a diverse group of visitors congregates in the Karbala old city to participate in the Al-Arbaeen rites. This significant event peaked on Safar 19th, resulting in mobility issues, particularly in the Bayn Al-Haramayn zone. To address this concern, this study proposes a plan that estimates the number of visitors over the next 25 years and presents a solution for the vertical expansion of the zone while maintaining its urban fabric. The proposal includes estimating the areas required to accommodate the visitors based on an average crowd density of 3.5 individuals per square meter. The authors predict that the number of pilgrims will continue to increase over the next 25 years, and by 2046, an area of 148 square kilometers will be necessary to accommodate them. Expanding the Bayn Al-Haramayn zone is crucial as it is a vital destination for many visitors, and its spiritual significance adds value to the experience of performing the Ziyarat-Alarbaeen rituals. The proposed solution focuses on vertical expansion, providing a total area of 10, 116 m2 and can accommodate up to 35, 500 capita. Moreover, the proposed solution also integrates mobility paths that align with the urban scene of the area.

The detection of crowd density levels and anomalies is a hot topic in video surveillance. Especially in human-centric action and activity-based movements. In some respects, the density level variation is considered an anomaly in the event. Crowd behaviour identification relies on a computer-vision-based approach and basically deals with spatial information of foreground video information. In this work, we focused on a deep-learning-based attention-oriented classification system for identifying several basic movements in public places, especially, human flock movement, sudden motion changes and panic events in several indoor and outdoor places. The important spatial features were extracted from a bilinear CNN and a multicolumn multistage CNN with preprocessed morphological video frames from videos. Finally, the abnormal and crowd density estimation was distinguished by using an attention feature combined with a multilayer CNN feature by modifying the fully connected layer for several categories (binary and multiclass). We validate the proposed method on several video surveillance datasets including PETS2009, UMN and UCSD. The proposed method achieved an accuracy of 98.62, 98.95, 96.97, 99.10 and 98.38 on the UCSD Ped1, UCSD Ped2, PETS2009, UMN Plaza1 and UMN Plaza2 datasets, respectively, with the different pretrained models. We compared the performance between recent modern approaches and the proposed method (MCMS-BCNN-Attention) and achieved the highest accuracy. The anomaly detection performance on the UMN and PETS2009 datasets was compared with that of a state-of-the-art method and achieved the best AUC results as 0.9953 and 1.00 for both scenarios, respectively, with a binary classification.

Video surveillance in smart cities provides efficient city operations, safer communities, and improved municipal services. Object detection is a computer vision-based technology, which is utilized for detecting instances of semantic objects of a specific class in digital videos and images. Crowd density analysis is a widely used application of object detection, while crowd density classification techniques face complications such as inter-scene deviations, non-uniform density, intra-scene deviations and occlusion. The convolution neural network (CNN) model is advantageous. This study presents Aquila Optimization with Transfer Learning based Crowd Density Analysis for Sustainable Smart Cities (AOTL-CDA3S). The presented AOTL-CDA3S technique aims to identify different kinds of crowd densities in the smart cities. For accomplishing this, the proposed AOTL-CDA3S model initially applies a weighted average filter (WAF) technique for improving the quality of the input frames. Next, the AOTL-CDA3S technique employs an AO algorithm with the SqueezeNet model for feature extraction. Finally, to classify crowd densities, an extreme gradient boosting (XGBoost) classification model is used. The experimental validation of the AOTL-CDA3S approach is tested by means of benchmark crowd datasets and the results are examined under distinct metrics. This study reports the improvements of the AOTL-CDA3S model over recent state of the art methods.

Regular shelves configuration forms unique characteristics of internal obstacles in a supermarket. It is crucial to study the crowd evacuation affected by obstacles during accidents or disasters in supermarkets as assembly occupancies. Based on the Tri-14 model, this paper studied the influence of safety exit designs and shelves’ configuration on the crowd evacuation efficiency with different densities in a supermarket through parameters and images. The results mainly indicate that: (1) The evacuation distance of farthest grid (Dfg) is the key factor to determine the total evacuation time of a low-density crowd. (2) For a high-density crowd, the closer the proportion ratio of the number of evacuees choosing each exit is to that of designed strand numbers of crowd flow at each exit, the higher the evacuation efficiency and average utilization efficiency of exits get; the scattered arrangement of exits will not necessarily lead to improving evacuation efficiency. Shelves’ configuration could lead to the extension of Dfg, but the change may reduce evacuation time instead, especially when forming effective advanced-gathering zones. (3) Under appropriate conditions, the impact of shelves’ configuration on evacuation efficiency can be negligible. This study has certain guiding significance for obstacle configuration and architectural design in large public gathering places.

