Image and Video Stabilization with Amped Five

Shaky video is something encountered pretty frequently. Stabilizing a shaky camera is something that can be accomplished in some other software. But what about other type of motion or stability? For stabilizing something beyond just a jittery cameraman, what do you do? This is why Amped Five has three different types of stabilization to work with multiple types of problems. Here is a quick rundown for these filters found in the Stabilization filter group:

1) Local Stabilization

What it does: Use for tracking an object or a subject and keep it steady in all the frames (license plates, faces, etc.). The subject or object is in motion.

When to use it: It’s the best one to use as a preprocessing step for frame averaging (typical in CCTV cases). When it works, it the fastest and the most precise method. Within the filter’s settings, the user can have total control when they use the various tracking settings discussed below.

Limitations: The object of interest must differ only in position (not zoom, rotation or changing angle). The only downside is that the object of interest must be present in all the frames, otherwise the stabilization calculations do not work correctly.

2) Global stabilization:

What it does: Use to globally stabilize a whole scene. Since it does not require any specific object to be stabilized and to be present in the whole scene, so it requires the least amount of interaction.

When to use it: This is the best choice for stabilizing shaking video like those coming from camera phones, police operations, helmet mounted cameras etc. where the camera movement is the issue.

Limitations: The downside is that this method is less precise than local stabilization but works in more situations, like when the camera is panning a scene.

3) Perspective Registration

What it does: It is like local stabilization but allows the stabilization of any kind of movement, even perspective changes with subjects. It is designed to work only on planar objects like license plates.

When to use it: This is typically used as preprocessing step for frame averaging in CCTV video: an example application is the frame integration of a car approaching a dome camera.

Limitations: it’s mostly manual, so it needs the user to set four points for all the frames, but the result can then be automatically optimized by the algorithm

How to use Local Stabilization.

Since Local Stabilization has the most frequent application, here is how to optimize it using the standard tracking and selection settings available in all tools.

For the Local Stabilization the most useful modes are Static Tracking and Dynamic Tracking, but here I will describe all the modes. The description is relevant to all local filters: the difference is that, while all the other filters will move the selection around the target, in the Local Stabilization filter the selection will be kept steady and the rest of the image will be "moved around" to keep the tracked area in the same position.

These are the possible settings:

· Whole Image: The entire image is filtered in all the frames.

· Static Selection: The selected area will be the same in all the frames.

· Static Tracking: The selected area will be tracked in all the frames with the same reference

o For example: If you set frame 10 with selection [points 100, 100, 40, 40], as a reference the, algorithm will try to find in all the other frames the best matching area to the reference one. The usage depends on context where it can be less than ideal if the content of the tracked area changes a lot (like tracking a person who keeps turning his head), the reference area won’t be correct anymore due to context changes.

· Dynamic Tracking: The selected area will be tracked in all the frames updating the reference after every frame.

o It is like Static Tracking, with the difference being that the tracked area will be updated after every frame.

o Even if the subject changes, and it does so gradually, and the stabilization will continue to work. That is until the tracking is wrong for one frame, it will be wrong in all the subsequent frames. This is dependent on the rate of change for the subject. For something like a car or person moving towards a camera, it is generally fine.

o For something moving very quickly, it can be problematic since every frame depends on the previous the whole video (or the selected part must be pre-processed).

o In general this works more often than Static Tracking but is a bit less precise.

o Since Five is so fast to work with, we suggest to first try Static Tracking, and then try Dynamic Tracking.

· Manual Tracking: This method allows the most amount of user control over the tracking and stability. The user can add different selections in various frames.

o The selection of intermediate position will be calculated simply interpolating the set reference frames (regardless of the content of the area).

Please note that all selection support the possibility to add several reference frames:

· If there is only one reference: it will be used for all frames.

· If there are two or more references, all intermediate positions will be calculated accordingly. Tracking will be disabled before the first reference frame and after the last reference frame.

· If you want to interrupt the tracking only for some frames of the video add an empty selection to the frame where you want to start the interruption.

The new Write Timestamp filter in Amped Five

Last week we released a new update with the 64 bit version of Amped Five. Today we launched another update with some other improvements and a few new tools.

One of the features that we just updated is the Write Timestamp filter.

