10/03/2024

OBS Studio - How to enable the "Video Capture Device" as a source USBHDCAP

Open the "video capture device" Source, properties.

1. Change [Audio Output Mode] from these:

Output desktop audio (DirectSound)

Output desktop audio(WaveOut)

2. Change [Audio Output Mode] to this:

 Capture audio only

This is not what it seems, selecting one of the others pipes the output of the device through a mix with the other source; either "Desktop audio" DirectSound or WaveOut .. which I suspect are Desktop1 Desktop2

If you select one of those then you disable the ability to enumerate and use the "Video Capture Device" as an audio source in the "mixer" panel of OBS.

Instead "Capture audio only" means, do not pre-process it and mix with anything else, pipe it straight into OBS as an independent source. It literally means "leave it alone" do not "do anything to it" simply "present it".

You CAN still check the box [x] User custom audio device, and "must" use CY3014USB, Analog 01 WaveIn to connect the video capture device to the OBS mixer.

This "might" seem like it would disable the ability to capture [both] video and audio to a [Start Recording] session. It DOES NOT ! 

Any Streaming or Recording includes [both] video and audio.

This is a very BIG deal.. it explains the original interpretive conceit with OBS and why its so hard to use for most people.



OBS Studio - Monitor silent with Startech USBHDCAP device "fix"

Here is how to fix a video capture device that records video and audio, but does not play sound while recording.

1. Click > [Settings] in Controls Panel (Lower right)

2. Click "Advanced" in Left Ribbon panel

3. Click [Audio] > Audio Monitoring Device [drop down]

Select a device other than "Bluetooth Headphones (2- Bluetooth Audio)" 

Example:

Select "Bluetooth Headset (2- Bluetooth Audio)"

4. Click [Apply] in lower right corner

5. Click [OK] in lower right corner


The A2DP Profile for some reason on OBS 21.1.2 (64 Bit) does not down sample the 48 Khz Line Input for the CVBS Composite or S-Video Inputs properly. When it defaults to "Default" or "Bluetooth Headphones (2- Bluetooth Audio)" the Monitoring audio cuts out and goes silent. Also the "Default" takes out not only the OBS video capture source, but any other Audio source on the Desktop, including Browsers playing video or other Application sources.

I suspect the source code for OBS 21.1.2 may not be initializing the windows mixer properly or not handling down sampling properly.. or the A2DP profile is just not working properly.

In any event the change is immediate and does not require restarting the application and all other audio sources are mixed and can be heard. Although with this video capture device, the video device audio input is not selectable and it captures the Desktop mix instead

Also a "Custom" audio device that selects the CY3014 device must be used or there will be no audio capture or monitoring.

6/30/2024

How to Remove Soft Touch Paint, quickly and safely

In the Early 2000's it seems everything Black was painted with a soft touch paint. By the 2020's it had degraded into a gummy sticky material that seemed almost impossible to remove even with IPA alcohol.

It turns out its actually not a paint, but a transparent "coating" that is sprayed over the top of black plastic pieces. I think its some type of silicone, making it generally hydrophobic.. so things like scrubbing tile cleaner or other things won't work to remove it.

But quite simply the LAVA hand soap is (not) electrically neutral, it has a clay mineral called Lanolin and Pumice, which combine to penetrate, lift and isolate it and allow it to be "Washed" away.

I've tried this on an old Mevo hand camera, a Diamond Multimedia Game Capture box, and a Toshiba RD-XS54 DVR.. and it works every time.. and I had tried nearly everything for years.

Anything that tends to melt plastic like MEK or Nail Polish Remover.. just makes the situation worse.. blending the silicon with the melted surface.

But using a soaped up rag with LAVA hand soap quickly and simply removes only the silicone layer.

Since this was a transparent "film" and not really a paint.. any pictures, labels or symbols that appear to be part of the paint, were actually under neath the "Soft Touch Paint" and remain after the gummy sticky film is removed.

Your mileage may vary.. not every case will be identical to mine.. but give it a try cautiously.

It really seems like "magic".