With rapid developments in platforms and sensors technology in terms of digital cameras and video recordings, crowd monitoring has taken a considerable attentions in many disciplines such as psychology, sociology, engineering, and computer vision. This is due to the fact that, monitoring of the crowd is necessary to enhance safety and controllable movements to minimize the risk particularly in highly crowded incidents (e.g. sports). One of the platforms that have been extensively employed in crowd monitoring is unmanned aerial vehicles (UAVs), because UAVs have the capability to acquiring fast, low costs, high-resolution and real-time images over crowd areas. In addition, geo-referenced images can also be provided through integration of on-board positioning sensors (e.g. GPS/IMU) with vision sensors (digital cameras and laser scanner). In this paper, a new testing procedure based on feature from accelerated segment test (FAST) algorithms is introduced to detect the crowd features from UAV images taken from different camera orientations and positions. The proposed test started with converting a circle of 16 pixels surrounding the center pixel into a vector and sorting it in ascending/descending order. A single pixel which takes the ranking number 9 (for FAST-9) or 12 (for FAST-12) was then compared with the center pixel. Accuracy assessment in terms of completeness and correctness was used to assess the performance of the new testing procedure before and after filtering the crowd features. The results show that the proposed algorithms are able to extract crowd features from different UAV images. Overall, the values of Completeness range from 55 to 70 % whereas the range of correctness values was 91 to 94 %.

Crowd density classification has been a challenging task in the field of computer vision, which has various applications in public and commercial domains. Many researches on the classification and recognition method of the crowd density have been introduced in the past, while there still exists the problems of inaccuracy, poor robustness and inefficiency. An adaptive crowd density classification method based on pixels and texture features is proposed in this paper. Core part of the method is to adopt different processing methods according to the corresponding crowd density. The method based on pixel regression method is used for the sparse crowd condition, while the texture features are applied in the dense crowd. Variety of texture features like local binary pattern (LBP), gray-level co-occurrence matrix (GLCM), Gabor, Haar-like and Wavelet group are used on the WorldExpo’10 dataset to obtain an optimum combination of these features, which is proposed to extract the texture features of the crowd images. Then the SVM classifier model based on Bayesian estimation is adopted to train the model which can filter the abnormal sample data to improve the accuracy and generalization performance of the algorithm. Meanwhile, a K-means clustering iterative training method based on optimized sorting samples is designed to improve the training speed in the training process. Extensive experiments from various aspects including parameter optimization, feature selection and model evaluation were conducted. The performance of the model is tested based on mean absolute error (MAE), mean squared error (MSE) and classification rate (CR) in dataset UCSD, Shanghai Tech_A and UCF_CC_50. The experimental results show that CR of the proposed method can reach to 98.2%, whose indexes of MAE and MSE also outperform the most existing methods. In general, the proposed approach in this paper has obvious advantages and great application value. [ABSTRACT FROM AUTHOR]

Cruise ships are large and complex, and it is difficult to manually make a plan to evacuate people to safe areas in a short time. Evacuation time and personnel safety are both important for emergency evacuation. This paper proposes an evacuation strategy that considers the path capacity and risk level to guide evacuees in fire; it not only ensures the safety of people on dangerous paths but also reduces road congestion to shorten evacuation time. High crowd density means slow moving speed, an exponential function including straight path and stairs speed characteristics is proposed to illustrate the relationship between crowd density and moving speed. Path capacity constraints are used to avoid the congestion caused by the evacuees in a panic. In order to evacuate the evacuees in the risk areas as soon as possible, this paper divides the path into three risk levels according to carbon monoxide concentration, visibility, and temperature along the paths. The people on the higher-risk paths are given higher priority to enter evacuation paths than those on lower risk. The priority strategy evacuates the people on risk paths to safe areas in less time. This paper models the evacuation network topology of a cruise ship and simulates the evacuation process of some situations that have different numbers of evacuees and path capacity constraints. The evacuation strategies and simulation results are guidelines for the crews to guide the people to evacuate to safe areas when there is a fire accident on the cruise ship.

