Crowd Activity Research Articles

Coupled Impact of Points of Interest and Thermal Environment on Outdoor Human Behavior Using Visual Intelligence

Although it is well established that thermal environments significantly influence travel behavior, the synergistic effects of points of interest (POI) and thermal environments on behavior remain unclear. This study developed a vision-based outdoor evaluation model aimed at uncovering the driving factors behind human behavior in outdoor spaces. First, Yolo v5 and questionnaires were employed to obtain crowd activity intensity and preference levels. Subsequently, target detection and clustering algorithms were used to derive variables such as POI attractiveness and POI distance, while a validated environmental simulator was utilized to simulate outdoor thermal comfort distributions across different times. Finally, multiple classification models were compared to establish the mapping relationships between POI, thermal environment variables, and crowd preferences, with SHAP analysis used to examine the contribution of each variable. The results indicate that XGBoost achieved the best predictive performance (accuracy = 0.95), with shadow proportion (|SHAP| = 0.24) and POI distance (|SHAP| = 0.12) identified as the most significant factors influencing crowd preferences. By extrapolation, this classification model can provide valuable insights for optimizing community environments and enhancing vitality in areas with similar climatic and cultural contexts.

Spatial quality measurement of commercial streets in old cities of medium-sized cities in China

ABSTRACT Chinese urban development has entered the stage of stock planning, and as an important part of urban public space, the construction of street space has a direct impact on urban development. High-quality street space contributes to sustainable urban development.High-quality street spaces are highly important for constructing vibrant and sustainable cities. Taking Jiaozuo city, a medium-sized city, as an example, this article establishes an evaluation index system for commercial street space quality from the aspects of external characterization and objective material space and uses the Pearson correlation coefficient to explore the influencing factors of urban commercial street space quality. This study finds that (1) crowd activities on commercial streets have different temporal and spatial patterns on weekdays and days off; (2) the external characterization of urban street space quality has a significant positive correlation with objective material spatial elements such as the density of public transportation stops, functional density, functional mixing, interface continuity, and spatial green visibility rate; (3) the enhancement of street accessibility and fine-tuning of functions are key to improving the spatial quality of commercial streets.This study provides theoretical basis and ideas for improving the spatial quality of commercial streets in medium-sized cities in China and promoting sustainable urban development.

Evaluating the vitality of urban public spaces: perspectives on crowd activity and built environment

PurposeIn urban planning, sustainability is closely linked to the quality of urban public spaces (UPS). However, some UPS encounter issues of low attractiveness and underutilisation. Vitality serves as a crucial measure in this context. The research perspective on the vitality of UPS centres on the balance between human activities and the built environment. Therefore, this article aims to systematically review critical aspects of UPS vitality evaluation system, including research objects, vitality components and research methods, from the dimensions of crowd activity and the built environment.Design/methodology/approachA systematic literature review using PRISMA analysed English-language publications from 2008 to 2023 in Scopus and Web of Science (WOS) databases, employing keywords related to UPS and vitality, with defined inclusion and exclusion criteria.Findings(1) Research objects, including parks, squares, waterfronts, blocks and streets. (2) The factors contributing to crowd activity characteristics originate from five dimensions, namely spatial, temporal, visitor, activity and feedback. Environmental factors, both external (accessibility, surrounding function mix and population density) and internal (service facility mix and water presence), significantly impact vitality. (3) The study primarily relies on quantitative data, including traditional surveys and emerging significant data sources like dynamic location and traffic, social media, geospatial and point of interest (POI) data. Data analysis methods commonly used include correlation analysis and comprehensive evaluation techniques.Originality/valueThe findings contribute to a comprehensive understanding of the vitality evaluation system for UPS from multiple perspectives for urban planners, aiding in identifying key factors and research methods in the vitality evaluation of various types of UPS.