6/10/2024

When is 4:2:2 not 4:2:0

4:2:2 is generically interpreted to be 4 samples luma, 2 chroma cr, 2 chroma cb but ignores the field based nature of most video capture

4:2:0 is a somewhat interpretive acknowledgement of the loss between fields interpostively

4:2 is Luma:Chroma over all where ::0 is the alternate state or field where no chroma subsampling takes place and the previous chroma subsampling for the associated field is substituted for the same or similar pixels which are going to take the place of a chroma sample for both fields combined.

 You can think of this as loosing information when the two fields are "smushed" together, or taking advantage of the similar or identical nature of the chroma sample and removing the redundancy.

Some have interpreted this as "skipping" a chroma sample inter field, or only taking a chroma sample every other field on the odd or even field.

This can be true or partially true for MPEG2 in certain cases, unless fields are retained, in which case it returns to 4:2:2 as each field much have its own chroma subsampling field to remain a part of the video stream.. but again this may require a software codec to deal with the extra information.

Whether any hardware codec would expose fields or retain their 4:2:2 format remains to be seen.

DV is "de-interlaced", MPEG2 can be "de-interlaced" or "not de-interlaced"

The DV video format is "progressive" in the sense it is frame and not field based. So a type of de-interlacing does occur as part of the digitization process.

MPEG2 was a more robust standard, in that it was a choice whether to de-interface the fields and then compress or retain the fields and compress. Less motion artifacts could be expected by avoiding de-interlacing. Depending on whether a hardware encoder like a standalone device or software encoder were used might allow this choice or not.

It remains to be seen if DVRs on the low or high end retained fields for capture and playback, varied between brands and models or simply defaulted to de-interlacing.

There are "Profiles" related to bit-rates and features. But I don't think those allowed choosing the de-interlace feature.

MPEG4 and other Professional codec also allowed this choice but its not something people often seek control over.. or understood.

Until we reach a technology can take field based information and infer a depth or object oriented interpretation of the image information and interpolate physics between frames its unlikely de-interlace technology will have improved much. Recent improvements in self driving cars appear to be approaching this level of technology but trickling down to the generic video market will probably take another ten years into the 2030s.

6/07/2024

140/400 is 0.35 still less than 0.5 of 4:2:2, so S-VHS with s-video on MPEG2 is still over kill

Kind of explains why HDV and D-VHS devices standardized on the MPEG2 digitization format with 0.15 overhead before reaching 4:2:2

They were much smaller than DV files or DV storage requirements, and still had far more chroma resolution. For that time.. they were future proof.

Only once the physical line lengths and aspect ratios began to change did they finally have to abandon the MPEG2 720x480x180 formats afforded by 4:2:2 for greater pastures.

80 / 240 is 0.33 just over 25% so DV may be barely enough for Standard Video if using s-video

 I would still be favoring MPEG2 if using s-video with Standard VHS "just in case" and for the convenience of a dedicated capture platform like a DVR, especially one that you could directly off load the video from in MPEG-TS format.. which is more tolerant of dropouts

A full conversion to MPEG-PS for burning DVDs would be likely to introduce more compromises to maintain the stream rate required by those playback formats.

Again, MPEG4 would be preferred to that.. if available.. in a dedicated device, native operating system players will not be encumbered by long expired licensing deals for MPEG2 playback codecs and more likely to be supported by minimally featured playback devices and programs going forwards.

However, MPEG2 capture devices like DVRs are more likely to have dedicated Time Base Correction and Frame Stabilization which is now no longer features included in a purely digital age.

I am biased.. since stumbling on to the ability to offload MPEG2 TS data directly from some of the most premium DVR capture devices ever made.. shortly before they were abandoned and shelved or consigned to the dump.. but their convenience and usage demonstrated by their popularity for about ten years says a lot about their overall effectiveness.

If an MPEG2 capture device like a DVR were used as a pass-thru device to feed an MPEG4 capture device for digitization, that might be the most effective combo and future proof.. but the odds of acquiring and combining them without introducing impedance mismatches or other signal glitches and coordinating them over a long period of time would seem cumbersome.. if only theoretical.


S-Video is not S-VHS, but it can roughly double the Chroma resolution

 

estimate the improvement in chroma resolution for Standard VHS and S-VHS when using s-video.

