Crowd Density Estimation Methods Research Articles

A Weakly-Supervised Crowd Density Estimation Method Based on Two-Stage Linear Feature Calibration

A Weakly-Supervised Crowd Density Estimation Method Based on Two-Stage Linear Feature Calibration

Crowd Density Estimation Method based on a Cascaded Multilevel Convolution Neural Network

Crowd Density Estimation Method based on a Cascaded Multilevel Convolution Neural Network

Crowd Density Estimation and Mapping Method Based on Surveillance Video and GIS

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.

Risk Assessment of Crowd-Gathering in Urban Open Public Spaces Supported by Spatio-Temporal Big Data

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.

Improving Crowd Density Estimation by Fusing Aerial Images and Radio Signals

A recent line of research focuses on crowd density estimation from RGB images for a variety of applications, for example, surveillance and traffic flow control. The performance drops dramatically for low-quality images, such as occlusion, or poor light conditions. However, people are equipped with various wireless devices, allowing the received signals to be easily collected at the base station. As such, another line of research utilizes received signals for crowd counting. Nevertheless, received signals offer only information regarding the number of people, while an accurate density map cannot be derived. As unmanned aerial vehicles (UAVs) are now treated as flying base stations and equipped with cameras, we make the first attempt to leverage both RGB images and received signals for crowd density estimation on UAVs. Specifically, we propose a novel network to effectively fuse the RGB images and received signal strength (RSS) information. Moreover, we design a new loss function that considers the uncertainty from RSS and makes the prediction consistent with the received signals. Experimental results show that the proposed method successfully helps break the limit of traditional crowd density estimation methods and achieves state-of-the-art performance. The proposed dataset is released as a public download for future research.

Crowd Density Estimation Method Using Deep Learning for Passenger Flow Detection System in Exhibition Center

Aiming at the problems of crowd distribution, scale feature, and crowd feature extraction difficulties in exhibition centers, this paper proposes a crowd density estimation method using deep learning for passenger flow detection systems in exhibition centers. Firstly, based on the pixel difference symbol feature, the difference amplitude feature and gray feature of the central pixel are extracted to form the CLBP feature to obtain more crowd group description information. Secondly, use the LR activation function to add nonlinear factors to the convolution neural network (CNN) and use dense blocks derived from crowd density estimation to train the LR-CNN crowd density estimation model. Finally, experimental results show that the mean absolute error (MAE) and mean square error (MSE) of the proposed method in the UCF_CC_50 dataset are 325.6 and 369.4, respectively. Besides, MAE and MSE in part_A of the Shanghai Tech dataset are 213.5 and 247.1, respectively, and they in part_B are 85.3 and 99.7, respectively. The proposed method effectively improves the accuracy of crowd density estimation in exhibition centers.

A survey of crowd counting and density estimation based on convolutional neural network

Crowd counting and crowd density estimation methods are of great significance in the field of public security. Estimating crowd density and counting from single image or video frame has become an essential part of a computer vision system in various scenarios. In this paper, we comprehensively review the recent research advancement on crowd counting and density estimation. First of all, we introduce the background of crowd counting and crowd density estimation. Second, the traditional crowd counting methods are summarized. Third, we focus on reviewing the crowd counting and crowd density methods based on convolutional neural network (CNN) models. Next, we report and discuss the experimental results of a number of typical methods on benchmark datasets. Finally, we present the promising future directions of crowd counting and crowd density.

Crowd density estimation via a multichannel dense grouping network

Deep learning has made substantial progress in crowd density estimation, but in practical application, due to the interference factors such as uneven distribution of crowd and changes in illumination, the existing methods still have large errors in counting. To solve the above problems, a crowd density estimation method based on multichannel dense grouping network is proposed. To solve the problem that it is difficult to extract the multiscale information of the crowd due to the uneven distribution of the crowd, multichannel dense grouping module (McDGM) is designed. In the module, Improved grouping convolution block (IGCB) is dense connected with other layers to obtain different levels of crowd characteristics, so as to avoid the loss of multi-scale information. In addition, the parameters of IGCB are reduced by group convolution. Then, to overcome the change of illumination, a crowd image enhancement algorithm is designed, which makes the image clear by the average pixel value and adjusting the contrast. Finally, to enhance the sensitivity of the network to crowd counting, a new loss function is proposed, which adds counting loss to the previous pixel space loss to improve the accuracy of crowd counting. The algorithm in this paper has been tested on ShanghaiTech and UCF_CC_50 datasets. The test results show that the algorithm in this paper has better statistical accuracy.

Crowd density estimation method based on floor area

Crowd density estimation is a hot issue in the analysis of crowd abnormal behavior. At present, the crowd density is calculated by the ratio of population and area. However, these methods ignore the influence of monitoring perspective and local crowd distribution in the selection and processing of area. In this paper, we propose a crowd density estimation method based on the floor area, which can accurately estimate the density of low and medium density crowd. Based on crowd density estimation, we propose a new division method of crowd density rank, which can effectively judge the crowd density rank at each moment. The proposed method is executed by the data sets of Mall, Smarty City and USCD. The experimental results show that proposed method can effectively estimate the crowd density value in the low and medium density crowd.

