1 Problem: Anonymous Crowd Monitoring

Monitoring the movement of crowds is a challenging problem and important for making municipal decisions, gathing sales information, and even preventing tragic accidents which can occur when too many people attempt to go in the same direction. Standard approaches such manual counting are too slow and time-consuming, while technical approaches such as cell phone traffic monitoring too invasive.

2 Solution: Drone and Stationary Cameras, Real-time In-Memory Analysis

Drone use for remote monitoring, police activities, and other services has increased rapidly in the past years. Many of these drones are equipped with video cameras producing a constant stream of information. By pairing this streaming output with our Spark Image Layer tools, live feeds from a number of sources can be processed in real-time. Furthermore since the images are being processed in real-time, it is not necessary to save any of the identifying image information alleviated many privacy concerns. Here is an example showing the activity of a street during a running event.