There are few methods for detecting abnormal behaviors of crowd massing in public places, and they have the following problem; most of the detection methods are performed after the crowd has gathered abnormally, and the detection accuracy is not high, and the timeliness is not good enough. Therefore, a crowd massing anomaly prediction model based on multi-scale convolutional neural network (MCNN) is proposed. Firstly, a crowd counting model is built through MCNN for testing the video of crowd massing anomaly. In the test, the number of crowd and the coordinate points of their heads are acquired. Secondly, the crowd density, crowd distance potential energy and crowd distribution entropy are calculated. Finally, the predictive model is built through the eigenvalues of three crowd motion state by PSO-ELM. Through the change of characteristic data, the prediction is completed. The experimental results show that, compared with the existing algorithms, the proposed algorithm can effectively achieve the early warning and detection of abnormal behaviors in crowd massing. With a prediction accuracy rate of 97.17%, it's more time-sensitive and provides more time for taking corresponding emergency measures. [ABSTRACT FROM AUTHOR]

Information on congestion of buses, which are one of the major public transportation modes, can be very useful in light of the current COVID-19 pandemic. Because it is unrealistic to manually monitor the number of riders on all buses in operation, a system that can automatically monitor congestion is necessary. The main goal of this paper’s work is to automatically estimate the congestion level on a bus route with acceptable performance. For practical operation, it is necessary to design a system that does not infringe on the privacy of passengers and ensures the safety of passengers and the installation sites. In this paper, we propose a congestion estimation system that protects passengers’ privacy and reduces the installation cost by using Bluetooth low-energy (BLE) signals as sensing data. The proposed system consists of (1) a sensing mechanism that acquires BLE signals emitted from passengers’ mobile terminals in the bus and (2) a mechanism that estimates the degree of congestion in the bus from the data obtained by the sensing mechanism. To evaluate the effectiveness of the proposed system, we conducted a data collection experiment on an actual bus route in cooperation with Nara Kotsu Co., Ltd. The results showed that the proposed system could estimate the number of passengers with a mean absolute error of 2.49 passengers (error rate of 38.8%).

In this paper we present a comparative critical study of visual and non-visual sensors used in crowd behavior analysis. The understanding of crowd has main impact of the analysis how much they support the system is the key factor of the analysis. The surveillance and security prospects are the main feature for crowd that can make system easy and gives better result. The visual sensors that have been widely used are wireless sensor network, computer vision, smart camera, sensor fusion and few more; and the non-visual sensors are regarding the call, IEEE 802, 11 signals measurement, Smart Evactrack, Social Network and Bluetooth etc. This comparative study identified the different analysis of crowd behavior and after analysis we show which technique is better to another one. The smart devices are used now days for surveillance and gives better result in crowd behavior analysis.

Pedestrian traffic is an important subject of surveillance to ensure public safety and traffic management, which may benefit from intelligent and continuous analysis of pedestrian videos. State-of-the-art methods for intelligent pedestrian surveillance have a number of limitations in automating and deriving useful information of high-density pedestrian traffic (HDPT) using closed circuit television (CCTV) images. This work introduces an automatic and improved HDPT surveillance system by integrating and optimizing multiple computational steps to predict pedestrian distribution from input video frames. A fast and efficient particle image velocimetry (PIV) technique is proposed to yield pedestrian velocities. A machine learning regressor model, boosted Ferns, is used to improve pedestrian count and density estimation: an essential metric for HDPT analysis. A camera perspective model is proposed to improve the speed and position estimates of HDPT by projecting 2D image pixels to 3D world-coordinate dat. All these functional improvements in HDPT velocity and displacement estimations are used as inputs to a sophisticated pedestrian flow evolution model, PEDFLOW to predict HDPT distribution at a future time point, which is a crucial information for pedestrian traffic management. The predicted and simulated HDPT properties (density, velocity) obtained using the proposed framework show low errors when compared to the ground truth data. The proposed framework is computationally efficient, suitable for multiple camera feeds with HDPT videos, and capable of rapidly analyzing and predicting flows of thousands of pedestrians. The paper shows one of the first steps towards fully integrated CCTV-based automated HDPT management system. [ABSTRACT FROM AUTHOR]

