# Enquiry about parameter meaning in ZED360

**URL:** <https://community.stereolabs.com/t/enquiry-about-parameter-meaning-in-zed360/10712>\
**Category:** Unity\
**Tags:** python, depth\
**Created:** [January 29, 2026, 6:35am UTC](https://community.stereolabs.com/t/enquiry-about-parameter-meaning-in-zed360/10712 "2026-01-29T06:35:17Z")\
**Posts on this page:** 6\
**Page:** 1

<div class="post-metadata">

**Author:** ![waystogetthere](https://community.stereolabs.com/user_avatar/community.stereolabs.com/waystogetthere/32/5710_2.png) [@waystogetthere](https://community.stereolabs.com/u/waystogetthere)\
**Post date:** [January 29, 2026, 6:35am UTC](https://community.stereolabs.com/t/enquiry-about-parameter-meaning-in-zed360/10712/1 "2026-01-29T06:35:18Z")

</div>

Hi Zed Team,

Recently I’ve been using **ZED360** , and I noticed that the documentation of this app ([https://www.stereolabs.com/docs/fusion/zed360](https://www.stereolabs.com/docs/fusion/zed360)) seems to correspond to an older version of ZED360.  
In the newer version, some options have been added to the UI, but there is no explanation of what these options actually mean.

 ![zed360-ui](https://community.stereolabs.com/uploads/default/original/2X/b/b17493901215edc1e28f9b3e8cdf66e32dbf37d9.jpeg)

(1) What does **Flip Camera** mean? I see that it has three options: _Auto_, _On_, and _Off_.

(2) For **Depth Modes** , I see _Ultra_ and _Neural_ in ZED360. However, according to the official depth modes documentation  
([https://www.stereolabs.com/docs/depth-sensing/depth-modes](https://www.stereolabs.com/docs/depth-sensing/depth-modes?utm_source=chatgpt.com)), the depth modes are _Neural Light_, _Neural_, and _Neural Plus_.  
Are the depth modes in ZED360 the same as the official depth modes?  
Is _Ultra_ equivalent to _Neural Plus_, is this a naming mismatch?

(3) For **Detection Threshold** , my intuitive understanding is that a higher value makes the algorithm more strict, and therefore less likely to produce false positives, such as detecting non-human objects as a human.  
Is this understanding correct?

(4) The **Body Model** setting has three modes: _Accurate_, _Medium_, and _Fast_.  
How does this setting affect the calibration result?  
Does _Accurate_ detect more human joints, while _Fast_ simply runs the body detection faster?

It seems that the ZED360 documentation lacks explanations for these parameters.  
It would be great if the documentation could be updated to cover the new version of ZED360.

---

<div class="post-metadata">

**Author:** ![Myzhar](https://community.stereolabs.com/user_avatar/community.stereolabs.com/myzhar/32/11_2.png) [@Myzhar](https://community.stereolabs.com/u/Myzhar)\
**Post date:** [January 29, 2026, 4:49pm UTC](https://community.stereolabs.com/t/enquiry-about-parameter-meaning-in-zed360/10712/2 "2026-01-29T16:49:50Z")

</div>

> [@waystogetthere](#):
>
> (1) What does **Flip Camera** mean? I see that it has three options: _Auto_, _On_, and _Off_.

This reflects this parameter of the ZED SDK API: [Video Module | API Reference | Stereolabs](https://www.stereolabs.com/docs/api/group __Video__ group.html#gafe09520beed3f2eba620708468d0eca6)

> [@waystogetthere](#):
>
> (2) For **Depth Modes** , I see _Ultra_ and _Neural_ in ZED360. However, according to the official depth modes documentation  
> ([https://www.stereolabs.com/docs/depth-sensing/depth-modes](https://www.stereolabs.com/docs/depth-sensing/depth-modes?utm_source=chatgpt.com)), the depth modes are _Neural Light_, _Neural_, and _Neural Plus_.  
> Are the depth modes in ZED360 the same as the official depth modes?

`ULTRA` is deprecated with the ZED SDK v5.