The Effect of Green Stormwater Infrastructures on Urban-Tier Human Thermal Comfort—A Case Study in High-Density Urban Blocks

Green stormwater infrastructure (GSI) is a key approach to greening and cooling high-density blocks. Previous studies have focused on the impact of a single GSI on thermal comfort on sunny days, ignoring rainwater’s role and GSI combinations. Therefore, based on measured data of a real urban area in Nanjing, China, this study utilized 45 single-GSI and combination simulation scenarios, as well as three local climate zone (LCZ) baseline scenarios to compare and analyze three high-density blocks within the city. Among the 32 simulations specifically conducted in LCZ1 and LCZ2, 2 of them were dedicated to baseline scenario simulations, whereas the remaining 30 simulations were evenly distributed across LCZ1 and LCZ2, with 15 simulations allocated to each zone. The physiological equivalent temperature (PET) was calculated using the ENVI-met specification to evaluate outdoor thermal comfort. The objective of this research was to determine the optimal GSI combinations for different LCZs, their impact on pedestrian thermal comfort, GSI response to rainwater, and the effect of GSI on pedestrian recreation areas. Results showed that GSI combinations are crucial for improving thermal comfort in compact high-rise and mid-rise areas, while a single GSI suffices in low-rise areas. In extreme heat, rainfall is vital for GSI’s effectiveness, and complex GSI can extend the thermal comfort improvement time following rainfall by more than 1 h. Adding shading and trees to GSI combinations maximizes thermal comfort in potential crowd activity areas, achieving up to 54.23% improvement. Future GSI construction in high-density blocks should focus on different combinations of GSI based on different LCZs, offering insights for GSI planning in Southeast Asia.

Drone path planning and dynamic arena-target allocation for crowd surveillance

The paper addresses the problem of surveillance of dynamic crowds in a bounded arena using multiple drones. The strategy proposes a prediction-based path planning approach for drones, where the target’s future position is predicted and used to generate a traverse path. The procedure for grouping numerous human beings in order to deal with a dense crowd scenario is also described. An algorithm to dynamically divide and allocate the arena to drones is also proposed to ensure equal workload distribution among all drones in the framework. The paper also discusses relevant concepts like detecting anomalous crowd activity and searching for any missing target in the arena. The proposed algorithms are validated on MATLAB environment numerically and ROS/Gazebo physics engine as a part of simulation-in-the-loop (SITL).

Suspicious Crowd Activity Detection and Localization using Computer Vision and CNN

Suspicious Crowd Activity Detection and Localization using Computer Vision and CNN

Cross‐modal knowledge learning with scene text for fine‐grained image classification

AbstractScene text in natural images carries additional semantic information to aid in image classification. Existing methods lack full consideration of the deep understanding of the text and the visual text relationship, which results in the difficult to judge the semantic accuracy and the relevance of the visual text. This paper proposes image classification based on Cross modal Knowledge Learning of Scene Text (CKLST) method. CKLST consists of three stages: cross‐modal scene text recognition, text semantic enhancement, and visual‐text feature alignment. In the first stage, multi‐attention is used to extract features layer by layer, and a self‐mask‐based iterative correction strategy is utilized to improve the scene text recognition accuracy. In the second stage, knowledge features are extracted using external knowledge and are fused with text features to enhance text semantic information. In the third stage, CKLST realizes visual‐text feature alignment across attention mechanisms with a similarity matrix, thus the correlation between images and text can be captured to improve the accuracy of the image classification tasks. On Con‐Text dataset, Crowd Activity dataset, Drink Bottle dataset, and Synth Text dataset, CKLST can perform significantly better than other baselines on fine‐grained image classification, with improvements of 3.54%, 5.37%, 3.28%, and 2.81% over the best baseline in mAP, respectively.

Detecting multiple moving objects for unusual crowd activities detection in video surveillance system

Unusual crowd activity detection is a challenging problem in surveillance video applications because feature extraction is difficult process in crowded scenes. The main objective of this research work is to detect unusual crowd activities and to detect unusual splits of moving objects. Various methods have been employed to address these challenges. However, there is still a lack of appropriate handling of this problem due to frames having occlusion, noise, and congestion. This paper proposes a novel clustering approach to detect unusual crowd activities. The proposed method consists of five phases including foreground extraction, foreground enhancement, foreground estimation, clustering crowds, and the Unusual Crowd Activities (UCA) model. The UCA model can find unusual crowd activities and unusual splits of moving objects using the Laplacian Matrix formulation. Two public datasets viz. PETS 2009 and UMN dataset are used for evaluating the proposed methodology. To estimate the effectiveness of the proposed work, several unusual event detection methods are compared with the proposed work results. The experimental results revealed that the proposed method gives better results than the existing methods.

