High-performance software for image processing
Image and video processing is a part of any Machine Vision system. MRTech SK develops proprietary cross-platform software for building full image processing pipelines for that systems. We offer service to implement, customize, and support integrated software solutions for virtually any customer’s hardware. Our cross-platform software has all basic functions for image processing and allows to add any filters, libraries, primitives, SDK which needed for a particular machine vision system.
- Cross-platform software
- Flexible processing which is open for integration with customer’s and third-party application software
- Main thing is that we can achieve maximum performance for the customer’s particular hardware/software configuration
- Acquisition of images and camera synchronization
- Colour images pre-processing
- Rendering on a screen
- Encoding/decoding and streaming
- Format transformations
- Disk writing, etc.
- X86, Apple, ARM
- Linux, Windows, MacOS, Android
- NVIDIA CUDA
- XIMEA API and tools for comfortable use of XIMEA cameras
High-speed GPU processing on CUDA
It’s obvious that GPU is matter-of-course hardware for imaging. If system have or can have NVDIA graphical system, MRTech strongly recommends customers to use outstanding Fastvideo software and we ourselves have mostly done the same thing.
Company Fastvideo designs high performance CUDA Image & Video Processing SDK for image and video processing on GPU. That SDK is a set of separate components which correspond to standard image processing pipeline for camera and non-camera applications.
Fastvideo Lab is also the creator of high performance software for CinemaDNG processing on GPU. Please look link below.
Machine vision algorithms
MRTech team with our partners proposes to implements 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
- Robust real-time object tracking algorithms etc.