> [@waystogetthere](#):
>
> Is _Ultra_ equivalent to _Neural Plus_, is this a naming mismatch?

No, ULTRA mode is not based on AI processing.

> [@waystogetthere](#):
>
> (3) For **Detection Threshold** , my intuitive understanding is that a higher value makes the algorithm more strict, and therefore less likely to produce false positives, such as detecting non-human objects as a human.  
> Is this understanding correct?

Yes: [BodyTrackingRuntimeParameters Struct Reference | API Reference | Stereolabs](https://www.stereolabs.com/docs/api/structsl_1_1BodyTrackingRuntimeParameters.html#aba4f4811a42c6d273a629b35c0f2889e)

> [@waystogetthere](#):
>
> (4) The **Body Model** setting has three modes: _Accurate_, _Medium_, and _Fast_.  
> How does this setting affect the calibration result?  
> Does _Accurate_ detect more human joints, while _Fast_ simply runs the body detection faster?

You can read more regarding the behaviors of the 3 models in the documentation:

> **[Body Tracking Module | API Reference | Stereolabs](https://www.stereolabs.com/docs/api/group __Body__ group.html#ga9714cbebb0c371ae37f1cac57661029f)**
>
> Report the actual inference precision used.

---

<div class="post-metadata">

**Author:** ![Myzhar](https://community.stereolabs.com/user_avatar/community.stereolabs.com/myzhar/32/11_2.png) [@Myzhar](https://community.stereolabs.com/u/Myzhar)\
**Post date:** [January 29, 2026, 4:50pm UTC](https://community.stereolabs.com/t/enquiry-about-parameter-meaning-in-zed360/10712/3 "2026-01-29T16:50:15Z")

</div>

> [@waystogetthere](#):
>
> It seems that the ZED360 documentation lacks explanations for these parameters.

We are going to update it soon

---

<div class="post-metadata">

**Author:** ![waystogetthere](https://community.stereolabs.com/user_avatar/community.stereolabs.com/waystogetthere/32/5710_2.png) [@waystogetthere](https://community.stereolabs.com/u/waystogetthere)\
**Post date:** [January 30, 2026, 2:15am UTC](https://community.stereolabs.com/t/enquiry-about-parameter-meaning-in-zed360/10712/4 "2026-01-30T02:15:25Z")

</div>

Hi @Myzhar ,

Thanks for the detailed explanation — that clarifies most of my questions.

I still have one remaining question regarding **depth modes** :

Since **`ULTRA` is deprecated in SDK versions \> 5.x** , does this mean that for **ZED360** we are now expected to **only use the NEURAL**?

Thanks in advance for the clarification.

---

<div class="post-metadata">

**Author:** ![waystogetthere](https://community.stereolabs.com/user_avatar/community.stereolabs.com/waystogetthere/32/5710_2.png) [@waystogetthere](https://community.stereolabs.com/u/waystogetthere)\
**Post date:** [January 30, 2026, 2:15am UTC](https://community.stereolabs.com/t/enquiry-about-parameter-meaning-in-zed360/10712/5 "2026-01-30T02:15:38Z")

</div>

Thanks that will be very helpful!

---

<div class="post-metadata">

**Author:** ![Myzhar](https://community.stereolabs.com/user_avatar/community.stereolabs.com/myzhar/32/11_2.png) [@Myzhar](https://community.stereolabs.com/u/Myzhar)\
**Post date:** [January 30, 2026, 9:49am UTC](https://community.stereolabs.com/t/enquiry-about-parameter-meaning-in-zed360/10712/6 "2026-01-30T09:49:39Z")

</div>

> [@waystogetthere](#):
>
> Since **`ULTRA` is deprecated in SDK versions \> 5.x** , does this mean that for **ZED360** we are now expected to **only use the NEURAL**?

Yes, all the “classic” depth processing methods based on Stereo Matching in v5 have been replaced by AI-based depth estimation methods, NEURAL\_LIGHT, NEURAL, and NEURAL\_PLUS.

The new methods provide denser and more accurate depth maps, with similar load requirements.