STICAP : Spatio-temporal Interactive Attention for Citywide Crowd Activity Prediction

Accurate citywide crowd activity prediction (CAP) can enable proactive crowd mobility management and timely responses to urban events, which has become increasingly important for a myriad of smart city planning and management purposes. However, complex correlations across the crowd activities, spatial and temporal urban environment features and their interactive dependencies, and relevant external factors (e.g., weather conditions) make it highly challenging to predict crowd activities accurately in terms of different venue categories (for instance, venues related to dining, services, and residence) and varying degrees (e.g., daytime and nighttime). To address the above concerns, we propose STICAP , a citywide spatio-temporal interactive crowd activity prediction approach. In particular, STICAP takes in the location-based social network check-in data (e.g., from Foursquare/Gowalla) as the model inputs and forecasts the crowd activity within each time step for each venue category. Furthermore, we have integrated multiple levels of temporal discretization to interactively capture the relations with historical data. Then, three parallel Residual Spatial Attention Networks ( RSAN ) in the Spatial Attention Component exploit the hourly, daily, and weekly spatial features of crowd activities, which are further fused and processed by the Temporal Attention Component for interactive CAP . Along with other external factors such as weather conditions and holidays, STICAP adaptively and accurately forecasts the final crowd activities per venue category, enabling potential activity recommendation and other smart city applications. Extensive experimental studies based on three different real-world crowd activity datasets have demonstrated that our proposed STICAP outperforms the baseline and state-of-the-art algorithms in CAP accuracy, with an average error reduction of 35.02%.

Research on the Spatial and Temporal Dynamics of Crowd Activities in Commercial Streets and Their Relationship with Formats—A Case Study of Lao Men Dong Commercial Street in Nanjing

Crowd activity is an important indicator of commercial streets’ attractiveness and developmental potential. The development of positioning technologies such as GPS and mobile signal tracking has provided a large amount of trajectory data for studying crowd activities on commercial streets. These data can not only be used for the statistics, extraction, and visualization of crowd information, but they also facilitate the exploration of deeper insights into dynamic behaviors, choices, trajectories, and other details of crowd activities. Based on this, this article proposes a new framework for analyzing crowd activities to explore the spatial activity patterns of crowds and understand the dynamic spatial needs of people by analyzing their correlations with local formats. Specifically, we analyze the spatial activity characteristics of a crowd in the Lao Men Dong Commercial Street area by identifying the stay points and trajectory clusters of the crowd, and we establish a regression analysis model by selecting commercial street format variables to evaluate their impact on crowd activities. Through case analysis of the Lao Men Dong Commercial Street, this study confirms that our method is feasible and suitable for spatial research at different scales, thereby providing relevant ideas for format location selection, spatial layout, and other planning types, and for promoting the sustainable development of urban spaces.

Supply-demand relationship and spatial flow of urban cultural ecosystem services: The case of Shenzhen, China

