Abstract
The current crowd counting tasks rely on a fully convolutional network to generate a density map that can achieve good performance. However, due to the crowd occlusion and perspective distortion in the image, the directly generated density map usually neglects the scale information and spatial contact information. To solve it, we proposed MDPDNet (Multiresolution Density maps and Parallel Dilated convolutions’ Network) to reduce the influence of occlusion and distortion on crowd estimation. This network is composed of two modules: (1) the parallel dilated convolution module (PDM) that combines three dilated convolutions in parallel to obtain the deep features on the larger receptive field with fewer parameters while reducing the loss of multiscale information; (2) the multiresolution density map module (MDM) that contains three-branch networks for extracting spatial contact information on three different low-resolution density maps as the feature input of the final crowd density map. Experiments show that MDPDNet achieved excellent results on three mainstream datasets (ShanghaiTech, UCF_CC_50, and UCF-QNRF).
Highlights
As the phenomenon of crowd congestion is becoming serious, safety- and security-oriented tasks– such as public safety control and traffic safety monitoring– face huge challenges
In the field of crowd counting, testing metrics that are produced by benchmarks include mean absolute error (MAE), mean square error (MSE), and root mean square error (RMSE)
Di2, where N represents the number of test images; di represents the actual number of test images pi by artificial marks; di represents the number of people estimated by pi through the network, and it is obtained by integrating the corresponding crowd density map
Summary
As the phenomenon of crowd congestion is becoming serious, safety- and security-oriented tasks– such as public safety control and traffic safety monitoring– face huge challenges. Deep-learning-based methods are more applicable at present since their process eliminates manual efforts and can analyze crowd aggregation accurately and quickly. Crowd estimation at the pixel level through the crowd distribution density maps has achieved tremendous progress. A crowd density map is a kind of image label that can reflect the distribution of crowd heads by processing the head coordinate value through Gaussian convolution. The crowd in images mostly involves different distribution modes and aggregation features. E crowd distribution density map can obtain more accurate spatial information and more comprehensive image features in dense scenes, which brings about that the density estimation method can be applied to vehicle control, bioecology research, and other cross-domain fields to share the advancement of this technology
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.
