A Deep Learning Approach for Crowd Counting in Highly Congested Scene

With the rapid progress of deep convolutional neural networks,several applications of crowd counting have been proposed and explored in the literature.In congested scene monitoring,a variety of crowd density estimating approaches has been developed.The understanding of highly congested scenes for crowd counting during Muslim gatherings of Hajj and Umrah is a challenging task,as a large number of individuals stand nearby and,it is hard for detection techniques to recognize them,as the crowd can vary from low density to high density.To deal with such highly congested scenes,we have proposed the Congested Scene Crowd Counting Network(CSCC-Net)using VGG-16 as a core network with its first ten layers due to its strong and robust transfer learning rate.A hole dilated convolutional neural network is used at the back end to widen the relevant field to extract a large range of information from the image without losing its original resolution.The dilated convolution neural network is mainly chosen to expand the kernel size without changing other parameters.Moreover,several loss functions have been applied to strengthen the evaluation accuracy of the model.Finally,the entire experiments have been evaluated using prominent data sets namely,ShanghaiTech parts A,B,UCF_CC_50,and UCF_QNRF.Our model has achieved remarkable results i.e.,68.0 and 9.0 MAE on ShanghaiTech parts A,B,199.1 MAE on UCF_CC_50,and 99.8 on UCF_QNRF data sets respectively.

Hajj Crowd Management Using CNN-Based Approach

Hajj as the Muslim holy pilgrimage,attracts millions of humans to Mecca every year.According to statists,the pilgrimage has attracted close to 2.5 million pilgrims in 2019,and at its peak,it has attracted over 3 million pilgrims in 2012.It is considered as the world’s largest human gathering.Safety makes one of the main concerns with regards to managing the large crowds and ensuring that stampedes and other similar overcrowding accidents are avoided.This paper presents a crowd management system using image classification and an alarm system for managing the millions of crowds during Hajj.The image classification system greatly relies on the appropriate dataset used to train the Convolutional neural network(CNN),which is the deep learning technique that has recently attracted the interest of the research community and industry in varying applications of image classification and speech recognition.The core building block of CNN is is a convolutional layer obtained by the getting CNN trained with patches bearing designated features of the trainee mages.The algorithm is implemented,using the Conv2D layers to activate the CNN as a sequential network.Thus,creating a 2D convolution layer having 64 filters and drop out of 0.5 makes the core of a CNN referred to as a set of KERNELS.The aim is to train the CNN model with mapped image data,and to make it available for use in classifying the crowd as heavily-crowded,crowded,semi-crowded,light crowded,and normal.The utility of these results lies in producing appropriate signals for proving helpful in monitoring the pilgrims.Counting pilgrims from the photos will help the authorities to determine the number of people in certain areas.The results demonstrate the utility of agent-based modeling for Hajj pilgrims.