Cultural ecosystem services (CES) have garnered significant attention due to their capacity to comprehensively evaluate the influence of ecosystem degradation on human well-being. It is very important to evaluate the spatial coordination relationship between the supply and demand of urban CES and explore its spatial flow mechanism for guiding the sustainable development of urban regions. However, research on the relationship between supply and demand of urban CES and their spatial flows is still in the conceptual exploration stage, and its quantitative assessment methods are not yet mature. Taking Shenzhen as an example, this study uses the Social Values for Ecosystem Services model to evaluate the supply of CES based on environmental background and survey statistics; Uses the topic model of natural language processing, quantify the demand of CES based on social media data. The Bivariate Local Indicators of Spatial Association index is utilized to examine the correlation between supply and demand, while a crowd activity extraction method based on mobile phone signaling data is developed to simulate the spatial flow pattern of CES. The results show that: (1) The supply of urban CES shows obvious spatial differentiation; There are differences in the perception of the needs of various CES. Among them, the beneficiaries have higher needs for Aesthetic and Recreation. (2) The relationship between supply and demand of urban CES shows different degrees of spatial mismatch, with the proportion of the supply-demand matching area to the total area being less than 20%, and the main type of supply-demand mismatch being low supply-high demand. (3) All kinds of CES flow from the center of the study area to the east, among which the flow of recreation and Aesthetic is more active, with the highest flow of 189.7 and 135.3, respectively. Overall, the coordination between various types of CES in the region is still insufficient. We should encourage the establishment and improvement of a diversified transportation system connecting the central urban area and other regions while enhancing the condition of the local ecological conditions, to improve the capacity of urban ring roads and rail transit, to promote the sustainable development of the regional ecological environment and social economy, and to enhance human well-being.

Unusual Crowd Activity Detection in Video Using CNN, LSTM and OpenCV

Abstract: Suspicious behaviour is dangerous in public areas that may cause heavy causalities. There are various systems developed on the basis of video frame acquisition where motion or pedestrian detection occur but those systems are not intelligent enough to identify the unusual activities even at real time. It is required to recognized scamper situation at real time from video surveillance for quick and immediate management before any casualties. Proposed system focuses on recognizing suspicious activities and target to achieve a technique which is able to detect suspicious activity automatically using computer vision. Here system uses OpenCV library for classifying different kind of actions at real time. The motion influence map has been used to represent the motion analysis that frequently changes the position from one place to another. System uses pixel level presentation for making it easy to understand or identify the actual situation.

Machine learning applications for a better demand controlled ventilation system experience in buildings: a review

PurposeAt the beginning of the Corona Virus Disease 2019 (COVID-19) pandemic, a digitalized construction environments surfaced in the heating, ventilation and air conditioning (HVAC) systems in the form of a modern delivery system called demand controlled ventilation (DCV). Demand controlled ventilation has the potential to solve the building ventilation's biggest problem of managing indoor air quality (IAQ) for controlling COVID-19 transmission in indoor environments. However, the improper evaluation and information management of infection prevention on dense crowd activities such as measurement errors and volatile organic compound (VOC) generation failure rates, is fragmented so the aim of this research is to integrate this and explore potentials with machine learning algorithms (MLAs).Design/methodology/approachThe method used is a thorough systematic literature review (SLR) approach. The results of this research consist of a detailed description of the DCV system and digitalized construction process of its IAQ elements.FindingsThe discussion revealed that DCV has a potential for being further integrated by perceiving it as a MLAs and hereby enabling the management of IAQ level from the perspective of health risk function mechanism (i.e. VOC and CO2) for maintaining a comfortable thermal environment and save energy of public and private buildings (PPBs). The appropriate MLA can also be selected in different occupancy patterns for seasonal variations, ventilation behavior, building type and locations, as well as current indoor air pollution control strategies. Furthermore, the conceptual framework showed that MLA application such as algorithm design/Model Predictive Control (MPC) integration can alleviate the high spread limitation of COVID-19 in the indoor environment.Originality/valueFinally, the research concludes that a large unexploited potential within integration and innovation is recognized in the DCV system and MLAs which can be improved to optimize level of IAQ from the perspective of health throughout the building sector DCV process systems. The requirements of CO2 based DCV along with VOC concentrations monitoring practice should be taken into consideration through further research and experience with adaption and implementation from the ventilation control initial stage of the DCV process.