While S-Video (Y/C) connections can significantly improve video quality compared to composite video connections for both Standard VHS and S-VHS formats, the extent of improvement in chroma resolution specifically can be challenging to quantify precisely. However, we can provide a rough estimate based on typical performance characteristics:

  1. Standard VHS with S-Video:

    • Standard VHS typically offers around 30-40 lines of horizontal chrominance resolution when using composite video connections.
    • With S-Video, the separation of the luminance and chrominance signals reduces color bleeding and improves overall image clarity. It can roughly double the chrominance resolution, providing an estimated improvement of around 60-80 lines of horizontal chrominance resolution.
  2. S-VHS with S-Video:

    • S-VHS offers an improvement in chrominance resolution over Standard VHS, but the exact increase can vary.
    • With S-Video, S-VHS recordings benefit from the same advantages as Standard VHS, but with a higher starting point for chrominance resolution. Therefore, the improvement in chrominance resolution with S-Video for S-VHS may be less dramatic compared to Standard VHS, but it still enhances overall color fidelity and sharpness.

Please note that these estimates are rough approximations and actual performance can vary depending on factors such as tape quality, playback equipment, and recording conditions. Additionally, the perceived improvement in video quality with S-Video connections may also depend on individual preferences and viewing conditions.

DV versus MPEG2 when converting VHS Tapes to Digital

DV uses 4:1:1 chroma subsampling. 

I had an intuitive grasp that DV would be sufficient if not overkill for converting Standard VHS tapes to digital files. I could prove it in numbers, but people continued to preach 4:4:4 was better. - I don't think oversampling the same material that far.. produces any better results and makes handling the converted files that much less likely to be copied or replicated through history.

S-VHS is a superior chroma subsampling on tape, which exceeds that of DV 4:1:1 chroma subsampling, but does not exceed that of MPEG2 4:2:2 subsampling. And direct broadcast signal conversion to digital would be even closer to 4:2:2 which is probably why it was selected for Tivo and other early Broadcast TV digital capture solutions. 4:4:4 was still not warranted however.

A more serious choice is to upgrade to Progressive or retain Field based capture and allow some future algorithm the choice to de-interlace video that has not yet been invented.. possibly even some sort of speculative A.I. de-interlacing method  that minimizes the information loss and artifacts created by early de-interlacing methods. 

Choosing how to archive video tape so that it survives into the future and holds on to as much information as its possible to capture when crossing from analog to digital is a balancing act.

The most important being Luma and Field capture then considering things like chroma sampling or whether to subsample.

In this case using 4:1:1 on Standard VHS (is not) subsampling when converting from Analog to Digital, it is over sampling.

In this case using 4:2:2 on Super VHS (is not) subsampling when converting from Analog to Digital, it is over sampling.

MPEG2 does compress Luma and Chroma for a smaller file size versus DV by a reduction in information in the noise zone of a progressive or field image.. but it is a choice.. and may make handling large video files less of a problem as is the case with DV files.

Given the success of MPEG2 at the time, it was a reasonable tradeoff and quite a success.. judging by the DVD video market of that time.

MPEG4 was introduced as a better version of MPEG2 initially for streaming and low bit rates, but later upgraded in silicon as a higher bit rate replacement for MPEG2 and does not suffer many of the artifacts of an MPEG2 video and is not license encumbered as MPEG2 became. 

Today MPEG4, overall is probably superior to DV or MPEG2 if given a good source to convert. 

However as media degrades, if a DV or MPEG2 conversion is already available, it may make more sense simply to retain that or consider placing it in an MPEG4 container form and format for playback that can conjugate but not re-encode the original digitization process without introducing new artifacts or quality degradation. this when the original source is no longer available, or had degraded further than when the first digitization methods were used.

 


An A.I. perspective on S-VHS versus 4:2:2 sampling

 is S-VHS closer to 4:1:1 or 4:2:2 ?

 

S-VHS (Super VHS) is an improved version of VHS that offers better video quality, especially in terms of resolution and color fidelity. While it's still an analog format, S-VHS does offer enhanced chroma resolution compared to standard VHS.

