• Shreya Varkuti
• SaikumarThumma
• PranavAddala
• Muni Sekhar Velpuru

People counting in a crowd is a significant challenge in the field of computer vision. Head detection-based approaches are utilized instead of density map-based crowd counting techniques to get more trustworthy crowd counting findings. This is because, in the case of density maps, the right location does not necessarily contribute to the final crowd count. This leads to untrustworthy results, particularly in the case of false positives. As a result, solving the problem of head detection in cluttered settings is a difficult issue. A population count may be required for statistical purposes that aid in the development of marketing plans, or it may be utilized for crowd control in various scenarios. Image processing is a technique of improving or extracting information from a photograph by performing operations on it. In our project, the system's input is a surveillance system's picture/video, which is then separated into image frames. Our proposed system calculates the number of people in the scene using the Faster R-CNN object detection algorithm.

R-CNN, Untrustworthy, False Positives, Surveillance

"People Counting in Crowd: Faster R-CNN ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 9, page no.d639-d644, September-2022, Available :http://www.jetir.org/papers/JETIR2209375.pdf

"People Counting in Crowd: Faster R-CNN ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 9, page no. ppd639-d644, September-2022, Available at : http://www.jetir.org/papers/JETIR2209375.pdf