Risk Simulation of Urban Rainstorm Flood Disasters Considering Crowd Activities

Social activities have a significant impact on the rainstorm flood disaster risk. It is crucial to explore the dynamic changes of urban rainstorm flood disaster risk caused by crowd activities. In this study, a risk simulation method of urban rainstorm flood disasters is proposed, composed of an urban rainstorm flood model based on SWMM and LISFLOOD-FP and a crowd activities model based on ABM. Taking the Futian District of Shenzhen as an example, the temporal and spatial changes in rainstorm flood disaster risk for buildings and roads are analyzed under three scenarios: midnight, morning peak, and evening peak. The results show that: (1) Although the overall risk of urban rainstorm flood disasters increases as the inundation area expands, the average risks of roads and buildings increase rapidly and then stabilize during the morning peak due to commuting activities, while the average risk of roads remains high level during the evening peak due to commuting activities, while; (2) The risk of urban rainstorm flood varies significantly at different time periods. The average risk of buildings is the largest during the morning peak, about twice that during the evening peak. The number of high-risk roads during the evening peak is much higher than in the morning peak, and both buildings and roads have the least risk during midnight; (3) The spatial distribution of urban rainstorm flood disaster risk changes with the crowd activities, shifting from residential areas to industrial areas, schools, shopping malls, etc., during the morning peak, while the evening peak shows the reverse.

Tawakal and Endeavors from the Perspective of Qadariyah and Jabariyah Thoughts Responding to the Covid 19 Pandemic

The Covid-19 outbreak is developing so fast in the midst of the life of the world community, and Indonesia is no exception. Its presence causes panic that is so terrible, because of the threat that is not kidding, which can lead to death. All lines take a role to be able to stop the rate of development of the effects of this virus, to stop crowd activities, including worship in houses of worship. With this policy, the community's response varied greatly. Of course this response is the result of the understanding that has been carried out so far. There are three groups in addressing the issue of destiny. First, Jabariyah is a group that only puts their trust in Allah, but denies endeavor. Second, the Qadariyyah are a group that denies destiny, only make endeavors but forget to rely on Allah. The third is the middle group, namely the group that is able to combine the concept of trustworthiness with endeavor in matters of destiny. So to provide a bright spot and be able to understand the problem of destiny, this situation needs to be described, then given a conceptual analysis related to the problem of destiny in the perspective of Qadariyah, Jabariyah and the concepts of endeavor and trust.

Key environmental factors affecting perceptions of security of night-time walking in neighbourhood streets: A discussion based on fear heat maps

BackgroundWalking plays an important role in residents’ health. After experiencing rapid development, most cities in China have gradually entered the process of urban renewal. Therefore, improving the quality of neighbourhood streets in the old city has become an important issue. The sense of security at night has become an important part of street reconstruction. Therefore, finding out the key environmental factors that affect the security of night-time walking in the streets of the old city has become an important prerequisite for street reconstruction. MethodsFirstly, according to the theoretical explanation of security in the existing literature, the environmental variables that may affect the security of night-time walking are determined. Besides, we chose the typical neighbourhood streets in the old town that need to be improved urgently, and recruited 32 subjects in an on-site experiment to record. Through wearable devices, the galvanic skin response, (GPS), and panoramic video signals generated by the subject during the experiment. The high arousal environment nodes of the subjects were determined by Galvanic skin response GSR signal and GPS signal. According to the semi-structured interview of the subjects, we valenced these high-arousal environment nodes and established a map of each subject’s fear emotional environment nodes. Aggregated into a street walking fear map by kernel density estimation. Finally, we selected the environment nodes with different degrees of fear on the map, established the optimal regression model of night-time walking security through the optimal subset regression method, and finally identified the critical environmental factors. Results and conclusionThe key environmental influences are street transparency, illegal parking level, environmental cleanliness level, light-transmittance intensity form building, CCTV density, and crowd activity intensity. The above key factors suggest that theEyes on the Street (EoS) theory seems to occupy a more important position in the relevant theories of street night-time security research. It also suggests that the privacy of subjects needs to be considered when improving the security of the street at night.

Localization of Strangeness for Real Time Video in Crowd Activity Using Optical Flow and Entropy

Anomaly detection, which is also referred to as novelty detection or outlier detection, is process of identifying unusual occurrences, observations, or events which considerably differ from the bulk of data and do not fit a predetermined definition of typical behavior. Medicine, cybersecurity, statistics, machine vision, law enforcement, neurology, and financial fraud are just a handful of the industries where anomaly detection is used. In the presented study, an online tool is utilized to identify crowd distortions, which could be brought on by panic. An activity map is produced with the use of numerous frames to show the continuity regarding the flow over time following the global optical flow has been calculated in the quickest time and with the highest precision possible utilizing the Farneback approach to calculate the magnitudes. Utilizing a specific threshold, the oddity in the video will be picked up by the activity map's generation of an entropy. The results indicate that the maximum entropy level for indoor video is <0.16 and the maximum entropy level for outdoor video is >0.45. A threshold of 0.04 is used to determine whether a frame is abnormal or normal.