Here's how it compares to digital chroma subsampling formats like 4:1:1 and 4:2:2:

S-VHS Color Resolution

S-VHS improves upon standard VHS in several ways, including better color resolution. While it still uses a composite video signal,it provides an improvement over VHS in terms of resolution, offering around 400 lines of horizontal resolution for luminance and a slight improvement in chrominance resolution, though specific figures for chrominance resolution in S-VHS can vary. Some estimates suggest an increase to around 60-70 lines of horizontal resolution for chrominance.

Comparison to Digital Chroma Subsampling

When comparing to digital formats:

  • 4:1:1:

    • Luma: 720 pixels per line.
    • Chroma: 180 pixels per line (a quarter of the luma resolution).
  • 4:2:2:

    • Luma: 720 pixels per line.
    • Chroma: 360 pixels per line (half of the luma resolution).

Approximate Digital Equivalent

Given the improved chroma resolution of S-VHS compared to standard VHS, it falls somewhere between 4:1:1 and 4:2:2. Here's why:

  • Chroma Resolution: While S-VHS offers better color resolution than standard VHS, it still falls short of the full 4:2:2 chroma resolution used in digital formats. However, it provides more detail than a mere quarter of the luma resolution, which is characteristic of 4:1:1.

Summary

S-VHS is closer to 4:2:2 in terms of effective color resolution compared to 4:1:1. While it doesn't match the full 4:2:2 resolution, its enhanced chroma resolution surpasses the quarter-luma resolution typically seen in 4:1:1 chroma subsampling. Therefore, S-VHS is closer to 4:2:2 than to 4:1:1, albeit still being an analog format with its own characteristics.

 

An A.I. perspective on Standard VHS versus 4:1:1 sampling

is standard VHS closer to 4:1:1 or 4:2:2 subsampling?

Standard VHS video quality does not directly correlate to digital chroma subsampling formats like 4:1:1 or 4:2:2 because VHS is an analog format. However, we can make an approximate comparison based on the effective color resolution and the way VHS handles color information.

VHS Color Resolution

 VHS, an analog format, uses a composite video signal where the luma (brightness) and chroma (color) signals are combined. The color resolution of VHS is significantly lower than its luma resolution. Here’s a general comparison:

  • Luma (Y): VHS can resolve around 240 lines of horizontal resolution.
  • Chroma (C): The color resolution of VHS is much lower, typically around 30-40 lines of horizontal resolution.

Comparison to Digital Chroma Subsampling

When comparing to digital formats:

  • 4:1:1:

    • Luma: 720 pixels per line.
    • Chroma: 180 pixels per line (a quarter of the luma resolution).
  • 4:2:2:

    • Luma: 720 pixels per line.
    • Chroma: 360 pixels per line (half of the luma resolution).

Approximate Digital Equivalent

Given the much lower chroma resolution of VHS, it is closer to 4:1:1 chroma subsampling rather than 4:2:2. Here’s why:

  • Chroma Resolution: The color resolution of VHS is significantly reduced compared to its luma resolution, similar to how 4:1:1 reduces chroma resolution to a quarter of the luma resolution.

Summary

While VHS does not use digital chroma subsampling, its effective color resolution is more similar to the 4:1:1 digital format. The 4:1:1 subsampling method reduces chroma resolution significantly, akin to the low chroma resolution of VHS. Therefore, standard VHS is closer to 4:1:1 than to 4:2:2 in terms of effective color resolution.

 

5/28/2024

Tracking Roth and Traditional contributions in One Retirement Account

 I am new at trying to use the "old" way and found it confusing from the Threads available.

