Abstract
In this paper, we analyze and calculate the crowd density in a tourist area utilizing video surveillance dynamic information analysis and divide the crowd counting and density estimation task into three stages. In this paper, novel scale perception module and inverse scale perception module are designed to further facilitate the mining of multiscale information by the counting model; the main function of the third stage is to generate the population distribution density map, which mainly consists of three columns of void convolution with different void rates and generates the final population distribution density map using the feature maps of different branch regressions. Also, the algorithm uses jump connections between the top convolution and the bottom void convolution layers to reduce the risk of network gradient disappearance and gradient explosion and optimizes the network parameters using an intermediate supervision strategy. The hierarchical density estimator uses a hierarchical strategy to mine semantic features and multiscale information in a coarse-to-fine manner, and this is used to solve the problem of scale variation and perspective distortion. Also, considering that the background noise affects the quality of the generated density map, the soft attention mechanism is integrated into the model to stretch the distance between the foreground and background to further improve the quality of the density map. Also, inspired by multitask learning, this paper embeds an auxiliary count classifier in the count model to perform the count classification auxiliary task and to increase the model’s ability to express semantic information. Numerous experimental results demonstrate the effectiveness and feasibility of the proposed algorithm in solving the problems of scale variation and perspective distortion.
Highlights
With the development of science and technology to a new level, the quality of life of the people has been gradually improved [1]
E goal of the research on the topic of crowd counting and density estimation is to serve the daily needs of people, which is of great practical significance for crowd counting and density estimation in real scenarios [3]. erefore, crowd counting and density estimation can be extended to the following three applications; in real-life scenarios, train stations, airports, large sports arenas, tourist attractions, and large shopping malls are crowded gathering places, and the number of people gathered in these places is usually very large [4]. e staff through the electronic camera equipment monitor such locations in real-time crowd dynamic information, and the relevant technology is used to analyze the potential safety hazards, to nip the catastrophic event in the bud [5]
In the case, where annual holiday travel has become a normal part of the population, it is useful to analyze the flow of people at major tourist destinations in the country to manage road traffic and make adjustments to the overall tourism policy based on the travel preferences and interests of the population at each time of the year [7]
Summary
With the development of science and technology to a new level, the quality of life of the people has been gradually improved [1]. Saon et al were the first to propose a study to learn the linear mapping between local patch blocks and corresponding density maps to achieve population counting, which successfully avoids the shortcomings of detection-based and regressionbased approaches by introducing a new method based on density estimation [17]. Yi et al concluded that the existing population density estimation scheme is computationally expensive and has some drawbacks in processing the number of features and proposed a random forest embedded in the tree nodes as a regression model to combine more extensive and richer image features to realize the counting estimation and the counting strategy have achieved certain results [20]. We use dynamic information analysis to encode the shallow texture features of the same population distributed at different resolutions by using the image pyramid set as input and the feature encoder to enhance the multiscale representation of the counting model. e population distribution density map is generated by the density map regression module, which contains multiple cross-branching subnetworks, and these subnetworks take the convolution of voids with different void rates as the main element to expand the model’s sensory field without increasing the weighting parameters
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
