Developed by Skylark Labs, a company founded by NITW alumni, the drone uses deep supervised learning algorithm that identifies people on the roads by bounding a box around them. The high-definition cameras set-up on the drones detects position of humans present at various locations and divides them into grids.
“The system detects humans even from a long range (up to 1000ft.), which is helpful to detect large numbers of people in a single frame. This decreases monitoring of drones constantly by zoning in for humans being detected,” read a press release issued by NITW.
The system accurately detects humans based on their closeness to others. For instance, a person is placed in a green box if he is not surrounded by any other human nearby. Whereas, a group of two on motorbike are placed in red boxes indicating that they are close to each other, placing them in an unacceptable category (distance
“Once a human has been detected violating the curfew, SMS alerts are sent right away to mobile phones of the police officers present closest to the spot regarding the location of the suspect and its corresponding real-time video. The location gets captured by the drone itself,” read the release.
The software uses robust deep Learning algorithms to solve real-world problems, with high accuracy and real-time processing which is really helpful for the current state of pandemic. The police can get greatly benefit from this system constantly monitoring people and at the same time can stay safe from exposure to the deadly virus.