Sometimes when you export a video that comes from a proprietary DVR format from CCTV you may lose the date and time information that was impressed on the native format when playing it.

With the Write Timestamp filter you can manually add back the date and time information so you can quickly locate events of interest at known times.

How does it work? Basically what you need is just to insert the know date and time for two frames of the video and the timestamp for all the others will be calculated automatically.

Usually the simplest solution is to put the date and time of the first and of the last frame as reference, as this is the easiest way, but you can put whatever you want from whichever frames you choose.

It’s very important to understand that the calculated time will be only estimated as a hypothetical time for reference and won’t have any scientific forensic value. Surveillance videos usually don’t have a perfectly constant frame rate and thus the calculated timestamp may be off by a few seconds or more. The system obviously will be completely wrong for videos activated by motion detection or with variable frame rate, which will bring interruptions and discontinuities in the density of frames with respect to time.

For this reason we decided not to print the timestamp on the actual pixels of the video, but only to display it on the Filter Settings panel. This solution also avoids the risk of covering some part of the image with the timestamp.

Update Five now to get the new features!

Amped Five now available in a 64 bit version

Today we just release a new major update to Five. As always all of our customers who have an active update/support plan, or who purchased Five within the past 12 months, can freely download the update. (If you haven’t tried it, go to Help>Check for Updates Online)

There are several new improvement that will be highlighted in the coming days, but the major one is that Five is now available in both 32 and 64 bit flavors.

The good thing is that when you install Five you will get both the version at the same time if you have a 64 bit operating system. By default the installer will create a link to the 32 bit version, but you can easily modify the link or create a new one changing the path from bin32 to bin64.

We preferred to leave the 32 bit version as default because of codec compatibility. Most of the codec packages that users install by default on systems are in 32 bit version and if you don’t install the codecs specifically for 64 bit you won’t be able to decode some file formats. This is just an issue inherent with all the proprietary formats, so we designed things this way so no loss of compatibility is risked with this new version.

So, what are the benefits of a 64-bit version? Mainly an improvement in performance and the possibility to use more than 3 GB of RAM (limitation in Windows for 32-bit OS). You may have noticed with previous version of Five that when you were working at big images (like the ones coming from modern digital cameras)after adding a few filters the memory could get full, thus limiting new processing steps and filters.This was especially true with memory intensive filters like the ones for image deblurring.

Now, with the 64 bit version, Five is able to use as much memory as is available on your system. So huge files aren’t a problem.

Both the 32 and 64 versions should work fine in most of the cases but the general advice could be the following:

· Use 32 bit version to work on CCTV videos, were support for same exotic codec available only for 32 bit operating systems may be required and where memory is not usually an issue. The quality is generally poor to begin with, so that is why we’re trying to clarify it, right?

· Use 64 bit version to work on digital camera and high definition images, where there is the risk of needing more than 3 GB of RAM. This is very useful for latent prints, crime scene photos, high quality images, etc. Now there is no limitation of memory size, so go as big as you need to go.

That’s NOT all folks… there are also some other improvements under the hood and in ease of use. We’ll go over more in the next days, or just update Five and see for yourself.

Amped Milestone integration and photo authentication at NATIA.

We’ll be present as exhibitors at NATIA Pacific Chapter Meeting in Pasadena, CA, USA on April 16.

Jim Hoerricks, from the Forensic Video and Image Analysis blog, will present two technical workshops about some special features of our products.

1. FVA of native IP cam (Milestone) footage with AmpedFIVE (2 hours)
With the roll-out of IP cameras, it goes without saying that some of the footage will need to be enhanced or clarified. This session will illustrate how Amped FIVE can work with the native Milestone files that come from cameras like Axis (the most popular cameras in the law enforcement arsenal) as well as work with the live feed, dialing into the camera/server directly and performing enhancements to the live feed.
2. Authentication of digital images (2 hours)
Programs like JPEG Snoop and FourMatch are based on a database of camera signatures. Thus, they are not effective in authenticating images from social media, DVRs, or deleted images carved from cell phone data dumps. Contextual authentication – has the image been altered through cut/paste or delete – is at the heart of most requests for authentication of digital images in our courts. This session will illustrate the many domains of contextual authentication using Amped’s Authenticate.

Read more on Jim’s blog.

You can get more info on Amped Five integration with Milestone XProtect on this technical paper.