This paper proposes a novel approach for crowd counting in low to high density scenarios in static images. Current approaches cannot handle huge crowd diversity well and thus perform poorly in extreme cases, where the crowd density in different regions of an image is either too low or too high, leading to crowd underestimation or overestimation. The proposed solution is based on the observation that detecting and handling such extreme cases in a specialized way leads to better crowd estimation. Additionally, existing methods find it hard to differentiate between the actual crowd and the cluttered background regions, resulting in further count overestimation. To address these issues, we propose a simple yet effective modular approach, where an input image is first subdivided into fixed-size patches and then fed to a four-way classification module labeling each image patch as low, medium, high-dense or no-crowd. This module also provides a count for each label, which is then analyzed via a specifically devised novel decision module to decide whether the image belongs to any of the two extreme cases (very low or very high density) or a normal case. Images, specified as high- or low-density extreme or a normal case, pass through dedicated zooming or normal patch-making blocks respectively before routing to the regressor in the form of fixed-size patches for crowd estimate. Extensive experimental evaluations demonstrate that the proposed approach outperforms the state-of-the-art methods on four benchmarks under most of the evaluation criteria. [ABSTRACT FROM AUTHOR]

Crowd density estimation is one of the critical issues in social activities. The traditional solution to this problem is to leverage video surveillance to monitor a crowd. However, this is not accurate for crowd density estimation because it is still hard to identify people from background. In the past few years, more and more people use Wi-Fi enabled smartphones. Smartphones can send Wi-Fi request packets periodically, even when they are not connected to access points. This gives another promising solution to the crowd density estimation even for the public environment. In this paper, we first develop a Wi-Fi monitor detection that can capture smartphone passive Wi-Fi signal information including MAC address and received signal strength indicator. Then, we propose a positioning algorithm based on smartphone passive Wi-Fi probe and a dynamic fingerprint management strategy. In real-world public social activities, a person may have zero, one, two, or multiple smartphones with variant Wi-Fi signals. Therefore, we design a method of computing the probability of a user generating one Wi-Fi signal to identify people population. Finally, we propose a crowd density estimation solution based on Wi-Fi probe packets positioning algorithm. Experiments were conducted in an indoor laboratory class and three public social activities, clearly demonstrated that the proposed solution can effectively and accurately estimate crowd density. [ABSTRACT FROM AUTHOR]

Crowd scene analysis, and in particular its density estimation, is a challenging task due to the lack of spatial information, scale variation, and the large amount of supervised-learning parameters. In order to address these challenges, we propose a Scale-Recursive encoder–decoder Network with Point Supervision (SRN+PS). On the one hand, an encoder–decoder recurrent structure uses features between adjacent scales to tackle scale variation, and a novel loss function, called the row vector-based counting loss, is proposed to focus on the crowd counting accuracy. On the other hand, we employ an additional point segmentation task in training and combine features learned from the two tasks above. The Euclidean loss, row vector-based counting loss, and two-label focal loss are integrated by a joint training scheme, which improves both the quality of density map estimation and the performance of crowd counting. Finally, we propose a weakly supervised framework based on the SRN structure and the Convolutional Winner-Take-All(CWTA) module. In this framework, most parameters are obtained by unsupervised learning with the exception of a few which are tuned by supervised learning in model training. As a result, our multi-scale structure can obtain salient object sparse spatial features from unsupervised learning. Experiments on the ShanghaiTech, UCF _ CC _ 50 and UCSD datasets demonstrate the effectiveness of our proposed method. [ABSTRACT FROM AUTHOR]

Simulation methods that can overcome the limitations of theory and experiment are widely used to predict disaster situations and analyze evacuation safety. To obtain more accurate and realistic simulation results, various situations that arise when people evacuate must be reflected. In this research, regression analysis is applied to existing research on walking speed changes according to crowd density, and we suggest a new equation for walking speed changes of people during evacuation. The suggested equation is applied to crowd evacuation simulations based on the actual viewing angle of a person. In addition, we developed a fallen person algorithm and applied it to examples from the Society of Fire Protection Engineers (SFPE) to analyze the effect a fallen person has on evacuation. Through this research, evacuation safety analysis can be performed for cases involving falling people, and it will be possible to design buildings that can minimize risk and evacuation time in case of an actual emergency situation by analyzing the optimum measures more strictly. [ABSTRACT FROM AUTHOR]