Simply, in as few words as possible;

  1. Quicken lets you set up a new account of type 401k (x) tax deferred.
  2. When you setup a paycheck using
  3. [BILLS & INCOME] tab > [Add v] button > "Add Income Reminder"
  4. Looking down at the bottom of the dialog click on "Paycheck setup wizard"

Choose (x) Gross amount > [Next] button

Company name: "myemployer" > [Next] button

Fill out the sections for your paycheck, adding a

[Add Pre-Tax Deductions] > Other Pre-Tax Deduction

  1. Name: Broker - Traditional
  2. Category: replace the word "Salary" with the "[401k Account]" you set up, type but ignore the dialog that pops up > "[401k Account]/Traditional" and press enter, press [OK], ignore the [New Tag] dialog and press [Save]
  3. Amount: enter an amount if you like, press [OK]

[Add After-Tax Deductions] > Other After-Tax Deduction

  1. Name: Broker - Roth
  2. Category: replace the blank field with the "[401k Account]" you set up, type but ignore the dialog that pops up > "[401k Account]/Roth" and press enter, press [OK], ignore the [New Tag] dialog and press [Save]
  3. Amount: enter an amount if you like, press [OK]

When a paycheck is "Action > Entered" from Bills&Income, "tagged" contributions will be placed into the same 401k account; you can tell from their tags their contribution type.

My Retirement Account does not track contributions separately until withdrawl, it lumps them into a ratio between the total of each contribution type which adds up to 100 percent.

On the day of withdrawl the current contribution ratio is used to calculate the available funds of each type from the total of the balance in the account.

A report to find out the current contribution totals can be run from;

Reports > Banking > Transaction

Select [Accounts] tab > [Clear all] button, and check the account "401k account"

Select [Tags] tab > [Clear all] button, and check the tags "Roth" and "Traditional"

Press the [Show Report] button

Select the [Date range: Year to date v] pick the [Custom to Date], press [OK]

a tabulate report will appear with only the tagged transactions for the account chosen.

This is a work around.

The important parts are the "/Roth" and "/Tradition" tag creation and appending to the Paycheck Cash Transfer Transaction type, not all Transaction types support tags.

This workaround does not support the Tax Planning or Forecasting features of Quicken, it allows you to manually track contribution types and reconcile with some retirement plan reports.

I find it better than nothing.

A more Robust solution would be appreciated.

5/11/2024

Windows XP Mode on Win7 with VirtualBox

 Windows XP Mode was a freely activated copy of Windows XP from 2001 that ran on Windows 7 Pro and Win 7 Ultimate in the old Connectix Virtual PC. Microsoft acquired Connectix Virtual PC and made it into a a standalone installation package which had to be installed separately from an installer that contained a Windows VHD image of a Windows XP machine called Windows XP Mode.

Windows XP Mode did not need to be activated online, since it relied upon a new version of Activation called OEM BIOS Locking.

The Microsoft Virtual PC software has a form of virtual BIOS which contains the activation key for Windows XP Mode, so after installation was complete within the Virtual PC instance it would autoactivate, or already be activated.

VirtualBox is a slightly more advanced virtual machine kit which comes from Oracle, but also runs on many Windows, Linux and MacOSX and MacOS platforms.

VirtualBox also has a way of loading a BIOS image if dumped from a running systems memory using a tool like SLIC Toolkit. By modifying the dumped image and adjusting the Virtual Machine Settings using the VBoxmanage.exe tool to load it.. the Windows XP Mode image can be loaded into Virtualbox on not only Windows, but Linux, MacOSX and MacOS.. 

The Windows XP Mode VHD must be converted first however using the VBoxmanage tool to clonehd the image and export it as format VDI.

The placement of the BIOS activation string within the modified BIOS dump also moves around slightly from VBox 4.0 to 5.1-5.22 to 6.0 by a single or more bytes. The BIOS is compiled differently for each version of VBox. This technique is known to work on those versions, but the latest version is 7.0 and it is not known if it can still be made to work on that version.

VirtualBox is also know for supporting USB pass thru and offers a more robust long term way of supporting XP SP3 as activated on more varied and modern os platforms in the current year.

3/11/2024

DV 4:1:1 and 320x240 NTSC Video Capture

Sampling 720 x 480 over an actual 320x240 full color picture.

320 x 2 = 640

240 x 2 =480

640 x 480 : 720 x 480 is over fit more than 2:1

Color Alone 160 x 120 : 720 x 480 is over fit more than 4:1

 

(sencore)

320x240 : 160x120 = Luma: Chroma

4:1 from 720 x 480 is a Perfect fit for full color capture

NTSC is field based so has more horizontal than vertical information per unit of time

"mixing" fields to "simulate" Progressive images is incorrect, artifacting is inevitable

DV is frame based storage it "does" compress the interlaced video into progressive frames.

