RSS
Логотип
Баннер в шапке 1
Баннер в шапке 2

Central Research Institute Cyclone: Program for detecting suspicious objects by drones

Product
Developers: Cyclone TsNII
Date of the premiere of the system: October 2022
Branches: MILITARY INDUSTRIAL COMPLEX

2022: Creating a program

October 26, 2022 became about the creation that Russia software helps drones look for mines and unexploded ordnance. This is a development (Central Research Institute "Cyclone" part of the holding Roselectronics"").

A self-learning program that can be used in infrared and television surveillance complexes, as well as in optical drone systems for detecting mines, helps to identify suspicious objects, remember them and subsequently identify new targets, comparing them with already "familiar" images. The system is capable of accompanying low-contrast and small-size objects in any spectrum range. The algorithm is resistant to camera turns and jerks, changes in the angle and scale of the image, the developers say.

In Russia, created software to help drones look for mines and unexploded ordnance

The program can interact with a neural network performing initial target detection for subsequent tracking. Also, an object for tracking can be set by an operator by highlighting its image on the screen. When a suspicious object is first detected, the tracker begins tracking it by video from the drone. This makes it possible to verify the goal from various angles for final confirmation by the neural network of its danger. 

According to the developers, the program does not require significant computing resources: the power of the processor used in portable devices is enough to simultaneously track four objects in real time at a frame rate of at least 25 per second. 

The algorithm stores images of a constantly changing object in its memory and, when a new target is detected, identifies it by comparing the image with the images it has in the database. Specialists are ready to adapt the program interface to the needs of a specific customer and configure the algorithm in accordance with the client's requests, said Peter Kovalev, General Director of the Central Research Institute "Cyclone."