Tag Archives: lab

Chronos 4k12 and Q12 Hi-Speed Announced!

Krontech the Canadian Hi-speed camera company has released press information for two new global shutter camera releases due to ship in 2024.  While they did excellent work with the Chronos 1.4 720p and Chronos 2.1 HD 1080p slow motion cameras, many users of the platform clamored for more resolution and better image quality.  Enter the new Chronos 4k12 a full 4k Camera capable of 1,397 FPS at 8 bit 4096 x 2160 resolution or at 3840 x 2160
UHD 1,491 FPS.  

To put this in perspective, the Phantom 4k camera does 4k at 1k fps and costs around $80k USD for a starter kit.  This new Chronos camera has some serious punch for the TV, Web, and Film industries that need the extra resolution. We can see many production houses adopting this camera for production without breaking the bank in a compact and fully contained package.  → Continue Reading Full Post ←

Phantom Slow Motion Camera Used to Study Coughing Reach!

Phantom Slow Motion Camera

Schlieren Imaging has always been a very narrow and specialized field of imaging. It can visualize air perturbations in a fluid-like way that can show the reach in this case of someone’s breath and heat dissipation to see if a mask makes a large enough difference in transmission of infected airborne particles compared to no covering.

By using a Phantom VEO4k 990 slow motion camera at 938fps and a speckled background with specialized angled lighting, researchers were able to test a variety of masks while coughing to see the effects.  You can watch the video posted here and also check out the full study available here if you want to dig deeper. → Continue Reading Full Post ←

NVIDIA Slow Motion Interpolation With AI Deep Learning Tech!

NVIDIA Slow Motion Interpolation

NVIDIA has been hard at work on the problem posed by high frame rate interpolation of video data shot on lower fps.  We have had this tech since the late 1990s with the advent of Twixtor and refined over the decades in systems like Twixtor Pro and Adobe’s Optical Flow in After Effects. You are still not getting real temporal detail data since the frames are created by extrapolating velocity and direction vectors plus pixel values between frames to get the result.

We explored this technique in our post on interpolation here and why it is no substitute from a real slow motion camera solution.  NVIDIA’s new method uses machine learning along with 11,000 videos to arrive at a more convincing result. Considering the relatively small sample size we can imagine a future where hundreds of thousands or millions of footage samples are used to generate near flawless interpolation. This technique takes some serious computation and data sets so as of now it is not really ready for the mass market but that could change with the cloud very soon.

NVIDIA Slow Motion Is New But Still flawed:

As you can see in the sample video below the artifacts produced by interpolation are very evident and more so when a fluid or fabric motion is introduced. The human eye can hide some of these in real time playback due to the persistence of vision effect and brain image processing but it is still quite apparent if you look at it witha  critical eye.

Transforming Standard Video Into Slow Motion with AI by NVIDIA:

There is no question this might be the best looking interpolation method we have seen to date but it is still not generating new information that has any scientific value. In other words, you can’t create something from nothing.  Nothing being the estimated values between two distant frames in time.  It sure is a marvel of computation and could really help in getting many more frames where detail is vast and artifacts suppressed but there is no real image captured from a live event.  If you record an explosion or fluid with this technique you will get what the computer estimates should be there and not what actually happened. Any rogue debris or physically distinct motion phenomena will not be there.  This technique is completely useless for education and scientific research.

That said the technique can make your slow-mo videos shot on your phone just a little more interesting even when shot at 30 or 60fps. As with any interpolation technique you can get better results the more frames you give the system.  If you shoot at 1000fps with a shutter of 1/4000 for example you will get the ability to interpolate down to 3k or 4k fps without much artifacting happening.  Then again if you shoot at 4000fps like what an edgertronic SC2+ can do you could interpolate down to 16,000fps without much in the way of artifacting.

We can certainly see a future in which you can upload your lower frame rate footage to the cloud and choose which frame rate you want it at within a reasonable range.   The cloud AI with the Machine Learning algorithms will get better with more and more videos being added to the collection. It is possible to do it with millions of samples instead of only 11,000 videos like the NVIDIA researchers were using in the lab.    The interpolation should get better and better as the computer learns from the added content.

It will also be possible to create footage from scratch by using video parts much like what Google did with Machine image learning to create new art.  What an interesting future it will be.

