Software pro vestavěný systém chytré kamery

Software for smart-camera embedded system

software

In order to use the result by another entity, it is always necessary to acquire a license

The licensor requires a license fee for the result

Nosko Matúš, Bc. (FIT)
Záhorský Matej, Ing.
Hájková Gabriela, Mgr. (DFIT)
Honec Peter, Ing., Ph.D. (UAMT)
Hradiš Michal, Ing., Ph.D. (DCGM)
Juránková Markéta, Ing., Ph.D. (DCGM)
Klepárník Petr, Ing., Ph.D. (DCGM)
Klíma Ondřej, Ing., Ph.D. (DCGM)
Musil Petr, Ing., Ph.D. (DCGM)
Nosko Svetozár, Ing., Ph.D. (DCGM)
Smrž Pavel, doc. RNDr., Ph.D. (DCGM)
Zemčík Pavel, prof. Dr. Ing., dr. h. c. (DCGM)

computer vision,machine learning,edge computing

The result of V2 is a service and configuration software, which is configured through a web interface. Within the EmIC project, V2 is deployed on an NVIDIA Jetson computing module, which is part of the V1 result. V2 consists of several modules including functions for device configuration, data reception from cameras, and an environment for running neural networks. In the case of applications running on V1, the runtime environment is based on the TensorRT framework, which enables fast and efficient data processing using neural networks. The neural networks themselves used in V2 are trained and optimized by V3 software. This software is designed to support the transfer of artificial intelligence algorithms to embedded systems, allowing real-time data processing.

Podléhá obchodnímu tajemství

EmIC - Embedded Intelligence for Smart Cameras with Traffic and Industrial Computer Vision Applications, TAČR, 2. veřejná soutěž - Program průmyslového výzkumu a experimentálního vývoje TREND, FW02020040, 2020-2023, running

Computer Graphics Research Group (RG GRAPH)

Department of Computer Graphics and Multimedia (DCGM)