Image processing

High-performance software for image processing

MRTech SK presents image processing software and integrated machine vision solutions for industrial, scientific, entertainment as well as embedded applications. We help our customers to build modern, highly demanding video systems by delivering images for their apps with maximum performance and minimum latency for software / hardware configuration selected by customer.

MRTech processing software is a proprietary cross-platform Image Flow Framework (IFF) that’s designed for building standard or customized image processing pipelines for machine vision systems. This software has all basic functions for image processing and allows us to add any filters, libraries, primitives, SDK which needed for the vision system.

This software is compatible with all major hardware platforms used on the machine vision and embedded markets and works with Linux, Windows, MacOS operating systems.

Basic features of the framework

  • Acquisition of images and camera synchronization
  • Color images pre-processing
  • Rendering on a screen
  • Encoding/decoding and streaming
  • Format transformations, disk writing, etc.

 

Compatibility of IFF

  • X86, Apple, ARM
  • Linux, Windows, MacOS, Android
  • NVIDIA CUDA
  • Software interfaces of XIMEA and Basler cameras
  • Other filters, libraries, primitives, SDK

 

The software is supplied under MRTech standard license. In addition, MRTech offers its customers the services of software/system support, processing customization, new and custom processing modules implementation, etc.

Please contact us for more information.

High-speed GPU processing on CUDA

Fastvideo has designed high performance SDK for image and video processing on NVIDIA GPU. That SDK is a set of software components which correspond to standard image processing pipeline for camera applications. This processing components or modules are done completely on GPU and this leads to real-time performance or even faster for the full pipeline.

Fastvideo also offers high speed imaging SDK for non-camera applications: offline raw processing, web, video walls, video transcoding, FFmpeg applications, 3D, VR, AI, etc.

Summary of Fastvideo SDK values:

  • High Performance
  • Low latency
  • Better image quality
  • Reduced TCO for final applications
  • Compatibility with third-party SDKs on CPU and GPU
  • Ease of maintenance, updates and upgrades
  • Availability for full range of NVIDIA GPUs

If you are interested Fastvideo SDK for your system, please request us or Fastvideo directly.

You can also test Fastvideo SDK yourselves using GPU Camera Sample Application – https://github.com/fastvideo/gpu-camera-sample/

Machine vision algorithms

MRTech team with our partners proposes the implementation of a wide range of classical and modern processing algorithms including:

  • Real-time object detection, localization and classification based on state of the art neural net technologies
  • Robust real-time object tracking algorithms
  • 2D human pose tracking, etc.

Please don’t hesitate to request additional information.