We are all for better interpolation but do not believe the hype when you are told you may never need a slow-motion camera again. In fact, temporal detail and nature recording cannot be interpolated to generate real information. So you better continue to use your slow motion camera and expect to get one more capable as technology improves and the price continues to lower. -HSC

Nvidia Slow Motion Interpolation Press Release on the Technology Below:

Link to the article here: https://news.developer.nvidia.com/transforming-standard-video-into-slow-motion-with-ai/?ncid=–43539

Transforming Standard Video Into Slow Motion with AI

June 18, 2018

Researchers from NVIDIA developed a deep learning-based system that can produce high-quality slow-motion videos from a 30-frame-per-second video, outperforming various state-of-the-art methods that aim to do the same.  The researchers will present their work at the annual Computer Vision and Pattern Recognition (CVPR) conference in Salt Lake City, Utah this week.

“There are many memorable moments in your life that you might want to record with a camera in slow-motion because they are hard to see clearly with your eyes: the first time a baby walks, a difficult skateboard trick, a dog catching a ball,” the researchers wrote in the research paper.  “While it is possible to take 240-frame-per-second videos with a cell phone, recording everything at high frame rates is impractical, as it requires large memories and is power-intensive for mobile devices,” the team explained.

With this new research, users can slow down their recordings after taking them.

Using NVIDIA Tesla V100 GPUs and cuDNN-accelerated PyTorch deep learning framework the team trained their system on over 11,000 videos of everyday and sports activities shot at 240 frames-per-second. Once trained, the convolutional neural network predicted the extra frames.

The team used a separate dataset to validate the accuracy of their system.

The result can make videos shot at a lower frame rate look more fluid and less blurry.

“Our method can generate multiple intermediate frames that are spatially and temporally coherent,” the researchers said. “Our multi-frame approach consistently outperforms state-of-the-art single frame methods.”

To help demonstrate the research, the team took a series of clips from The Slow Mo Guys, a popular slow-motion based science and technology entertainment YouTube series created by Gavin Free, starring himself and his friend Daniel Gruchy, and made their videos even slower.

The method can take everyday videos of life’s most precious moments and slow them down to look like your favorite cinematic slow-motion scenes, adding suspense, emphasis, and anticipation.

The researchers, which include Huaizu Jiang, Deqing Sun, Varun Jampani, Ming-Hsuan Yang, Erik Learned-Miller, and Jan Kautz, will present on Thursday, June 21 from 2:50 – 4:30 PM at CVPR.

Samsung Exynos Camera Rumor With Super Slow Motion!

Samsung Exynos Camera

The folks at Mirrorless Rumors have a new story based on an anonymous source that claims to know information about a super camera being tested at Samsung’s labs that can do among other things 480fps at 1080p resolution.  Its also claimed to be 4k 120fps ready and using the Exynos 9810 SoC which is reserved for their high-end phones up to now.

These claims are too detailed and too extraordinary to be believed but the Exynos Chip should be able to process all of that data.  The Rumor also states that it will be an APS-C chip with ISOCELL Technology on a stacked design capable of 30.1 Megapixels or 6720*4480px at 30p frame rates. The camera is a prototype according to the source and it is not known if it will be released as a real product in the future.

Samsung Exynos Camera Rumor Highlights:

  • – Full sensor (6720*4480) @ 30fps
    – 5376*3024 @ 60fps
    – 3840*2160 @ 120fps
    – 2688*1512 @ 240fps
    – 1920*1080 @ 480fps
  • – full width of the sensor is used up to 480fps 
  • -Dual Pixel AF System with Phase detection
  • Accelerometer-based shutter
  • H.265 codec
  • Up to 120fps should be full sensor read-out, 2.7K and 1080p at higher frame-rates is 2×2 pixel binning and then down-sampling
  • Full rumor specs here: https://www.mirrorlessrumors.com/good-true-high-end-samsung-aps-c-camera-based-exynos-9810-soc/

Our Take:

When you get outlandish rumors with a list of features that leapfrog everything in the current camera landscape you have to remain a skeptic.  However, the frame rates touted are already possible my much lesser processors out there but they have to be paired with super fast RAM buffers in the several GB range and record for very limited time frames.

