Crowd counting model for evacuation scenarios based on a cascaded CNN
DENG Qing1,2, ZHANG Bo3, LI Yihao2, ZHOU Liang1,2, ZHOU Zhengqing1,2, JIANG Huiling1,4, GAO Yang5,6
1. Research Institute of Macro-Safety Science, University of Science and Technology Beijing, Beijing 100083, China; 2. School of Civil and Resource Engineering, University of Science and Technology Beijing, Beijing 100083, China; 3. Xi'an Fire Rescue Detachment, Xi'an 710000, China; 4. Technical Support Center for Prevention and Control of Disastrous Accidents in Metal Smelting, University of Science and Technology Beijing, Beijing 100083, China; 5. Institute of Public Safety Research, Department of Engineering Physics, Tsinghua University, Beijing 100084, China; 6. School of Intelligence Policing, China People's Police University, Langfang 065000, China
Abstract：Accurate crowd counts during evacuations can support real-time optimization of evacuation routes and scheduling of emergency resources. This study estimates the number of occupants in an evacuation passageway by setting a classification level and personnel density together in a cascaded convolutional neural network (CNN) crowd counting model based on analyses of existing methods. The method avoids the loss of image information and over fitting in the convolution process. The model estimates the real-time crowd count in crowded situations by learning the relationship between the number and the position of occupants in the image and by changing the image features. The model was implemented on the PyTorch platform with an identification accuracy for the validation set (612 photos) of 84.2% and for the test set (182 photos) of 83.6%, which shows that this method can accurately predict the number of evacuees in a monitoring screen.
[1] FAN Z Z, ZHANG H, ZHANG Z, et al. A survey of crowd counting and density estimation based on convolutional neural network[J]. Neurocomputing, 2022, 472: 224-251. [2] BHANGALE U, PATIL S, VISHWANATH V, et al. Near real-time crowd counting using deep learning approach[J]. Procedia Computer Science, 2020, 171: 770-779. [3] 吕伟, 李承旭, 马亚萍. 基于GIS位置分配的城市应急避难场所责任区划分[J]. 清华大学学报(自然科学版), 2022, 62(6): 1102-1109. LV W, LI C X, MA Y P. Division of responsibility areas for urban emergency shelters based on a GIS location-allocation analysis[J]. Journal of Tsinghua University (Science and Technology), 2022, 62(6): 1102-1109. (in Chinese) [4] CHEN J Y, XIU S, CHEN X, et al. Flounder-Net: An efficient CNN for crowd counting by aerial photography[J]. Neurocomputing, 2021, 420: 82-89. [5] ZHANG L, SHI M J, CHEN Q B. Crowd counting via scale-adaptive convolutional neural network[C]// Proceedings of 2018 IEEE Winter Conference on Applications of Computer Vision. Lake Tahoe, USA: IEEE, 2018: 1113-1121. [6] LESANI A, NATEGHINIA E, MIRANDA-MORENO L F. Development and evaluation of a real-time pedestrian counting system for high-volume conditions based on 2D LiDAR[J]. Transportation Research Part C: Emerging Technologies, 2020, 114: 20-35. [7] MA R, LI L, HUANG W, et al. On pixel count based crowd density estimation for visual surveillance[C]// Proceedings of IEEE Conference on Cybernetics and Intelligent Systems, 2004. Singapore: IEEE, 2004: 170-173. [8] CHAN A B, LIANG Z S J, VASCONCELOS N. Privacy preserving crowd monitoring: Counting people without people models or tracking[C]// Proceedings of 2008 IEEE Conference on Computer Vision and Pattern Recognition. Anchorage, USA: IEEE, 2008: 1-7. [9] WU X Y, LIANG G Y, LEE K K, et al. Crowd density estimation using texture analysis and learning[C]// Proceedings of 2006 IEEE International Conference on Robotics and Biomimetics. Kunming, China: IEEE, 2006: 214-219. [10] CHAN A B, VASCONCELOS N. Counting people with low-level features and Bayesian regression[J]. IEEE Transactions on Image Processing, 2012, 21(4): 2160-2177. [11] MARANA A N, COSTA L F, LOTUFO R A, et al. On the efficacy of texture analysis for crowd monitoring[C]// Proceedings SIBGRAPI'98. International Symposium on Computer Graphics, Image Processing, and Vision. Rio de Janeiro, Brazil: IEEE, 1998: 354-361. [12] FU M, XU P, LI X D, et al. Fast crowd density estimation with convolutional neural networks[J]. Engineering Applications of Artificial Intelligence, 2015, 43: 81-88. [13] JIANG G Q, WU R, HUO Z Q, et al. LigMSANet: Lightweight multi-scale adaptive convolutional neural network for dense crowd counting[J]. Expert Systems with Applications, 2022, 197: 116662. [14] ZHANG Y Y, ZHOU D S, CHEN S Q, et al. Single-image crowd counting via multi-column convolutional neural network[C]// Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA: IEEE, 2016: 589-597. [15] HUO Z Q, LU B, MI A Z, et al. Learning multi-level features to improve crowd counting[J]. IEEE Access, 2020, 8: 211391-211400. [16] GAO J Y, WANG Q, LI X L. PCC Net: Perspective crowd counting via spatial convolutional network[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2020, 30(10): 3486-3498. [17] CHEN Y, HU S J, MAO H, et al. Application of the best evacuation model of deep learning in the design of public structures[J]. Image and Vision Computing, 2020, 102: 103975. [18] RUBY A U, THEERTHAGIRI P, JACOB I J, et al. Binary cross entropy with deep learning technique for image classification[J]. International Journal of Advanced Trends in Computer Science and Engineering, 2020, 9(4): 5393-5397. [19]邓青, 马晔风, 刘艺, 等. 基于BP神经网络的微博转发量的预测[J]. 清华大学学报(自然科学版), 2015, 55(12): 1342-1347. DENG Q, MA Y F, LIU Y, et al. Prediction of retweet counts by a back propagation neural network[J]. Journal of Tsinghua University (Science and Technology), 2015, 55(12): 1342-1347. (in Chinese)
2023, Vol. 63 
