Send Motion-user mailing list submissions to
        motion-user@lists.sourceforge.net

To subscribe or unsubscribe via the World Wide Web, visit
        https://lists.sourceforge.net/lists/listinfo/motion-user
or, via email, send a message with subject or body 'help' to
        motion-user-requ...@lists.sourceforge.net

You can reach the person managing the list at
        motion-user-ow...@lists.sourceforge.net

When replying, please edit your Subject line so it is more specific
than "Re: Contents of Motion-user digest..."


Today's Topics:

   1. video processing when detecting motion (Hamza Mogni)
   2. Re: video processing when detecting motion (MrDave)
   3. Re: video processing when detecting motion (Hamza Mogni)


----------------------------------------------------------------------

Message: 1
Date: Fri, 17 Feb 2023 15:58:45 +0100
From: Hamza Mogni <hamzamog...@gmail.com>
To: motion-user@lists.sourceforge.net
Subject: [Motion-user] video processing when detecting motion
Message-ID:
        <CAAVsVPTmuGimkZ-7mPwsiX=hheyopsoyw2gino4nmemg9wj...@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"

Hello,

I am using motion to detect and record movement on a video stream, however,
there is text that appears on videos that I absolutely want to hide.

I have trained a YOLO ML model to detect text. For now, my solution is to
process the video after it is recorded (another process reads the video and
does the inferencing to detect and hide text). Now I don't know if my way
to do it is the right approach or if there is a simpler and more efficient
way.

My question is if there is a way to do this natively with motion, a way to
send pictures to another process to hide text (draw polygons over text) and
return it to motion to store it in the video.

Can I do that?

Thank you in advance.
[image: photo]
*Hamza Mogni*

+212 649 10 21 61 <+212+649+10+21+61>
Tangier, Morocco
<http://github.com/hamzamogni> <http://linkedin.com/in/hamza-mogni>
<http://facebook.com/hmogni>
-------------- next part --------------
An HTML attachment was scrubbed...

------------------------------

Message: 2
Date: Fri, 17 Feb 2023 08:24:10 -0700
From: MrDave <motionmrd...@gmail.com>
To: motion-user@lists.sourceforge.net
Subject: Re: [Motion-user] video processing when detecting motion
Message-ID: <f6e9dc8e-9d75-762c-908a-05a8056b5...@gmail.com>
Content-Type: text/plain; charset="utf-8"; Format="flowed"

If the video is created via the Passthrough option of Motion, the answer 
is no.? That process just takes the source and puts it out to a file.? 
If you do not use the passthrough option, you can create a 
mask_privacy.? This was added so that users could block out the 
neighbors or anything else on the saved pictures and videos.? The 
requirement however is that the text must always be in the same location 
on the image.


On 2/17/2023 7:58 AM, Hamza Mogni wrote:
> Hello,
>
> I am using motion to detect and record movement on a video stream, 
> however, there is text that appears on videos that I absolutely want 
> to hide.
>
> I have trained a YOLO ML model to detect text. For now, my solution is 
> to process the video after it is recorded (another process reads the 
> video and does the inferencing to detect and hide text). Now I don't 
> know if my way to do it is the right approach or if there is a simpler 
> and more efficient way.
>
> My question is if there is a way to do this natively with motion, a 
> way to send pictures to another process to hide text (draw polygons 
> over text) and return it to motion to store it in the video.
>
> Can I do that?
>
> Thank you in advance.
> photo         
>       
> *Hamza Mogni*
>
> +212 649 10 21 61 <tel:+212+649+10+21+61>
>
> Tangier, Morocco
>
> <http://github.com/hamzamogni>        <http://linkedin.com/in/hamza-mogni> 
> <http://facebook.com/hmogni>
>
>
>
>
> _______________________________________________
> Motion-user mailing list
> Motion-user@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/motion-user
> https://motion-project.github.io/
>
> Unsubscribe:https://lists.sourceforge.net/lists/options/motion-user
-------------- next part --------------
An HTML attachment was scrubbed...

------------------------------

Message: 3
Date: Fri, 17 Feb 2023 16:46:01 +0100
From: Hamza Mogni <hamzamog...@gmail.com>
To: Motion discussion list <motion-user@lists.sourceforge.net>
Subject: Re: [Motion-user] video processing when detecting motion
Message-ID:
        <CAAVsVPSv1pGP=AmTe9ssxLBnipX_GmvK2CErQsE=h_bpk+4...@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"

thanks for your reply. I am not using the Passthrough option. And I am
already using mask_privacy to hide parts of the video. But the text I want
to hide appears now right in the middle of the screen (parts I want to show
on the video)... I want to hide only the text but still show the area.
[image: photo]
*Hamza Mogni*

+212 649 10 21 61 <+212+649+10+21+61>
Tangier, Morocco
<http://github.com/hamzamogni> <http://linkedin.com/in/hamza-mogni>
<http://facebook.com/hmogni>


On Fri, 17 Feb 2023 at 16:26, MrDave <motionmrd...@gmail.com> wrote:

> If the video is created via the Passthrough option of Motion, the answer
> is no.  That process just takes the source and puts it out to a file.  If
> you do not use the passthrough option, you can create a mask_privacy.  This
> was added so that users could block out the neighbors or anything else on
> the saved pictures and videos.  The requirement however is that the text
> must always be in the same location on the image.
>
>
> On 2/17/2023 7:58 AM, Hamza Mogni wrote:
>
> Hello,
>
> I am using motion to detect and record movement on a video stream,
> however, there is text that appears on videos that I absolutely want to
> hide.
>
> I have trained a YOLO ML model to detect text. For now, my solution is to
> process the video after it is recorded (another process reads the video and
> does the inferencing to detect and hide text). Now I don't know if my way
> to do it is the right approach or if there is a simpler and more efficient
> way.
>
> My question is if there is a way to do this natively with motion, a way to
> send pictures to another process to hide text (draw polygons over text) and
> return it to motion to store it in the video.
>
> Can I do that?
>
> Thank you in advance.
> [image: photo]
> *Hamza Mogni*
>
> +212 649 10 21 61 <+212+649+10+21+61>
> Tangier, Morocco
> <http://github.com/hamzamogni> <http://linkedin.com/in/hamza-mogni>
> <http://facebook.com/hmogni>
>
>
>
> _______________________________________________
> Motion-user mailing 
> listMotion-user@lists.sourceforge.nethttps://lists.sourceforge.net/lists/listinfo/motion-userhttps://motion-project.github.io/
>
> Unsubscribe: https://lists.sourceforge.net/lists/options/motion-user
>
> _______________________________________________
> Motion-user mailing list
> Motion-user@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/motion-user
> https://motion-project.github.io/
>
> Unsubscribe: https://lists.sourceforge.net/lists/options/motion-user
-------------- next part --------------
An HTML attachment was scrubbed...

------------------------------



------------------------------

Subject: Digest Footer

_______________________________________________
Motion-user mailing list
Motion-user@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/motion-user


------------------------------

End of Motion-user Digest, Vol 198, Issue 7
*******************************************

Reply via email to