• Pravinraj.C
• Sakthiswarup.J.P.
• Venkatesh Krishna. E.

Crowd counting and density estimation is an important and challenging problem in the visual analysis of the crowd. Estimating crowd density or estimating the number of people attending the event can substantially reduce the cost by deploying an exact number of security personnel required for public safety and security Most of the existing approaches use regression on density maps for the crowd count from a single image. However, these methods cannot localize individual pedestrians and therefore cannot estimate the actual distribution of pedestrians in the environment. On the other hand, detection-based methods detect and localize pedestrians in the scene, but the performance of these methods degrade when applied in high-density situations. In our project we have used Faster R-CNN for the detection of pedestrians in the low-to-medium density crowd images that can help in overcoming the drawbacks of existing method.

CNN, R-CNN, UCSD dataset, mean absolute error

"CROWD COUNTING USING SURVEILLANCE FOOTAGE", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 5, page no.h751-h754, May-2022, Available :http://www.jetir.org/papers/JETIR2205899.pdf

"CROWD COUNTING USING SURVEILLANCE FOOTAGE", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 5, page no. pph751-h754, May-2022, Available at : http://www.jetir.org/papers/JETIR2205899.pdf