Fast VCR software for GigE cameras from Emergent Vision Technologies
Emergent Vision Technologies is a leading provider of high speed GigE Vision cameras for machine vision, sports technology, volumetric capture and the metaverse, virtual reality imaging applications. Their award-winning area scan cameras feature the latest CMOS image sensors from Sony and Gpixel and are designed to solve today’s toughest imaging challenges while opening the doors for exciting new applications.
In addition to cameras, Emergent Vision Technologies offers comprehensive eSDK, network interface cards, switches, cables, lens mounts, and power and I/O products, making us a one-stop shop for your high-speed imaging needs.
You can test any Emergent Vision Technologies camera with their eCapture Pro software, this is a standard option which is intended for multicamera systems and volumetric imaging applications. To expand image processing capabilities we've developed Fast VCR software with GPU-based image processing to work with EVT cameras and to allow maximum performance and the highest image quality at realtime. You can download FastVCR software from our site and test it with available EVT area scan cameras (8/10/12-bit monochrome or bayer).
Why do we need high performance software for EVT cameras?
If we have a look at the latest SONY Pregius image sensors of the 4th generation, most of them have "high speed" version which means that these image sensors have not only high resolution, but also high frame rate, which is doubled in comparison with the second generation on SONY image sensors. EVT cameras with these image sensors are supplied with high speed 10/25/50/100-GigE interfaces, so they have capabilities to capture acquired frames at the maximum data rate.
That's true not only for SONY image sensors, the situation is the same with Gpixel as well. Modern machine vision cameras offer both high resolution and high fps, so it's quite a complicated task to perform real time processing with high quality and without dropped frames. That is exactly what we can do with FastVCR software which is running on NVIDIA GPU (laptop/desktop/server). In our pipeline we've included high quality demosaicing together with other image processing modules to take into account color science and high performance requirements.
Machine vision cameras capture high quality images at realtime, so they are utilized in industrial applications, streaming and broadcasting, digital cinema, volumetric capture, 3D, AR and VR.
EVT high speed area-scan cameras with 10/25/50/100-GigE interfaces
Fast VCR software for EVT camera control
Fast VCR software: image processing pipeline on GPU
Fast VCR software outputs
Fast VCR performance benchmarks
That software was built with the idea of GPU image processing to be capable of working in high speed camera applications. This is exactly what Emergent Vision is offering for their products with 10/25/50/100-GigE interfaces. That software can work with multicamera systems to process raw frames from all cameras in real time without frame drops. Still, the maximum performance could be achieved with 100-GigE cameras due to their bandwidth. FastVCR software can process RAW images from 65 MPix camera (9344×7000, 8-bit, 70 fps) on the NVIDIA GeForce RTX 4090, the pipeline includes RAW import, RAW-to-RGB transform, color correction, JPEG encoding, storage to SSD. This is just one use case which could show the performance level, which is very high. In general, the performance depends on the complexity of image processing pipeline and utilized hardware (CPU/GPU/SSD, etc). You can get the demo software by request to test your EVT camera and to evaluate image quality, latency and performance.
That software can also work at camera emulator mode to check image processing performance on GPU without having a camera connected to a PC. User can load arbitrary RAW image in PGM format to work with. This is very useful to check time measurements which are available for each image processing module on GPU.
Fast VCR image quality tuning
While working with a camera, the software is capable of storing acquired RAW frames to SSD in DNG format, this is a standard option. If we know color correction matrices or DCP profile for a camera, that info would be embedded into captured DNG images. These DNG images could be processed on any other software like Raw Therapee, Adobe Lightroom or Camera Raw, Dark Table, Davinci Resolve, etc. Such processing could be done to choose better parameters (curves, levels and 3d luts) which could be utilized in the FastVCR software to get better image quality.
Optional image processing modules on GPU
Fast VCR command-line application
Quite often we need to run a software without any GUI, and it could happen in different situations. This is the case for drone applications or for any other task with remote camera control. This is also the case for any long-term unsupervised video recording and streaming.
To meet these requirements, we've developed a CLI application which has all the above features of FastVCR software and it could work without GUI. We are still able to have full control on image sensor and image processing parameters at real time. For video preview we supply our own player with RTSP client or one can use VLC instead. The software is compatible with Windows/Linux and all image processing is done on the GPU.
All the above features are designed on the basis of our CUDA image processing SDK. Now our customers have an opportunity to utilize GPU-accelerated software components in their applications as a part of video processing pipeline. Here you can find other benchmarks for Fastvideo SDK.
Apart from Fast VCR software, we are offering custom software design to build a solution according to customers' requirements. We can implement application-specific modes of operation to solve the task you need. Please fill the contact form below with your project info and send it to us.
Fast VCR roadmap
Blog posts on the subject