4:1:1 more properly captures 100 percent of the Luma, Chroma and Temporal resolution without distortion

Even if capturing a theoretical 400 or 500 TVL, 720x480 is still over sampling and the increased resolution is in the Luma dimension, not the Chroma, bandwidth allocation is fixed.

 

(sencore)

720 x 480 DV 4:1:1 is still more than enough to capture everything available 

The shape of the pixels captured for an NTSC signal are appropriate for the dimensions of the signal information available and skew more towards the horizontal dimension where there is more information.

The shape of the pixels captured for an ATSC signal are appropriate for the dimensions of the signal information available and skew more towards the vertical dimension to encompass the change in format from interlaced to progressive.

4:1:1 DV is appropriate for 4:3 Aspect and 720x480 digital capture

4:2:0 HDV is appropriate for 16:9 Aspect and 1280 x 720 digital capture

in plain simple language, DV video is appropriate for NTSC 4:3 video capture

in plain simple language HDV video is appropriate for NTSC 16:9 video capture

there is a "Reason" why these standards were developed, they are "overfit" for their purpose


While "live" Broadcast can in theory exceed what can be stored on Video tape in many cases, most of that available on VHS never stored the maximum available and it is already lost.

1/07/2024

Using M4B Audiobook files in Windows 7

Apple basically came up with the MPEG-4 container format MP4 but also came up with the M4B to host audiobooks in AAC format with Artwork and tags of information about the books.

Windows supports M4A format files with basically most of the same functions for storing AAC and Artwork and tags of information, but do not contain the ability to store Chapters or a Bookmark as in an M4B file format.

Within Apple the iTunes program properly handles M4B format and exposes Chapter navigation and stores the last played position as a bookmark.

On Windows the iTunes for Windows program does much the same thing.

However probably the best M4B file format "viewer" or audiobook playback is found with VLC - Video Lan Client 2.2.6 "Umbrella"

In VLC its possible to navigate the chapter marks on the playback timeline as they show up as short vertical grey lines across the bottom of the timeline.

The Playback menu has a complete Chapter menu for jumping specifically to any chapter.

And Custom Bookmarks can be created and written to the M4B file and then referred to so that Playback could jump to a specific Custom Bookmark.



VLC has an xml based Playlist system and a concept for a Media Library that deviates a little from Apple iTunes and Windows Media Player.

First there is the "Media Library" Playlist, disabled by default. It is a special xml playlist stored in the folder with other user interface configuration options; 

Example:

C:\Users\jwillis\AppData\Roaming\vlc\ml.xspf

It gets created by turning on the feature under;

Tools> Preferences >"Show Settings -  [x] All 

Then traveling down to branch [+] Playlist and checking > Use media library

The ml.xspf file gets populated by one of two ways:

1. right clicking with a mouse in the main window and selecting + files or +folders

2. by drag and dropping files or folders on the main window

Then shutting down the VLC client and restarting it will have automatically saved those choices in the ml.xspf file and reload them in the > "Media Library" branch of the [Media Library]

note: VLC will continue to default to loading nothing and focus there on start up, you have to click on the Media Library / Media Library in order to see that it saved your previous media choices.

You can default the Playlist under Media Library / Playlist to refer to a personal xml format .xspf file, but it will not open it.. unless you set the "Default stream" option under:

Tools> Preferences >"Show Settings -  [x] All 

Then traveling down to branch [+] Playlist and filling out "Default stream [ ________ ]

With a specially formatted  "Reverse slash" path prefixed with a file: operator like this -

file:///C:/Users/jwillis/AppData/Roaming/vlc/ml.xspf

And checkboxes that include "Auto start"

But that will also immediately start playing the Playlist.

If you do not it will offer you the choice to open the xspf file to list the choices, but it will not by default display the contents unless clicked upon.

Using the other method with Media Library is frankly closer to what you would expect, you just have to remember to travel to the folder under Playlist to see the most recently saved collection of media.