Crowd Counting with Semantic Scene Segmentation in Helicopter Footage.

Continually improving crowd counting neural networks have been developed in recent years. The accuracy of these networks has reached such high levels that further improvement is becoming very difficult. However, this high accuracy lacks deeper semantic information, such as social roles (e.g., student, company worker, or police officer) or location-based roles (e.g., pedestrian, tenant, or construction worker). Some of these can be learned from the same set of features as the human nature of an entity, whereas others require wider contextual information from the human surroundings. The primary end-goal of developing recognition software is to involve them in autonomous decision-making systems. Therefore, it must be foolproof, which is, it must have good semantic understanding of the input. In this study, we focus on counting pedestrians in helicopter footage and introduce a dataset created from helicopter videos for this purpose. We use semantic segmentation to extract the required additional contextual information from the surroundings of an entity. We demonstrate that it is possible to increase the pedestrian counting accuracy in this manner. Furthermore, we show that crowd counting and semantic segmentation can be simultaneously achieved, with comparable or even improved accuracy, by using the same crowd counting neural network for both tasks through hard parameter sharing. The presented method is generic and it can be applied to arbitrary crowd density estimation methods. A link to the dataset is available at the end of the paper.

Multi-scale dilated convolution of convolutional neural network for crowd counting

Growing numbers of crowd density estimation methods have been developed in scene monitoring, crowd safety and on-site management scheduling. We proposed a method for density estimation of a single static image based on convolutional neural network naming Multi-scale Dilated Convolution of Convolutional Neural Network (Multi-scale-CNN). The proposed method employed the method of density maps regression to learn the mapping relationship between single-image and density maps through convolutional neural network. The adopted network structure is composed of two major components to adapt changes of characters scales in crowd images, a convolutional neural network for the general feature extraction and the other is multi-scale dilated convolution for disposing the scale change problem. It is insufficient for currently study that tackled the multi-column or multi-input convolutional neural networks to solve multi-scale problems. Our method utilizes a single-column network to extract features and combines multi-scale dilated convolution to aggregate multi-scale information to address the shortcomings of two networks. The multi-scale dilated convolution module aggregates multi-scale context information systematically by making use of dilated convolution without reducing the receiving domain, thereby integrate the underlying detail information into the high-level semantic features to promote the perception and counting ability of network for small targets. This paper demonstrates the proposed network structure in ShanghaiTech dataset, UCF_CC_50 dataset and worldexpo’10 dataset, and compares the results with numbers of current mainstream crowd counting algorithms, proves that our method surpasses current state-of-the-art methods and has excellent counting accuracy and robustness. The training and testing codes of our method models can be downloaded at https://github.com/doctorwgd/Multi-scale-CNN.

Crowd density estimation in still images using multiple local features and boosting regression ensemble

Crowd density estimation is a challenging research problem in computer vision and has many applications in commercial and defense sectors. Various crowd density estimation methods have been proposed by researchers in the past, but there is an utmost need for accurate, robust and efficient crowd density estimation techniques for its practical implementation. In this paper, we propose a fine-tuned and computationally economical, ensemble regression-based machine learning model for crowd density estimation. The WorldExpo’10 dataset has been used for experimental analysis and model performance evaluation. We extract variety of features in texture-based features such as gray-level co-occurrence matrix, local binary pattern and histogram of oriented gradients, structure-based features such as perimeter pixel and the orientation of pixels, and segment-based handcrafted features from each patch of the image and use an optimum combination of these features as input to the regression model. To achieve optimized memory utilization and faster speed, principal component analysis is employed to reduce the dimensions of the lengthy feature vector. Extensive experiments on different fronts ranging from the model hyperparameter optimization, features optimization and features selection were conducted, and at each step, we selected the most favorable results as input to the optimized model. The performance of the model is evaluated based on two popular metrics, i.e., mean absolute error and mean squared error. The comparative analysis shows that the proposed system outperforms the former methods tested on the WorldExpo’10 dataset.

Crowd Density Estimation of Scenic Spots Based on Multifeature Ensemble Learning

Estimating the crowd density of public territories, such as scenic spots, is of great importance for ensuring population safety and social stability. Due to problems in scenic spots such as illumination change, camera angle change, and pedestrian occlusion, current methods are unable to make accurate estimations. To deal with these problems, an ensemble learning (EL) method using support vector regression (SVR) is proposed in this study for crowd density estimation (CDE). The method first uses human head width as a reference to separate the foreground into multiple levels of blocks. Then it adopts the first-level SVR model to roughly predict the three features extracted from image blocks, including D-SIFT, ULBP, and GIST, and the prediction results are used as new features for the second-level SVR model for fine prediction. The prediction results of all image blocks are added for density estimation according to the crowd levels predefined for different scenes of scenic spots. Experimental results demonstrate that the proposed method can achieve a classification rate over 85% for multiple scenes of scenic spots, and it is an effective CDE method with strong adaptability.