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.

Abnormal event detection model using an improved ResNet101 in context aware surveillance system

AbstractSurveillance system plays a significant role for achieving security monitoring in the place of crowd areas. Offline monitoring of these crowd activity is quite challenging because it requires huge number of human resources for attaining efficient tracking. For shortcoming these issue automated and intelligent based system must be developed for efficiently monitor crowd and detect abnormal activity. However the existing methods faces issues like irrelevant features, high cost and process complexity. In this current research context aware surveillance‐system utilising hybrid ResNet101‐ANN is developed for effective abnormal activity detection. For this proposed approach video acquired from surveillance camera is considered as input. Then, acquired video is segmented into multiple frames. After that pre‐processing techniques such as denoising using mean filter, motion deblurring, contrast enhancement using Histogram Equalisation and canny edge detection is applied in this segmented frames. Further, the pre‐processed frame is fetched into hybrid ResNet101‐ANN classifier for abnormal event classification. Here, ResNet101 is used for extracting the features from the frames and Artificial neural network which replaces the fully connected layer of ResNet101 us used to detect the abnormal activity. If once abnormal‐events detected the context aware services generate alert to the user for preventing abnormal‐activities. Accuracy, precision, recall, and error values reached for the proposed‐model on simulation were 0.98, 0.98, 0.98 and 0.017 respectively. Using this proposed model effective crowd monitoring and abnormal activity detection can be achieved.

Parameterized Site Selection Approach of Park Entrance Based on Crowd Simulation and Design Requirement

With the extensive application of data analysis in various parts of the landscape design process, Building Information Modeling (BIM), City Information Modeling (CIM), and Landscape Information Modeling (LIM) all aim to achieve key data sharing and collaboration in the whole cycle and promote the development of smart cities. Landscape element indicators are complex, diverse, and difficult to quantify, which is one of the reasons for the slow development of LIM. However, with the development requirements of LIM, quantifying landscape elements and transforming landscapes into digital landscape information has become a hot spot in the landscape design industry. Landscape parametric design aims to transform the design elements into quantifiable parameters, obtain the design scheme by changing the value of the parameters, and form the design results based on digital information. It is one of the foundations of LIM. Based on the Rhino + Grasshopper (R+G) platform, this study takes Shuixizhuang Park as an example and establishes the parametric design approach for the park entrance. The approach involves several steps: (1) Confirming the boundary and key points of the park to prepare the basic data for parametric design. (2) Utilizing the Physarealm Algorithm Method (PAM) to simulate crowd paths, the Site Slope Algorithm Model (SSAM) to analyze terrain slope, the Road Intersection Algorithm Model (RIAM) to determine the scope of the park entrance area based on the national and local design codes, and the Crowd Density Algorithm Model (CDAM) and Crowd Convenience Algorithm Model (CCAM) to analyze the density and convenience of the crowd to preliminarily confirm the park entrance. (3) Meeting the basic requirements of the crowd and vehicle gathering and spread by using the Square Area Review Algorithm Model (SARAM) and Parking Lot Review Algorithm Model (PLRAM) to recheck the site area of the park entrance square and park lot to optimize the park entrance. This approach constructs several site analysis models based on the R+G platform and introduces PAM to analyze crowd activity paths, proposing a landscape parametric design method that integrates crowd activity and landscape design requirements. Compared with the classical design, the landscape parametric design derived from the comprehensive data analysis reduces human interference, is more scientific and practical, and better meets the requirements of people entering the park. The approach also provides ideas for other landscape parametric site selections. By adjusting the values of element parameters, the approach can also be applied to the site selection and design of other landscapes.