Super Slow Motion Movie Taken by 3-layer Stacked CMOS Image Sensor with DRAM by Sony:

A Samsung camera with those specs would need a huge stacked sensor cache module and a secondary memory module in the 16-32GB range for just a few seconds or record time.  We also have to expect a sensor with that many pixels to be full of rolling shutter distortion unless they have implemented a Sony RX like electronic shutter 1/32000 which could be also possible.

What is the Exynos 9810 – Gary explains by  Android Authority: → Continue Reading Full Post ←

Chronos Kickstarter Camera One Year Later!

Chronos Kickstarter Camera

David Kronstein has published a walkthrough video of the Krontech warehouse, assembly installations, and offices located near Vancouver Canada, in what could be described as a rapid expansion of a startup that just a year ago was just coalescing.  With now 337 Chronos 1.4c cameras shipped to Kickstarter backers and also direct purchase buyers; this is a significant number of units for any high-speed camera and we can probably expect that number to increase!

David also goes shares his thanks to the people who helped make the camera project possible and where the company can grow from here. We expect great things from Krontech not that they have shown the ability to mass produce gear that works and as it continues to improve with software releases. We are excited about their future and congratulate them on their success thus far.

Chronos Kickstarter update – One year later Video:

We are eager to see what David and his team of software engineer coders and electrical engineers can cook up now that their first project is maturing.  We would love to see a 1080p camera with a larger sensor and possibly a 4k capable high-speed unit with windowing in the 1080p and 720p modes.  All of this with the touchscreen ability of the Chronos 1.4c which makes it a breeze to run and gun with the camera.

Chronos Kickstarter Camera announces- Open Source Code on Chronos 1.4c:

“At long last, the Chronos Camera application source is now available at the following git repository:

: chronos-cam-app

Currently, we only support Ubuntu 16.04 LTS as a build environment. 17.04 is known to NOT work due to different compiler versions included. You’re welcome to try other environments, please let us know what works and what doesn’t.

Follow the instructions in the repository readme to set up your build environment.

We suggest not doing any significant changes or customization right now. We are in the process of breaking out the low-level camera control into a daemon controlled over D-Bus. This will allow the cam app to talk to the camera seamlessly, whether local or operating remotely over a network connection. Ideally, the exact same application will be able to be compiled to run on the camera or on a PC.

Once you have the application compiling, you can connect to your camera over SSH. Plug the mini-USB port into your computer, and it will enumerate as a USB to Ethernet bridge (serial numbers 00050 and above, earlier cameras need an update, this should be available in the next day or two). You can then log into the camera using root/<no password>

I’m sure there will be many questions, please let us know any problems so we can provide better build instructions.

David”

It is encouraging to see that the source code for the Chronos 1.4c is already up, ready to be explored and played with by enthusiasts.  We expect many new features and improvements added by the community over time with the possibility as well of improved UI and automation.  The Chronos 1.4c code is still maturing with it still in the testing phase to support the majority of the ports on the camera side. The LAN support is taking longer than expected because it requires a host interface to be supported with it as well for it to be useful for the common user.

Releasing the code is a big first step and we can’t wait to see what talented coders are able to do with it.

We are also working on an initial look at the Chronos 1.4c which will have answers to several questions we have been asked. We will look into the quality and shooting experience as well as the continued feature evolution. We received a new camera last week that will allow us to review it without setbacks which caused a delay with an early unit we received. -HSC

For more information about the Chronos 1.4c camera and ordering information please visit:  http://www.krontech.ca –

“Please mention HSC if ordering a camera from any manufacturer, helps us measure the reach of our blog”.

iPhone X Slow Motion Samples 240fps!

Now that the iPhone X has been released to the public, it is time to examine its slow-motion quality when shooting at 240fps 1080p mode.  There is a lot of expectation for what this phone can do but in the end you will get a mild bump in camera quality compared to the iPhone 7 and the exact same camera module as the iPhone 8 Plus.

It is of note that the phone is smaller than the 8 Plus and that battery life should be about the same since the screen is not feeding that extra real estate.  We were very excited about having 1080p finally hitting 240fps on a phone but as you will see; it may not be as good as claimed.  Looks pretty close to 720p upscaled and quite soft which means information is being thrown away to have the high frame rates.

iPhone X Slow Motion Samples 240fps:

iPhone X with Maria Sergejeva / shot 4K 60p & 240fps 1080p by Daniel Peters:

iPhone X 1080p 240fps Cat by Zeck: → Continue Reading Full Post ←