Estimation of crowd density in surveillance scenes based on deep convolutional neural network

As an effective way for crowd monitoring, control and behavior understanding, crowd density estimation is an important research topic in artificial intelligence applications. In this paper, we propose a new crowd density estimation method by deep convolutional neural network (ConvNet). The contributions are two-folds: first, typical deep networks are imported for crowd density estimation. Second, a new dataset including 31 crowd Subway-carriage scenes with over 160K density annotated images is introduced to better evaluate the accuracy of cross-scene crowd density estimation methods. Experiment results confirm the good performance of our proposed method for real-world application.

Recent survey on crowd density estimation and counting for visual surveillance

Automated crowd density estimation and counting are popular and important topic in crowd analysis. The last decades witnessed different of many significant publications in this field and it has been and still a challenging problem for automatic visual surveillance over many years. This paper presents a survey on crowd density estimation and counting methods employed for visual surveillance in the perspective of computer vision research. This survey covers two main approaches which are direct approach (i.e., object based target detection) and indirect approach (e.g. pixel-based, texture-based, and corner points based analysis). This review categorizes and delineates several crowd density estimation and counting methods that have been applied for the examination of crowd scenes.

Video scene invariant crowd density estimation using geographic information systems

Crowd density is an important factor of crowd stability. Previous crowd density estimation methods are highly dependent on the specific video scene. This paper presented a video scene invariant crowd density estimation method using Geographic Information Systems (GIS) to monitor crowd size for large areas. The proposed method mapped crowd images to GIS. Then we can estimate crowd density for each camera in GIS using an estimation model obtained by one camera. Test results show that one model obtained by one camera in GIS can be adaptively applied to other cameras in outdoor video scenes. A real-time monitoring system for crowd size in large areas based on scene invariant model has been successfully used in ‘Jiangsu Qinhuai Lantern Festival, 2012’. It can provide early warning information and scientific basis for safety and security decision making.

Mobile Mapping of Sporting Event Spectators Using Bluetooth Sensors: Tour of Flanders 2011

Accurate spatiotemporal information on crowds is a necessity for a better management in general and for the mitigation of potential security risks. The large numbers of individuals involved and their mobility, however, make generation of this information non-trivial. This paper proposes a novel methodology to estimate and map crowd sizes using mobile Bluetooth sensors and examines to what extent this methodology represents a valuable alternative to existing traditional crowd density estimation methods. The proposed methodology is applied in a unique case study that uses Bluetooth technology for the mobile mapping of spectators of the Tour of Flanders 2011 road cycling race. The locations of nearly 16,000 cell phones of spectators along the race course were registered and detailed views of the spatiotemporal distribution of the crowd were generated. Comparison with visual head counts from camera footage delivered a detection ratio of 13.0 ± 2.3%, making it possible to estimate the crowd size. To our knowledge, this is the first study that uses mobile Bluetooth sensors to count and map a crowd over space and time.

신경망을 이용한 실외 군중 밀도 측정

The population growth along with the urbanization, has caused more problems in many public areas, such as subway airport terminals, hospital, etc. Many surveillance systems have been installed in the public areas, but not all of those can be monitored in real-time, because the operators that observe the monitors are very small compared with the number of the monitors. For example, the observer can miss some crucial accidents or detect after considerable delays. Thus, intelligent surveillance system for preventing the accidents are needed, such as Intelligent Surveillance Systems. in this paper, we propose a new crowd density estimation method which aims at estimating moving crowd using images from surveillance cameras situated in outdoor locations. The moving crowd is estimated from the area where using optical flow. The edge information is also used as feature to measure the crowd density, so we improve the accuracy of estimation of crowd density. A multilayer neural network is designed to classify crowd density into 5 classes. Finally the proposed method is experimented with PETS 2009 images.

Estimation of Crowd Density in Public Areas Based on Neural Network

There are nowadays strong demands for intelligent surveillance systems, which can infer or understand more complex behavior. The application of crowd density estimation methods could lead to a better understanding of crowd behavior, improved design of the built environment, and increased pedestrian safety. In this paper, we propose a new crowd density estimation method, which aims at estimating not only a moving crowd, but also a stationary crowd, using images captured from surveillance cameras situated in various public locations. The crowd density of the moving people is measured, based on the moving area during a specified time period. The moving area is defined as the area where the magnitude of the accumulated optical flow exceeds a predefined threshold. In contrast, the stationary crowd density is estimated from the coarseness of textures, under the assumption that each person can be regarded as a textural unit. A multilayer neural network is designed, to classify crowd density levels into 5 classes. Finally, the proposed method is experimented with PETS 2009 and the platform of Gangnam subway station image sequences.