Computer Vision and Convolutional Neural Network for Dense Crowd Count Detection

Crowd counting is an approach for the process of counting the people in an image. Extensive studies on crowd detection and density estimation are being carried out for crime prevention, crowd irregularities, public safety, visual monitoring, and urban planning. Approaches to detect crowd count are available in the literature; however, available algorithms could not detect the accurate number of people. Therefore, in the current work, computer vision techniques in fusion with convolutional neural networks (CNNs) are employed to produce impressively precise estimates. The proposed work will precisely detect count of the persons in an image using computer vision and CNN. Pattern recognition techniques are employed for crowd count detection by using face detection. However, detecting a face in the crowd is complex as inconsistency prevails in human faces comprising of color, pose, expression, position, orientation, and illumination. Congested Scene Recognition Network (CSRNet) attains 47.3% lower mean absolute error compared with existing techniques. The current work is also extended to various intended applications such as vehicles. The experimental results reveal that CSRNet has shown significant improvement in the output by 15.4% better MAE than existing contemporary approaches.